https://doi.org/10.5281/zenodo.20677995
references.bib
@article{Hernan2004,
doi = {10.1136/jech.2002.006361},
url = {https://pubmed.ncbi.nlm.nih.gov/15026432 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1732737/},
issn = {0143-005X},
year = {2004},
month = {4},
pages = {265--271},
title = {A definition of causal effect for epidemiological research},
author = {Hern{\'{a}}n, M A},
number = {4},
volume = {58},
journal = {Journal of epidemiology and community health},
keywords = {*Causality, *Epidemiologic Studies, Humans, Randomized Controlled Trials as Topic/*standards, Research Design/standards},
language = {eng},
publisher = {BMJ Group}}
@article{Horvitz1952,
doi = {10.2307/2280784},
issn = {01621459},
year = {1952},
month = {12},
pages = {663},
title = {A Generalization of Sampling Without Replacement From a Finite Universe},
author = {Horvitz, D. G. and Thompson, D. J.},
number = {260},
volume = {47},
journal = {Journal of the American Statistical Association},
publisher = {JSTOR}}
@article{Efron1983,
year = {1983},
pages = {36--48},
title = {A leisurely look at the bootstrap, the jackknife, and cross-validation},
author = {Efron, Bradley and Gong, Gail},
number = {1},
volume = {37},
journal = {The American Statistician},
publisher = {Taylor {\&}amp; Francis}}
@article{Robins1986,
doi = {https://doi.org/10.1016/0270-0255(86)90088-6},
url = {http://www.sciencedirect.com/science/article/pii/0270025586900886},
isbn = {0270-0255},
year = {1986},
pages = {1393--1512},
title = {A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect},
author = {Robins, James},
number = {9},
volume = {7},
journal = {Mathematical Modelling}}
@article{Oehlert1992,
doi = {10.1080/00031305.1992.10475842},
issn = {15372731},
year = {1992},
pages = {27--29},
title = {A note on the delta method},
author = {Oehlert, Gary W.},
number = {1},
volume = {46},
journal = {American Statistician},
keywords = {Approximate moments, Asymptotic approximation, Taylor series}}
@article{Levy2018,
url = {https://arxiv.org/pdf/1811.04573.pdf},
year = {2018},
title = {An Easy Implementation of CV-TMLE},
author = {Levy, Jonathan},
journal = {arXiv}}
@book{Efron1993,
url = {http://www.loc.gov/catdir/enhancements/fy0730/93004489-d.html},
isbn = {0412042312},
year = {1993},
title = {An introduction to the bootstrap},
author = {Efron, Bradley and Tibshirani, Robert},
volume = {57},
address = {New York},
publisher = {Chapman {\&} Hall}}
@book{Agresti2010,
isbn = {9780470082898 (cloth)},
year = {2010},
title = {Analysis of ordinal categorical data},
author = {Agresti, Alan},
address = {Hoboken, N.J.},
publisher = {Wiley}}
@article{Robins1999,
doi = {10.2307/20118224},
url = {https://www.jstor.org/stable/20118224 http://www.jstor.org/stable/20118224},
year = {1999},
pages = {151--179},
title = {Association, Causation, and Marginal Structural Models},
author = {Robins, James M.},
number = {1/2},
volume = {121},
journal = {Synthese},
publisher = {Springer}}
@book{Vaart1998,
url = {http://www.loc.gov/catdir/toc/cam024/98015176.html},
isbn = {0521496039 (hardcover)},
year = {1998},
title = {Asymptotic statistics},
author = {Vaart, A W van der},
address = {Cambridge, UK},
publisher = {Cambridge University Press}}
@article{Austin2009BalanceSamples,
doi = {10.1002/sim.3697},
url = {/pmc/articles/PMC3472075/ /pmc/articles/PMC3472075/?report=abstract https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3472075/},
issn = {02776715},
pmid = {19757444},
year = {2009},
pages = {3083--3107},
title = {Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples},
author = {Austin, Peter C},
number = {25},
volume = {28},
journal = {Statistics in Medicine},
keywords = {Balance, Bias, Goodness-of-fit, Matching, Observational study, Propensity score, Propensity-score matching, Standardized difference},
publisher = {Wiley-Blackwell}}
@article{article,
doi = {10.1214/09-SS057},
year = {2009},
pages = {96--146},
title = {Causal Inference in Statistics: An Overview},
author = {Pearl, Judea},
volume = {3},
journal = {Statistics Surveys}}
@article{Rubin2011,
url = {http://dx.doi.org/10.1198/016214504000001880},
year = {2005},
pages = {322--331},
title = {Causal inference using potential outcomes},
author = {Rubin, Donald B},
number = {469},
volume = {100},
journal = {Journal of the American Statistical Association},
publisher = {Taylor {\&}amp; Francis}}
@article{Naimi2017,
url = {http://arxiv.org/abs/1711.07137},
year = {2017},
month = {11},
title = {Challenges in Obtaining Valid Causal Effect Estimates with Machine Learning
Algorithms},
author = {Naimi, Ashley I and Mishler, Alan E and Kennedy, Edward H},
arxivid = {1711.07137},
journal = {arXiv},
keywords = {causal inference, doubly-robust estimation, epidemiologic methods, machine
learning, nonparametric methods, semiparametric theory}}
@article{Naimi2017b,
url = {http://arxiv.org/abs/1711.07137},
year = {2017},
title = {Challenges in Obtaining Valid Causal Effect Estimates with Machine Learning Algorithms},
author = {Naimi, Ashley I and Mishler, Alan E and Kennedy, Edward H},
arxivid = {1711.07137},
journal = {arXiv},
keywords = {causal inference, doubly-robust estimation, epidemiologic methods, machine learning, nonparametric methods, semiparametric theory}}
@article{Jung2019,
doi = {10.3389/fpsyg.2019.02215},
url = {https://www.frontiersin.org/article/10.3389/fpsyg.2019.02215/full},
issn = {1664-1078},
year = {2019},
month = {10},
pages = {2215},
title = {Comparison of Bootstrap Confidence Interval Methods for GSCA Using a Monte Carlo Simulation},
author = {Jung, Kwanghee and Lee, Jaehoon and Gupta, Vibhuti and Cho, Gyeongcheol},
volume = {10},
journal = {Frontiers in Psychology},
keywords = {Monte Carlo simulation, bootstrap methods, confidence intervals, generalized structured component analysis (GSCA), structural equation modeling (SEM)},
publisher = {Frontiers Media S.A.}}
@article{Jung2019b,
doi = {10.3389/fpsyg.2019.02215},
url = {https://www.frontiersin.org/article/10.3389/fpsyg.2019.02215/full},
issn = {1664-1078},
year = {2019},
pages = {2215},
title = {Comparison of Bootstrap Confidence Interval Methods for GSCA Using a Monte Carlo Simulation},
author = {Jung, Kwanghee and Lee, Jaehoon and Gupta, Vibhuti and Cho, Gyeongcheol},
volume = {10},
journal = {Frontiers in Psychology},
keywords = {Monte Carlo simulation, bootstrap methods, confidence intervals, generalized structured component analysis (GSCA), structural equation modeling (SEM)},
publisher = {Frontiers Media S.A.}}
@misc{Cole2008,
doi = {10.1093/aje/kwn164},
url = {https://academic.oup.com/aje/article/168/6/656/88658},
issn = {00029262},
pmid = {18682488},
year = {2008},
month = {9},
pages = {656--664},
title = {Constructing inverse probability weights for marginal structural models},
author = {Cole, Stephen R. and Hern{\'{a}}n, Miguel A.},
number = {6},
volume = {168},
keywords = {Bias (epidemiology), Causality, Confounding factors (epidemiology), Probability weighting, Regression model},
booktitle = {American Journal of Epidemiology},
publisher = {Oxford Academic}}
@misc{Cole2008b,
doi = {10.1093/aje/kwn164},
url = {https://academic.oup.com/aje/article/168/6/656/88658},
issn = {00029262},
pmid = {18682488},
year = {2008},
pages = {656--664},
title = {Constructing inverse probability weights for marginal structural models},
author = {Cole, Stephen R and Hern{\'{a}}n, Miguel A},
number = {6},
volume = {168},
keywords = {Bias (epidemiology), Causality, Confounding factors (epidemiology), Probability weighting, Regression model},
booktitle = {American Journal of Epidemiology},
publisher = {Oxford Academic}}
@misc{Cole2008ConstructingModels,
doi = {10.1093/aje/kwn164},
url = {https://academic.oup.com/aje/article/168/6/656/88658},
issn = {00029262},
pmid = {18682488},
year = {2008},
pages = {656--664},
title = {Constructing inverse probability weights for marginal structural models},
author = {Cole, Stephen R and Hern{\'{a}}n, Miguel A},
number = {6},
volume = {168},
keywords = {Bias (epidemiology), Causality, Confounding factors (epidemiology), Probability weighting, Regression model},
booktitle = {American Journal of Epidemiology},
publisher = {Oxford Academic}}
@article{Luque-Fernandez2018Data-AdaptivePresentation,
doi = {10.1093/aje/kwx317},
url = {https://pubmed.ncbi.nlm.nih.gov/29020131/},
issn = {14766256},
pmid = {29020131},
year = {2018},
pages = {871--878},
title = {Data-Adaptive Estimation for Double-Robust Methods in Population-Based Cancer Epidemiology: Risk Differences for Lung Cancer Mortality by Emergency Presentation},
author = {Luque-Fernandez, Miguel Angel and Belot, Aurélien and Valeri, Linda and Cerulli, Giovanni and Maringe, Camille and Rachet, Bernard},
number = {4},
volume = {187},
journal = {American Journal of Epidemiology},
keywords = {cancer epidemiology, causality, machine learning, population-based data, statistics, targeted maximum likelihood estimation},
publisher = {Oxford University Press}}
@article{Luque-Fernandez2020,
year = {2020},
title = {Delta Method in Epidemiology: An Applied and Reproducible Tutorial},
author = {Luque-Fernandez, M A},
journal = {GitHub repository}}
@article{Kang2007,
doi = {10.1214/07-STS227},
url = {https://projecteuclid.org/euclid.ss/1207580167 http://www.jstor.org/stable/27645858},
issn = {08834237},
year = {2007},
month = {11},
pages = {523--539},
title = {Demystifying Double Robustness: A Comparison of Alternative Strategies for Estimating a Population Mean from Incomplete Data},
author = {Tsiatis, Anastasios A and Davidian, Marie and Kang, Joseph D.Y. Y and Schafer, Joseph L.},
number = {4},
volume = {22},
journal = {Statistical Science},
keywords = {Causal inference, Missing data, Model-assisted survey estimation, Propensity score, Weighted estimating equations},
publisher = {Institute of Mathematical Statistics}}
@article{Bang2005,
year = {2005},
pages = {962--973},
title = {Doubly robust estimation in missing data and causal inference models},
author = {Bang, Heejung and Robins, James M},
number = {4},
volume = {61},
journal = {Biometrics},
publisher = {Wiley Online Library}}
@article{doi:10.2105/AJPH.2018.304916,
doi = {10.2105/AJPH.2018.304916},
url = {https://doi.org/10.2105/AJPH.2018.304916},
year = {2019},
pages = {e12-e13},
title = {Effect Modification and Collapsibility in Evaluations of Public Health Interventions},
author = {Luque-Fernandez, Miguel Angel and Redondo-Sanchez, Daniel and Schomaker, Michael},
number = {3},
volume = {109},
journal = {American Journal of Public Health}}
@book{Herberg1962,
year = {1962},
title = {Elementary mathematical analysis},
author = {Herberg, Theodore and Bristol, James D},
address = {Boston},
publisher = {Heath}}
@book{Armitage2005,
url = {http://www.loc.gov/catdir/toc/ecip054/2004028292.html},
isbn = {047084907X (set : cloth)},
year = {2005},
title = {Encyclopedia of biostatistics},
author = {Armitage, P and Colton, Theodore},
address = {Chichester, West Sussex, England},
publisher = {John Wiley}}
@book{Boos2013,
isbn = {9781461448174 (hdbk.)},
year = {2013},
title = {Essential statistical inference: theory and methods},
author = {Boos, Dennis D and Stefanski, L A},
publisher = {Springer}}
@article{Rubin1974,
year = {1974},
pages = {688},
title = {Estimating causal effects of treatments in randomized and nonrandomized studies.},
author = {Rubin, Donald B},
number = {5},
volume = {66},
journal = {Journal of educational Psychology},
publisher = {American Psychological Association}}
@article{Gutman2015,
year = {2015},
month = {11},
pages = {3381--3398},
title = {Estimation of causal effects of binary treatments in unconfounded studies},
author = {Gutman, Roee and Rubin, Donald B},
number = {26},
volume = {34},
journal = {Stat Med},
keywords = {Rubin causal model, causal inference, multiple imputation, propensity score, spline, subgroup analysis}}
@article{Gutman2015b,
year = {2015},
month = {11},
pages = {3381--3398},
title = {Estimation of causal effects of binary treatments in unconfounded studies},
author = {Gutman, Roee and Rubin, Donald B},
number = {26},
volume = {34},
journal = {Stat Med},
keywords = {Rubin causal model, causal inference, multiple imputation, propensity score, spline, subgroup analysis}}
@article{Robins1994,
url = {http://www.jstor.org/stable/2290910},
year = {1994},
pages = {846--866},
title = {Estimation of Regression Coefficients When Some Regressors Are Not Always Observed},
author = {Robins, James M and Rotnitzky, Andrea and Zhao, Lue Ping},
number = {427},
volume = {89},
journal = {Journal of the American Statistical Association},
publisher = {[American Statistical Association, Taylor {\&} Francis, Ltd.]}}
@article{Goetghebeur2020FormulatingAnswers,
doi = {10.1002/sim.8741},
url = {www.ofcaus.org},
issn = {10970258},
pmid = {32964526},
year = {2020},
pages = {4922--4948},
title = {Formulating causal questions and principled statistical answers},
author = {Goetghebeur, Els and le Cessie, Saskia and De Stavola, Bianca and Moodie, Erica E M and Waernbaum, Ingeborg},
number = {30},
volume = {39},
arxivid = {1906.12100},
journal = {Statistics in Medicine},
keywords = {causation, instrumental variable, inverse probability weighting, matching, potential outcomes, propensity score},
publisher = {John Wiley and Sons Ltd}}
@techreport{Dominici,
url = {https://www.goodreads.com/shelf/show/causality},
title = {FROM CONTROLLED TO UNDISCIPLINED DATA: ESTIMATING CAUSAL EFFECTS IN THE ERA OF DATA SCIENCE USING A POTENTIAL OUTCOME FRAMEWORK},
author = {Dominici, Francesca and Bargagli-Stoffi, Falco J and Mealli, Fabrizia},
arxivid = {2012.06865v1}}
@techreport{Dominicib,
url = {https://www.goodreads.com/shelf/show/causality},
title = {FROM CONTROLLED TO UNDISCIPLINED DATA: ESTIMATING CAUSAL EFFECTS IN THE ERA OF DATA SCIENCE USING A POTENTIAL OUTCOME FRAMEWORK},
author = {Dominici, Francesca and Bargagli-Stoffi, Falco J and Mealli, Fabrizia},
arxivid = {2012.06865v1}}
@book{Buhlmann2016,
year = {2016},
title = {Handbook of big data},
author = {B{\"{u}}hlmann, Peter and Drineas, Petros and van der Laan, Mark and Kane, Michael},
publisher = {CRC Press}}
@article{Greenland1986,
year = {1986},
pages = {413--419},
title = {Identifiability, exchangeability, and epidemiological confounding},
author = {Greenland, Sander and Robins, James M},
number = {3},
volume = {15},
journal = {International journal of epidemiology},
publisher = {IEA}}
@article{Greenland2015,
doi = {10.1007/s10654-015-9995-7},
url = {https://link.springer.com/article/10.1007/s10654-015-9995-7},
issn = {15737284},
pmid = {25687168},
year = {2015},
month = {10},
pages = {1101--1110},
title = {Limitations of individual causal models, causal graphs, and ignorability assumptions, as illustrated by random confounding and design unfaithfulness},
author = {Greenland, Sander and Mansournia, Mohammad Ali},
number = {10},
volume = {30},
journal = {European Journal of Epidemiology},
keywords = {Causal graphs, Confounding, Directed acyclic graphs, Ignorability, Inverse probability weighting, Unfaithfulness},
publisher = {Springer Netherlands}}
@article{Zivich2020,
url = {http://arxiv.org/abs/2004.10337},
year = {2020},
month = {4},
title = {Machine learning for causal inference: on the use of cross-fit estimators},
author = {Zivich, Paul N and Breskin, Alexander},
arxivid = {2004.10337},
journal = {arXiv}}
@article{Zivich2020b,
url = {http://arxiv.org/abs/2004.10337},
year = {2020},
title = {Machine learning for causal inference: on the use of cross-fit estimators},
author = {Zivich, Paul N and Breskin, Alexander},
arxivid = {2004.10337},
journal = {arXiv}}
@article{Robins2000,
url = {https://journals.lww.com/epidem/Fulltext/2000/09000/Marginal_Structural_Models_and_Causal_Inference_in.11.aspx},
issn = {1044-3983},
year = {2000},
title = {Marginal Structural Models and Causal Inference in Epidemiology},
author = {Robins, James M and Hern{\'{a}}n, Miguel Ángel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
keywords = {causality, confounding, counterfactuals, epidemiologic methods, intermediate variables, longitudinal data, structural models}}
@article{Robins_2000,
doi = {10.1097/00001648-200009000-00011},
url = {http://dx.doi.org/10.1097/00001648-200009000-00011},
issn = {1044-3983},
year = {2000},
month = {9},
pages = {550--560},
title = {Marginal Structural Models and Causal Inference in Epidemiology},
author = {Robins, James M and Hern{\'{a}}n, Miguel Ángel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
publisher = {Ovid Technologies (Wolters Kluwer Health)}}
@article{Robins_2000b,
doi = {10.1097/00001648-200009000-00011},
url = {http://dx.doi.org/10.1097/00001648-200009000-00011},
issn = {1044-3983},
year = {2000},
month = {9},
pages = {550--560},
title = {Marginal Structural Models and Causal Inference in Epidemiology},
author = {Robins, James M and Hern{\'{a}}n, Miguel Ángel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
publisher = {Ovid Technologies (Wolters Kluwer Health)}}
@article{Robins_2000c,
doi = {10.1097/00001648-200009000-00011},
url = {http://dx.doi.org/10.1097/00001648-200009000-00011},
issn = {1044-3983},
year = {2000},
month = {9},
pages = {550--560},
title = {Marginal Structural Models and Causal Inference in Epidemiology},
author = {Robins, James M and Hern{\'{a}}n, Miguel Ángel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
publisher = {Ovid Technologies (Wolters Kluwer Health)}}
@book{Wolfram1992,
isbn = {020151012X},
year = {1992},
title = {Mathematica reference guide},
author = {Wolfram, Stephen},
address = {Reading, Mass.},
publisher = {Addison-Wesley Pub. Co.}}
@book{Wackerly2002,
year = {2002},
title = {Mathematical Statistics with Applications},
author = {Wackerly, Dennis D and III, William Mendenhall and Scheaffer, Richard L},
publisher = {Duxbury Advanced Series}}
@book{Rothman2008,
url = {http://www.loc.gov/catdir/enhancements/fy0743/2007036316-d.html},
isbn = {9780781755641},
year = {2008},
title = {Modern epidemiology},
author = {Rothman, Kenneth J and Greenland, Sander and Lash, Timothy L},
address = {Philadelphia},
publisher = {Wolters Kluwer Health/Lippincott Williams {\&} Wilkins}}
@misc{Bruin2011,
url = {http://www.ats.ucla.edu/stat/stata/ado/analysis/},
year = {2011},
title = {newtest: command to compute new test @ONLINE},
author = {Bruin, J}}
@article{Kennedy2017,
year = {2017},
pages = {1229--1245},
title = {Non-parametric methods for doubly robust estimation of continuous treatment effects},
author = {Kennedy, Edward H and Ma, Zongming and McHugh, Matthew D and Small, Dylan S},
number = {4},
volume = {79},
journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
publisher = {Wiley Online Library}}
@article{Cai2019,
url = {https://arxiv.org/pdf/1905.10299.pdf},
year = {2019},
title = {Nonparametric Bootstrap Inference for the Targeted Highly Adaptive LASSO Estimator},
author = {Cai, Weixin and van der Laan, Mark}}
@article{Freedman2006,
url = {http://www.jstor.org/stable/27643806},
year = {2006},
pages = {299--302},
title = {On the So-Called "Huber Sandwich Estimator" and "Robust Standard Errors"},
author = {Freedman, David A},
number = {4},
volume = {60},
journal = {The American Statistician},
publisher = {[American Statistical Association, Taylor {\&} Francis, Ltd.]}}
@misc{R2020,
url = {http://www.r-project.org/},
year = {2020},
title = {R: A Language and Environment for Statistical Computing},
author = {R Core Team},
address = {Vienna, Austria},
institution = {R Foundation for Statistical Computing}}
@article{MA2021ReflectionEpidemiologists,
doi = {10.1093/IJE/DYAA260},
url = {https://pubmed.ncbi.nlm.nih.gov/33351919/},
issn = {1464-3685},
pmid = {33351919},
year = {2021},
pages = {346--351},
title = {Reflection on modern methods: demystifying robust standard errors for epidemiologists},
author = {MA, Mansournia and M, Nazemipour and AI, Naimi and GS, Collins and MJ, Campbell},
number = {1},
volume = {50},
journal = {International journal of epidemiology},
keywords = {Cluster Analysis, Epidemiologists*, Humans, MEDLINE, Maryam Nazemipour, Michael J Campbell, Models, Mohammad Ali Mansournia, NCBI, NIH, NLM, National Center for Biotechnology Information, National Institutes of Health, National Library of Medicine, PubMed Abstract, Statistical*, Uncertainty, doi:10.1093/ije/dyaa260, pmid:33351919},
publisher = {Int J Epidemiol}}
@article{Mansournia2020,
doi = {10.1093/ije/dyaa260},
url = {https://academic.oup.com/ije/advance-article/doi/10.1093/ije/dyaa260/6044447},
issn = {0300-5771},
year = {2020},
month = {12},
title = {Reflections on modern methods: demystifying robust standard errors for epidemiologists},
author = {Mansournia, Mohammad Ali and Nazemipour, Maryam and Naimi, Ashley I and Collins, Gary S and Campbell, Michael J},
journal = {International Journal of Epidemiology},
keywords = {Robust standard error, clustering, heteroscedasticity, model-based standard error},
publisher = {Oxford University Press (OUP)}}
@article{Mansournia2020b,
doi = {10.1093/ije/dyaa260},
url = {https://academic.oup.com/ije/advance-article/doi/10.1093/ije/dyaa260/6044447},
issn = {0300-5771},
year = {2020},
title = {Reflections on modern methods: demystifying robust standard errors for epidemiologists},
author = {Mansournia, Mohammad Ali and Nazemipour, Maryam and Naimi, Ashley I and Collins, Gary S and Campbell, Michael J},
journal = {International Journal of Epidemiology},
keywords = {Robust standard error, clustering, heteroscedasticity, model-based standard error},
publisher = {Oxford University Press (OUP)}}
@article{Dorie2019,
url = {http://dx.doi.org/10.1214/18-STS688},
year = {2019},
month = {2},
pages = {94--99},
title = {Rejoinder: Response to Discussions and a Look Ahead},
author = {Dorie, Vincent and Hill, Jennifer and Shalit, Uri and Scott, Marc and Cervone, Dan},
number = {1},
volume = {34},
journal = {Statistical Science},
publisher = {Institute of Mathematical Statistics}}
@inproceedings{Canty,
title = {Resampling Methods in R : The boot Package},
author = {Canty, Angelo J}}
@misc{Kennedy2016,
year = {2016},
pages = {141--167},
title = {Semiparametric theory and empirical processes in causal inference},
author = {Kennedy, Edward H},
booktitle = {Statistical Causal Inferences and Their Applications in Public Health Research},
publisher = {Springer}}
@article{Breiman1996,
year = {1996},
pages = {49--64},
title = {Stacked regressions},
author = {Breiman, Leo},
number = {1},
volume = {24},
journal = {Machine learning},
publisher = {Springer}}
@article{Lunceford2004,
url = {http://dx.doi.org/10.1002/sim.1903},
year = {2004},
pages = {2937--2960},
title = {Stratification and weighting via the propensity score in estimation of causal treatment effects: a comparative study},
author = {Lunceford, Jared K and Davidian, Marie},
number = {19},
volume = {23},
journal = {Statistics in Medicine},
publisher = {John Wiley {\&}amp; Sons, Ltd.}}
@article{van2007,
doi = {10.2202/1544-6115.1309},
url = {https://pubmed.ncbi.nlm.nih.gov/17910531/},
issn = {15446115},
pmid = {17910531},
year = {2007},
month = {9},
title = {Super learner},
author = {Van Der Laan, Mark J. and Polley, Eric C. and Hubbard, Alan E. and der Laan,
Mark J and Polley, Eric C. and Hubbard, Alan E.},
number = {1},
volume = {6},
journal = {Statistical applications in genetics and molecular biology},
keywords = {Cross-validation, Loss-based estimation, Machine learning, Prediction},
publisher = {Berkeley Electronic Press}}
@article{Polley2010,
url = {https://biostats.bepress.com/ucbbiostat/paper266},
year = {2010},
month = {5},
title = {Super Learner In Prediction},
author = {Polley, Eric and Laan, Mark van der},
journal = {U.C. Berkeley Division of Biostatistics Working Paper Series}}
@book{VanderLaan2011,
isbn = {9781441997814 (alk. paper)},
year = {2011},
title = {Targeted learning: causal inference for observational and experimental data},
author = {van der Laan, M J and Rose, Sherri},
address = {New York},
publisher = {Springer Series in Statistics}}
@article{doi:10.1002/sim.7628,
doi = {10.1002/sim.7628},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/sim.7628},
year = {2018},
title = {Targeted maximum likelihood estimation for a binary treatment: A tutorial},
author = {Luque-Fernandez, Miguel Angel and Schomaker, Michael and Rachet, Bernard and Schnitzer, Mireille E},
volume = {2018},
journal = {Statistics in Medicine},
keywords = {causal inference, ensemble Learning, machine learning, observational studies, targeted maximum likelihood estimation}}
@article{Luque-Fernandez2018,
doi = {10.1002/sim.7628},
url = {http://doi.wiley.com/10.1002/sim.7628},
issn = {02776715},
year = {2018},
month = {7},
pages = {2530--2546},
title = {Targeted maximum likelihood estimation for a binary treatment: A tutorial},
author = {Luque-Fernandez, Miguel Angel and Schomaker, Michael and Rachet, Bernard and Schnitzer, Mireille E.},
number = {16},
volume = {37},
journal = {Statistics in Medicine},
keywords = {causal inference, ensemble Learning, machine learning, observational studies, targeted maximum likelihood estimation},
publisher = {John Wiley and Sons Ltd}}
@article{Schuler2017TargetedStudies,
doi = {10.1093/aje/kww165},
url = {https://academic.oup.com/aje/article/185/1/65/2662306},
issn = {14766256},
pmid = {27941068},
year = {2017},
pages = {65--73},
title = {Targeted maximum likelihood estimation for causal inference in observational studies},
author = {Schuler, Megan S and Rose, Sherri},
number = {1},
volume = {185},
journal = {American Journal of Epidemiology},
keywords = {Causal inference, Machine learning, Observational studies, Super learner, Targeted maximum likelihood estimation},
publisher = {Oxford University Press}}
@article{VanderLaan2006,
year = {2006},
title = {Targeted maximum likelihood learning},
author = {van der Laan, Mark J and Rubin, Daniel},
number = {1},
volume = {2},
journal = {The International Journal of Biostatistics}}
@article{Coyle2020,
url = {http://arxiv.org/abs/2006.07333},
year = {2020},
month = {6},
title = {Targeting Learning: Robust Statistics for Reproducible Research},
author = {Coyle, Jeremy R. and Hejazi, Nima S. and Malenica, Ivana and Phillips, Rachael V. and Arnold, Benjamin F. and Mertens, Andrew and Benjamin-Chung, Jade and Cai, Weixin and Dayal, Sonali and Colford, John M. and Hubbard, Alan E. and van der Laan, Mark J.},
arxivid = {2006.07333},
journal = {arXiv}}
@article{Coyle2020b,
url = {http://arxiv.org/abs/2006.07333},
year = {2020},
title = {Targeting Learning: Robust Statistics for Reproducible Research},
author = {Coyle, Jeremy R and Hejazi, Nima S and Malenica, Ivana and Phillips, Rachael V and Arnold, Benjamin F and Mertens, Andrew and Benjamin-Chung, Jade and Cai, Weixin and Dayal, Sonali and Colford, John M and Hubbard, Alan E and van der Laan, Mark J},
arxivid = {2006.07333},
journal = {arXiv}}
@article{Rosenbaum1983,
year = {1983},
pages = {41--55},
title = {The central role of the propensity score in observational studies for causal effects},
author = {Rosenbaum, Paul R and Rubin, Donald B},
number = {1},
volume = {70},
journal = {Biometrika},
publisher = {Biometrika Trust}}
@article{Rubin2007,
year = {2007},
month = {1},
pages = {20--36},
title = {The design versus the analysis of observational studies for causal effects: parallels with the design of randomized trials},
author = {Rubin, Donald B},
number = {1},
volume = {26},
journal = {Stat Med}}
@article{Rubin2007b,
year = {2007},
month = {1},
pages = {20--36},
title = {The design versus the analysis of observational studies for causal effects: parallels with the design of randomized trials},
author = {Rubin, Donald B},
number = {1},
volume = {26},
journal = {Stat Med}}
@article{Connors1996,
doi = {10.1001/jama.276.11.889},
url = {https://pubmed.ncbi.nlm.nih.gov/8782638/},
issn = {00987484},
pmid = {8782638},
year = {1996},
month = {9},
pages = {889--897},
title = {The effectiveness of right heart catheterization in the initial care of critically ill patients},
author = {Connors, Alfred F. and Speroff, Theodore and Dawson, Neal V. and Thomas, Charles and Harrell, Frank E. and Wagner, Douglas and Desbiens, Norman and Goldman, Lee and Wu, Albert W. and Califf, Robert M. and Fulkerson, William J. and Vidaillet, Humberto and Broste, Steven and Bellamy, Paul and Lynn, Joanne and Knaus, William A.},
number = {11},
volume = {276},
journal = {Journal of the American Medical Association},
keywords = {A F Connors, APACHE, Aged, Catheterization, Cohort Studies, Critical Illness* / economics, Critical Illness* / mortality, Female, Health Care Costs, Health Care*, Hospital Mortality, Humans, Intensive Care Units* / economics, Length of Stay / economics, Linear Models, Logistic Models, MEDLINE, Male, Middle Aged, Multicenter Study, Multivariate Analysis, NCBI, NIH, NLM, National Center for Biotechnology Information, National Institutes of Health, National Library of Medicine, Non-U.S. Gov't, Outcome and Process Assessment, Prognosis, Proportional Hazards Models, Prospective Studies, PubMed Abstract, Research Support, Sensitivity and Specificity, Survival Rate, Swan-Ganz* / economics, T Speroff, United States, W A Knaus, doi:10.1001/jama.276.11.889, pmid:8782638},
publisher = {JAMA}}
@article{Connors1996b,
doi = {10.1001/jama.276.11.889},
url = {https://pubmed.ncbi.nlm.nih.gov/8782638/},
issn = {00987484},
pmid = {8782638},
year = {1996},
month = {9},
pages = {889--897},
title = {The effectiveness of right heart catheterization in the initial care of critically ill patients},
author = {Connors, Alfred F. and Speroff, Theodore and Dawson, Neal V. and Thomas, Charles and Harrell, Frank E. and Wagner, Douglas and Desbiens, Norman and Goldman, Lee and Wu, Albert W. and Califf, Robert M. and Fulkerson, William J. and Vidaillet, Humberto and Broste, Steven and Bellamy, Paul and Lynn, Joanne and Knaus, William A.},
number = {11},
volume = {276},
journal = {Journal of the American Medical Association},
keywords = {A F Connors, APACHE, Aged, Catheterization, Cohort Studies, Critical Illness* / economics, Critical Illness* / mortality, Female, Health Care Costs, Health Care*, Hospital Mortality, Humans, Intensive Care Units* / economics, Length of Stay / economics, Linear Models, Logistic Models, MEDLINE, Male, Middle Aged, Multicenter Study, Multivariate Analysis, NCBI, NIH, NLM, National Center for Biotechnology Information, National Institutes of Health, National Library of Medicine, Non-U.S. Gov't, Outcome and Process Assessment, Prognosis, Proportional Hazards Models, Prospective Studies, PubMed Abstract, Research Support, Sensitivity and Specificity, Survival Rate, Swan-Ganz* / economics, T Speroff, United States, W A Knaus, doi:10.1001/jama.276.11.889, pmid:8782638},
publisher = {JAMA}}
@article{Hampel1974,
year = {1974},
pages = {383--393},
title = {The influence curve and its role in robust estimation},
author = {Hampel, Frank R},
number = {346},
volume = {69},
journal = {Journal of the American Statistical Association},
publisher = {Taylor {\&}amp; Francis}}
@book{Efron1982,
year = {1982},
title = {The jackknife, the bootstrap and other resampling plans},
author = {Efron, Bradley},
volume = {38},
publisher = {SIAM}}
@article{DorfmanTheRevisited,
title = {The l-l:ijek Estimator Revisited},
author = {Dorfman, Alan H and Valliant, Richard and Bureau, U S},
keywords = {Horvitz-Thompson estimator, balanced sample, best linear unbiased predictor, ratio estimator, robustness, superpopulation model}}
@article{Keil2014,
doi = {10.1097/EDE.0000000000000160},
issn = {15315487},
pmid = {25140837},
year = {2014},
title = {The parametric g-formula for time-to-event data: Intuition and a worked example},
author = {Keil, Alexander P. and Edwards, Jessie K. and Richardson, David B. and Naimi, Ashley I. and Cole, Stephen R.},
journal = {Epidemiology}}
@article{Gruber2011,
year = {2011},
title = {tmle: An R Package for Targeted Maximum Likelihood Estimation},
author = {Gruber, Susan and van der Laan, Mark},
journal = {U.C. Berkeley Division of Biostatistics Working Paper Series}}
@article{Gruber2012Tmle:Estimation,
doi = {10.18637/jss.v051.i13},
url = {https://www.jstatsoft.org/index.php/jss/article/view/v051i13/v51i13.pdf https://www.jstatsoft.org/index.php/jss/article/view/v051i13},
issn = {15487660},
year = {2012},
pages = {1--35},
title = {tmle: An R package for targeted maximum likelihood estimation},
author = {Gruber, Susan and van der Laan, Mark J},
number = {13},
volume = {51},
journal = {Journal of Statistical Software},
keywords = {Causal inference, Controlled direct effect, MSM, R, TMLE, Targeted maximum likelihood estimation},
publisher = {American Statistical Association}}
@article{Sturmer2010TreatmentStudyb,
doi = {10.1093/aje/kwq198},
url = {/pmc/articles/PMC3025652/ /pmc/articles/PMC3025652/?report=abstract https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3025652/},
issn = {14766256},
pmid = {20716704},
year = {2010},
pages = {843--854},
title = {Treatment effects in the presence of unmeasured confounding: Dealing with observations in the tails of the propensity score distribution-A simulation study},
author = {St{\"{u}}rmer, Til and Rothman, Kenneth J and Avorn, Jerry and Glynn, Robert J},
number = {7},
volume = {172},
journal = {American Journal of Epidemiology},
keywords = {bias (epidemiology), causal inference, cohort studies, confounding factors (epidemiology), epidemiologic methods, models, propensity score, research design, statistical},
publisher = {Oxford University Press}}
@article{Sturmer2010TreatmentStudy,
doi = {10.1093/aje/kwq198},
url = {https://pubmed.ncbi.nlm.nih.gov/20716704/},
issn = {14766256},
pmid = {20716704},
year = {2010},
pages = {843--854},
title = {Treatment effects in the presence of unmeasured confounding: Dealing with observations in the tails of the propensity score distribution-A simulation study},
author = {St{\"{u}}rmer, Til and Rothman, Kenneth J and Avorn, Jerry and Glynn, Robert J},
number = {7},
volume = {172},
journal = {American Journal of Epidemiology},
keywords = {bias (epidemiology), causal inference, cohort studies, confounding factors (epidemiology), epidemiologic methods, models, propensity score, research design, statistical},
publisher = {Oxford University Press}}
@misc{Ridgeway2013,
year = {2013},
title = {twang: Toolkit for Weighting and Analysis of Nonequivalent Groups. R package version 1.3-20},
author = {Ridgeway, G and McCaffrey, D and Morral, A and Griffin, B A and Burgette, L}}
@article{Fisher2018,
year = {2018},
title = {Visually communicating and teaching intuition for influence functions},
author = {Fisher, Aaron and Kennedy, Edward H},
journal = {arXiv preprint arXiv:1810.03260}}
@article{VerHoef2012,
url = {http://dx.doi.org/10.1080/00031305.2012.687494},
year = {2012},
month = {5},
pages = {124--127},
title = {Who Invented the Delta Method?},
author = {Ver Hoef, Jay M},
number = {2},
volume = {66},
journal = {The American Statistician},
publisher = {Informa UK Limited}}
@article{Neugebauer2005,
year = {2005},
pages = {405--426},
title = {Why prefer double robust estimators in causal inference?},
author = {Neugebauer, Romain and van der Laan, Mark},
number = {1},
volume = {129},
journal = {Journal of Statistical Planning and Inference},
publisher = {Elsevier}}
@article{Robins1986AEffect,
doi = {10.1016/0270-0255(86)90088-6},
issn = {02700255},
year = {1986},
month = {1},
pages = {1393--1512},
title = {A new approach to causal inference in mortality studies with a sustained exposure period-application to control of the healthy worker survivor effect},
author = {Robins, James},
number = {9-12},
volume = {7},
journal = {Mathematical Modelling},
publisher = {Pergamon}}
@book{Wasserman2006AllStatistics,
doi = {10.1007/0-387-30623-4},
year = {2006},
title = {All of Nonparametric Statistics},
author = {Wasserman, Larry},
booktitle = {All of Nonparametric Statistics},
publisher = {Springer New York}}
@misc{AllSpringer,
url = {https://www.springer.com/gp/book/9780387251455},
title = {All of Nonparametric Statistics | Larry Wasserman | Springer}}
@article{Levy2018AnCV-TMLE,
issn = {23318422},
year = {2018},
title = {An Easy Implementation of CV-TMLE},
author = {Levy, Jonathan},
arxivid = {1811.04573},
journal = {arXiv}}
@article{Basu2011AnOneb,
doi = {10.1007/978-1-4419-5825-9{\_}24},
year = {2011},
pages = {167--206},
title = {An Essay on the Logical Foundations of Survey Sampling, Part One*},
author = {Basu, D.},
journal = {Selected Works of Debabrata Basu},
publisher = {Springer New York}}
@article{Austin2009BalanceSamplesb,
doi = {10.1002/sim.3697},
url = {/pmc/articles/PMC3472075/ /pmc/articles/PMC3472075/?report=abstract https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3472075/},
issn = {02776715},
pmid = {19757444},
year = {2009},
month = {11},
pages = {3083--3107},
title = {Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples},
author = {Austin, Peter C.},
number = {25},
volume = {28},
journal = {Statistics in Medicine},
keywords = {Balance, Bias, Goodness-of-fit, Matching, Observational study, Propensity score, Propensity-score matching, Standardized difference},
publisher = {Wiley-Blackwell}}
@book{Hajek1971CommentEds.,
year = {1971},
pages = {236},
title = {Comment on An essay on the logical foundations of survey sampling by Basu, D. in Foundations of Statistical Inference (Godambe, V.P. and Sprott, D.A. eds.)},
author = {Hajek, J.},
publisher = {Holt, Rinehart and Winston}}
@misc{ComparisonModels,
url = {https://www.degruyter.com/document/doi/10.1515/em-2012-0006/html},
title = {Comparison of Approaches to Weight Truncation for Marginal Structural Cox Models}}
@article{Xiao2013ComparisonModels,
doi = {10.1515/em-2012-0006},
url = {https://www.degruyter.com/document/doi/10.1515/em-2012-0006/html},
issn = {2161962X},
year = {2013},
month = {12},
pages = {1--20},
title = {Comparison of approaches to weight truncation for marginal structural Cox models},
author = {Xiao, Yongling and Moodie, Erica E.M. and Abrahamowicz, Michal},
number = {1},
volume = {2},
journal = {Epidemiologic Methods},
keywords = {IPTW estimator, Marginal structural model, Positivity assumption, Survival analysis, Weight truncation},
publisher = {Walter de Gruyter GmbH}}
@misc{Cole2008ConstructingModelsb,
doi = {10.1093/aje/kwn164},
url = {https://academic.oup.com/aje/article/168/6/656/88658},
issn = {00029262},
pmid = {18682488},
year = {2008},
month = {9},
pages = {656--664},
title = {Constructing inverse probability weights for marginal structural models},
author = {Cole, Stephen R. and Hern{\'{a}}n, Miguel A.},
number = {6},
volume = {168},
keywords = {Bias (epidemiology), Causality, Confounding factors (epidemiology), Probability weighting, Regression model},
booktitle = {American Journal of Epidemiology},
publisher = {Oxford Academic}}
@article{Brenner1997ControllingResearch,
doi = {10.1097/00001648-199707000-00014},
url = {https://www.jstor.org/stable/3702586},
issn = {10443983},
pmid = {9209859},
year = {1997},
pages = {429--434},
title = {Controlling for continuous confounders in epidemiologic research},
author = {Brenner, Hermann and Blettner, Maria},
number = {4},
volume = {8},
journal = {Epidemiology},
keywords = {Biostatistics, Confounding, Epidemiologic methods, Logistic regression}}
@incollection{Zheng2011Cross-ValidatedEstimation,
doi = {10.1007/978-1-4419-9782-1{\_}27},
year = {2011},
title = {Cross-Validated Targeted Minimum-Loss-Based Estimation},
author = {Zheng, Wenjing and van der Laan, Mark J.}}
@article{Luque-Fernandez2018Data-AdaptivePresentationb,
doi = {10.1093/aje/kwx317},
url = {https://pubmed.ncbi.nlm.nih.gov/29020131/},
issn = {14766256},
pmid = {29020131},
year = {2018},
month = {4},
pages = {871--878},
title = {Data-Adaptive Estimation for Double-Robust Methods in Population-Based Cancer Epidemiology: Risk Differences for Lung Cancer Mortality by Emergency Presentation},
author = {Luque-Fernandez, Miguel Angel and Belot, Aurélien and Valeri, Linda and Cerulli, Giovanni and Maringe, Camille and Rachet, Bernard},
number = {4},
volume = {187},
journal = {American Journal of Epidemiology},
keywords = {cancer epidemiology, causality, machine learning, population-based data, statistics, targeted maximum likelihood estimation},
publisher = {Oxford University Press}}
@incollection{Daniel2018DoubleRobustness,
doi = {10.1002/9781118445112.stat08068},
url = {https://onlinelibrary.wiley.com/doi/full/10.1002/9781118445112.stat08068 https://onlinelibrary.wiley.com/doi/abs/10.1002/9781118445112.stat08068 https://onlinelibrary.wiley.com/doi/10.1002/9781118445112.stat08068},
year = {2018},
month = {8},
pages = {1--14},
title = {Double Robustness},
author = {Daniel, Rhian M.},
keywords = {adaptive estimation, causal inference, convergence, data, inverse probability weighting, local efficiency, missing data, nuisance functionals, outcome regression},
booktitle = {Wiley StatsRef: Statistics Reference Online},
publisher = {Wiley}}
@article{Daniel2018DoubleRobustnessb,
doi = {10.1002/9781118445112.STAT08068},
year = {2018},
month = {8},
pages = {1--14},
title = {Double Robustness},
author = {Daniel, Rhian M.},
journal = {Wiley StatsRef: Statistics Reference Online},
publisher = {Wiley}}
@article{Chernozhukov2018Double/debiasedParameters,
doi = {10.1111/ECTJ.12097},
url = {https://academic.oup.com/ectj/article/21/1/C1/5056401},
issn = {1368-4221},
year = {2018},
month = {2},
pages = {C1-C68},
title = {Double/debiased machine learning for treatment and structural parameters},
author = {Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Duflo, Esther and Hansen, Christian and Newey, Whitney and Robins, James},
number = {1},
volume = {21},
journal = {The Econometrics Journal},
publisher = {Oxford Academic}}
@article{Chernozhukov2018Double/debiasedParametersb,
doi = {10.1111/ectj.12097},
issn = {1368423X},
year = {2018},
pages = {C1-C68},
title = {Double/debiased machine learning for treatment and structural parameters},
author = {Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Duflo,
Esther and Hansen, Christian and Newey, Whitney and Robins, James},
number = {1},
volume = {21},
journal = {Econometrics Journal}}
@article{Chernozhukov2018Double/debiasedParametersc,
doi = {10.1111/ectj.12097},
issn = {1368423X},
year = {2018},
title = {Double/debiased machine learning for treatment and structural parameters},
author = {Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Duflo, Esther and Hansen, Christian and Newey, Whitney and Robins, James},
journal = {Econometrics Journal}}
@article{Chernozhukov2018Double/debiasedParametersd,
doi = {10.1111/ectj.12097},
issn = {1368423X},
year = {2018},
title = {Double/debiased machine learning for treatment and structural parameters},
author = {Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Duflo, Esther and Hansen, Christian and Newey, Whitney and Robins, James},
journal = {Econometrics Journal}}
@article{Cattaneo2010EfficientIgnorability,
url = {https://econpapers.repec.org/RePEc:eee:econom:v:155:y:2010:i:2:p:138-154},
issn = {0304-4076},
year = {2010},
pages = {138--154},
title = {Efficient semiparametric estimation of multi-valued treatment effects under ignorability},
author = {Cattaneo, Matias D.},
number = {2},
volume = {155},
journal = {Journal of Econometrics},
keywords = {Multi, valued treatment effects Unconfoundedness Semipara},
publisher = {Elsevier}}
@article{Goetghebeur2020FormulatingAnswersb,
doi = {10.1002/sim.8741},
url = {www.ofcaus.org},
issn = {10970258},
pmid = {32964526},
year = {2020},
month = {12},
pages = {4922--4948},
title = {Formulating causal questions and principled statistical answers},
author = {Goetghebeur, Els and le Cessie, Saskia and De Stavola, Bianca and Moodie, Erica E.M. and Waernbaum, Ingeborg},
number = {30},
volume = {39},
arxivid = {1906.12100},
journal = {Statistics in Medicine},
keywords = {causation, instrumental variable, inverse probability weighting, matching, potential outcomes, propensity score},
publisher = {John Wiley and Sons Ltd}}
@article{Smith2020IntroductionTutorial,
doi = {10.1002/SIM.9234},
url = {https://onlinelibrary.wiley.com/doi/full/10.1002/sim.9234 https://onlinelibrary.wiley.com/doi/abs/10.1002/sim.9234 https://onlinelibrary.wiley.com/doi/10.1002/sim.9234},
issn = {1097-0258},
year = {2020},
month = {12},
title = {Introduction to computational causal inference using reproducible Stata, R, and Python code: A tutorial},
author = {Smith, Matthew J. and Mansournia, Mohammad A. and Maringe, Camille and Zivich, Paul N. and Cole, Stephen R. and Leyrat, Clémence and Belot, Aurélien and Rachet, Bernard and Luque-Fernandez, Miguel A.},
arxivid = {2012.09920},
journal = {Statistics in Medicine},
keywords = {G, causal inference, double, formula, g, inverse probability weighting, machine learning, methods, propensity score, regression adjustment, robust methods, targeted maximum likelihood estimation},
publisher = {John Wiley {\&} Sons, Ltd}}
@article{Lendle2017Ltmle:Data,
doi = {10.18637/JSS.V081.I01},
url = {https://www.jstatsoft.org/index.php/jss/article/view/v081i01},
issn = {1548-7660},
year = {2017},
month = {10},
pages = {1--21},
title = {ltmle: An R Package Implementing Targeted Minimum Loss-Based Estimation for Longitudinal Data},
author = {Lendle, Samuel D. and Schwab, Joshua and Petersen, Maya L. and van Der Laan, Mark J.},
volume = {81},
journal = {Journal of Statistical Software},
keywords = {R, based estimation, causal inference, estimation, longitudinal data, targeted minimum loss},
publisher = {American Statistical Association}}
@article{Diaz2020MachineLearning,
doi = {10.1093/biostatistics/kxz042},
issn = {14684357},
pmid = {31742333},
year = {2020},
title = {Machine learning in the estimation of causal effects: targeted minimum loss-based estimation and double/debiased machine learning},
author = {D{\'{i}}az, Iván},
journal = {Biostatistics (Oxford, England)},
keywords = {Causal inference, Double/debiased machine learning, Machine learning, Targeted minimum loss-based estimation}}
@article{Diaz2020MachineLearningb,
doi = {10.1093/BIOSTATISTICS/KXZ042},
url = {https://pubmed.ncbi.nlm.nih.gov/31742333/},
issn = {1468-4357},
pmid = {31742333},
year = {2020},
month = {4},
pages = {353--358},
title = {Machine learning in the estimation of causal effects: targeted minimum loss-based estimation and double/debiased machine learning},
author = {D{\'{i}}az, Iván},
number = {2},
volume = {21},
journal = {Biostatistics (Oxford, England)},
keywords = {Biostatistics*, Causality, Data Interpretation, Humans, Iv{\'{a}}n D{\'{i}}az, MEDLINE, Machine Learning*, Models, NCBI, NIH, NLM, National Center for Biotechnology Information, National Institutes of Health, National Library of Medicine, PubMed Abstract, Statistical*, doi:10.1093/biostatistics/kxz042, pmid:31742333},
publisher = {Biostatistics}}
@article{Robins2000MarginalEpidemiology,
doi = {10.1097/00001648-200009000-00011},
url = {http://europepmc.org/article/med/10955408},
issn = {10443983},
pmid = {10955408},
year = {2000},
month = {9},
pages = {550--560},
title = {Marginal structural models and causal inference in epidemiology},
author = {Robins, James M. and Hern{\'{a}}n, Miguel Ángel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
keywords = {Causality, Confounding, Counterfactuals, Epidemiologic methods, Intermediate variables, Longitudinal data, Structural models}}
@article{Robins2000MarginalEpidemiologyb,
doi = {10.1097/00001648-200009000-00011},
url = {http://europepmc.org/article/med/10955408},
issn = {10443983},
pmid = {10955408},
year = {2000},
month = {9},
pages = {550--560},
title = {Marginal structural models and causal inference in epidemiology},
author = {Robins, James M. and Hern{\'{a}}n, Miguel Ángel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
keywords = {Causality, Confounding, Counterfactuals, Epidemiologic methods, Intermediate variables, Longitudinal data, Structural models}}
@article{Hernan2000MarginalMen,
doi = {10.1097/00001648-200009000-00012},
url = {https://pubmed.ncbi.nlm.nih.gov/10955409/},
issn = {10443983},
pmid = {10955409},
year = {2000},
pages = {561--570},
title = {Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men},
author = {Hern{\'{a}}n, Miguel Ángel and Brumback, Babette and Robins, James M.},
number = {5},
volume = {11},
journal = {Epidemiology},
keywords = {AIDS, Causality, Confounding, Counterfactuals, Epidemiologic methods, Intermediate variables, Longitudinal data, Structural models, Survival analysis},
publisher = {Epidemiology}}
@misc{Luque-Fernandez2019Migariane/meltmle:Zenodo,
url = {https://zenodo.org/record/2560828},
year = {2019},
title = {migariane/meltmle: Ensemble Learning Targeted Maximum Likelihood Estimation for Stata users | Zenodo},
author = {Luque-Fernandez, Miguel Angel},
booktitle = {Zenodo}}
@article{Gill1989Non-1,
url = {https://www.jstor.org/stable/4616127?seq=1},
year = {1989},
pages = {97--128},
title = {Non- and Semi-Parametric Maximum Likelihood Estimators and the Von Mises Method (Part 1)},
author = {Gill, Richard D},
number = {2},
volume = {16},
journal = {Scandinavian Journal of Statistics}}
@software{Zivich2020Pythonv0.9.0,
url = {https://zenodo.org/record/3339870/export/hx
https://github.com/pzivich/Python-for-Epidemiologists},
year = {2020},
title = {Python for Epidemiologists (v0.9.0)},
author = {Zivich, Paul N},
journal = {Zenodo},
publisher = {Zenodo}}
@article{Zivich2019Pzivich/Python-for-Epidemiologists:V0.8.0,
doi = {10.5281/ZENODO.3339870},
url = {https://zenodo.org/record/3339870},
year = {2019},
month = {7},
title = {pzivich/Python-for-Epidemiologists: Updates for v0.8.0},
author = {Zivich, Paul}}
@article{MA2021ReflectionEpidemiologistsb,
doi = {10.1093/IJE/DYAA260},
url = {https://pubmed.ncbi.nlm.nih.gov/33351919/},
issn = {1464-3685},
pmid = {33351919},
year = {2021},
month = {2},
pages = {346--351},
title = {Reflection on modern methods: demystifying robust standard errors for epidemiologists},
author = {MA, Mansournia and M, Nazemipour and AI, Naimi and GS, Collins and MJ, Campbell},
number = {1},
volume = {50},
journal = {International journal of epidemiology},
keywords = {Cluster Analysis, Epidemiologists*, Humans, MEDLINE, Maryam Nazemipour, Michael J Campbell, Models, Mohammad Ali Mansournia, NCBI, NIH, NLM, National Center for Biotechnology Information, National Institutes of Health, National Library of Medicine, PubMed Abstract, Statistical*, Uncertainty, doi:10.1093/ije/dyaa260, pmid:33351919},
publisher = {Int J Epidemiol}}
@article{Schomaker2020RegressionCausality,
url = {http://arxiv.org/abs/2006.11754},
year = {2020},
month = {6},
title = {Regression and Causality},
author = {Schomaker, Michael},
arxivid = {2006.11754},
journal = {arXiv:2006.11754}}
@book{Tsiatis2006SemiparametricData,
doi = {10.1007/0-387-37345-4},
year = {2006},
title = {Semiparametric Theory and Missing Data},
author = {Tsiatis, Anastasios A},
keywords = {Mathematical Physics and Mathematics},
booktitle = {Semiparametric Theory and Missing Data},
publisher = {Springer Science and Business Media LLC}}
@article{Keil2019SuperSystem,
url = {https://arxiv.org/abs/1805.08058},
year = {2019},
title = {Super learning in the SAS system},
author = {Keil, Alexander P. and Westreich, Daniel and Edwards, Jessie K. and Cole,
Stephen R.},
arxivid = {1805.08058},
journal = {arXiv}}
@article{Schuler2017TargetedStudiesb,
doi = {10.1093/aje/kww165},
url = {https://academic.oup.com/aje/article/185/1/65/2662306},
issn = {14766256},
pmid = {27941068},
year = {2017},
month = {1},
pages = {65--73},
title = {Targeted maximum likelihood estimation for causal inference in observational studies},
author = {Schuler, Megan S. and Rose, Sherri},
number = {1},
volume = {185},
journal = {American Journal of Epidemiology},
keywords = {Causal inference, Machine learning, Observational studies, Super learner, Targeted maximum likelihood estimation},
publisher = {Oxford University Press}}
@article{Gruber2009TargetedIntroduction,
url = {https://biostats.bepress.com/ucbbiostat/paper252},
year = {2009},
month = {8},
title = {Targeted Maximum Likelihood Estimation: A Gentle Introduction},
author = {Gruber, Susan and Laan, Mark van der},
journal = {U.C. Berkeley Division of Biostatistics Working Paper Series}}
@article{DorfmanTheRevisitedb,
title = {The l-l:ijek Estimator Revisited},
author = {Dorfman, Alan H and Valliant, Richard and Bureau, U S},
keywords = {Horvitz-Thompson estimator, balanced sample, best linear unbiased predictor, ratio estimator, robustness, superpopulation model}}
@article{Gruber2012Tmle:Estimationb,
doi = {10.18637/jss.v051.i13},
url = {https://www.jstatsoft.org/index.php/jss/article/view/v051i13/v51i13.pdf https://www.jstatsoft.org/index.php/jss/article/view/v051i13},
issn = {15487660},
year = {2012},
month = {11},
pages = {1--35},
title = {tmle: An R package for targeted maximum likelihood estimation},
author = {Gruber, Susan and van der Laan, Mark J.},
number = {13},
volume = {51},
journal = {Journal of Statistical Software},
keywords = {Causal inference, Controlled direct effect, MSM, R, TMLE, Targeted maximum likelihood estimation},
publisher = {American Statistical Association}}
@article{Sturmer2010TreatmentStudyc,
doi = {10.1093/aje/kwq198},
url = {/pmc/articles/PMC3025652/ /pmc/articles/PMC3025652/?report=abstract https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3025652/},
issn = {14766256},
pmid = {20716704},
year = {2010},
month = {10},
pages = {843--854},
title = {Treatment effects in the presence of unmeasured confounding: Dealing with observations in the tails of the propensity score distribution-A simulation study},
author = {St{\"{u}}rmer, Til and Rothman, Kenneth J. and Avorn, Jerry and Glynn, Robert J.},
number = {7},
volume = {172},
journal = {American Journal of Epidemiology},
keywords = {bias (epidemiology), causal inference, cohort studies, confounding factors (epidemiology), epidemiologic methods, models, propensity score, research design, statistical},
publisher = {Oxford University Press}}
@article{Sturmer2010TreatmentStudyd,
doi = {10.1093/aje/kwq198},
url = {https://pubmed.ncbi.nlm.nih.gov/20716704/},
issn = {14766256},
pmid = {20716704},
year = {2010},
month = {10},
pages = {843--854},
title = {Treatment effects in the presence of unmeasured confounding: Dealing with observations in the tails of the propensity score distribution-A simulation study},
author = {St{\"{u}}rmer, Til and Rothman, Kenneth J. and Avorn, Jerry and Glynn, Robert J.},
number = {7},
volume = {172},
journal = {American Journal of Epidemiology},
keywords = {bias (epidemiology), causal inference, cohort studies, confounding factors (epidemiology), epidemiologic methods, models, propensity score, research design, statistical},
publisher = {Oxford University Press}}
@article{Webster-Clark2021UsingScience,
doi = {10.1002/sim.8866},
url = {https://onlinelibrary.wiley.com/doi/full/10.1002/sim.8866 https://onlinelibrary.wiley.com/doi/abs/10.1002/sim.8866 https://onlinelibrary.wiley.com/doi/10.1002/sim.8866},
issn = {10970258},
pmid = {33377193},
year = {2021},
month = {3},
pages = {1718--1735},
title = {Using propensity scores to estimate effects of treatment initiation decisions: State of the science},
author = {Webster-Clark, Michael and St{\"{u}}rmer, Til and Wang, Tiansheng and Man, Kenneth and Marinac-Dabic, Danica and Rothman, Kenneth J. and Ellis, Alan R. and Gokhale, Mugdha and Lunt, Mark and Girman, Cynthia and Glynn, Robert J.},
number = {7},
volume = {40},
journal = {Statistics in Medicine},
keywords = {comparative effectiveness research, propensity scores, real-world data, real-world evidence, review},
publisher = {John Wiley and Sons Ltd}}
@article{Petersen_2014,
doi = {10.1097/ede.0000000000000078},
url = {https://doi.org/10.1097%2Fede.0000000000000078},
year = {2014},
month = {may},
pages = {418--426},
title = {Causal Models and Learning from Data},
author = {Maya L. Petersen and Mark J. van der Laan},
number = {3},
volume = {25},
journal = {Epidemiology},
publisher = {Ovid Technologies (Wolters Kluwer Health)}}
@article{Dang2023,
DOI = {10.1017/cts.2023.635},
year = {2023},
pages = {e212},
title = {A causal roadmap for generating high-quality real-world evidence},
author = {Dang, Lauren E. and Gruber, Susan and Lee, Hana and Dahabreh, Issa J. and Stuart,
Elizabeth A. and Williamson, Brian D. and Wyss, Richard and Díaz, Iván and Ghosh,
Debashis and Kıcıman, Emre and et al.},
number = {1},
volume = {7},
journal = {Journal of Clinical and Translational Science}}
@article{Greifer2023,
url = {https://arxiv.org/abs/2106.10577},
year = {2023},
title = {Choosing the Causal Estimand for Propensity Score Analysis of Observational Studies},
author = {Noah Greifer and Elizabeth A. Stuart},
eprint = {2106.10577},
journal = {arXiv},
primaryClass = {stat.ME},
archivePrefix = {arXiv}}
@article{Greenland1986_a428,
year = {1986},
pages = {413--419},
title = {{Identifiability, exchangeability, and epidemiological confounding}},
author = {Greenland, Sander and Robins, James M},
number = {3},
volume = {15},
journal = {International journal of epidemiology},
publisher = {IEA}}
@article{Xiao2013,
doi = {10.1515/em-2012-0006},
url = {https://www.degruyter.com/document/doi/10.1515/em-2012-0006/html},
issn = {2161962X},
year = {2013},
month = {dec},
pages = {1--20},
title = {Comparison of approaches to weight truncation for marginal structural Cox
models},
author = {Xiao, Yongling and Moodie, Erica E.M. and Abrahamowicz, Michal},
number = {1},
volume = {2},
journal = {Epidemiologic Methods},
abstract = {Marginal structural Cox Models (Cox MSMs) have been used to estimate the
causal effect of a time-varying treatment on the hazard when there exist
time-dependent confounders, which are themselves also affected by previous
treatment. A Cox MSM can be estimated via the
inverse-probability-of-treatment weighting (IPTW) estimator. However, IPTW
estimators suffer from large variability if some observations are assigned
extremely high weights. Weight truncation has been proposed as one simple
solution to this problem, but truncation levels are typically chosen based on
ad hoc criteria that have not been systematically evaluated. Bembom et al.
proposed data-adaptive selection of the optimal truncation level using the
estimated mean-squared error (MSE) of a truncated IPTW estimator for
cross-sectional data. Based on a similar principle, we proposed data-adaptive
approaches to select the truncation level that minimizes the expected MSE for
time-to-event data with time-varying treatments. The expected MSE is
approximated by using either observed statistics as a proxy for the true
unknown parameter or using cross-validation. Simulations confirm that simple
weight truncation at high percentiles such as the 99th or 99.5th of the
distribution of weights improves the IPTW estimators in most scenarios we
considered. Our newly proposed approaches exhibit similarly good performance
and may be applied in a wide range of settings.},
keywords = {IPTW estimator,Marginal structural model,Positivity assumption,Survival
analysis,Weight truncation},
publisher = {Walter de Gruyter GmbH}}
@article{Robins2000_5bdd,
url = {https://journals.lww.com/epidem/Fulltext/2000/09000/Marginal_Structural_Models_and_Causal_Inference_in.11.aspx},
issn = {1044-3983},
year = {2000},
title = {{Marginal Structural Models and Causal Inference in Epidemiology}},
author = {Robins, James M and Hern{\'{a}}n, Miguel {\'{A}}ngel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
abstract = {In observational studies with exposures or treatments that vary over time, standard approaches for adjustment of confounding are biased when there exist time-dependent confounders that are also affected by previous treatment. This paper introduces marginal structural models, a new class of causal models that allow for improved adjustment of confounding in those situations. The parameters of a marginal structural model can be consistently estimated using a new class of estimators, the inverse-probability-of-treatment weighted estimators.},
keywords = {causality,confounding,counterfactuals,epidemiologic methods,intermediate variables,longitudinal data,structural models}}
@article{Greenland1986_4742,
year = {1986},
pages = {413--419},
title = {{Identifiability, exchangeability, and epidemiological confounding}},
author = {Greenland, Sander and Robins, James M},
number = {3},
volume = {15},
journal = {International journal of epidemiology},
publisher = {IEA}}
@article{Xiao2013_942c,
doi = {10.1515/em-2012-0006},
url = {https://www.degruyter.com/document/doi/10.1515/em-2012-0006/html},
issn = {2161962X},
year = {2013},
month = {dec},
pages = {1--20},
title = {{Comparison of approaches to weight truncation for marginal structural Cox models}},
author = {Xiao, Yongling and Moodie, Erica E.M. and Abrahamowicz, Michal},
number = {1},
volume = {2},
journal = {Epidemiologic Methods},
abstract = {Marginal structural Cox Models (Cox MSMs) have been used to estimate the causal effect of a time-varying treatment on the hazard when there exist time-dependent confounders, which are themselves also affected by previous treatment. A Cox MSM can be estimated via the inverse-probability-of-treatment weighting (IPTW) estimator. However, IPTW estimators suffer from large variability if some observations are assigned extremely high weights. Weight truncation has been proposed as one simple solution to this problem, but truncation levels are typically chosen based on ad hoc criteria that have not been systematically evaluated. Bembom et al. proposed data-adaptive selection of the optimal truncation level using the estimated mean-squared error (MSE) of a truncated IPTW estimator for cross-sectional data. Based on a similar principle, we proposed data-adaptive approaches to select the truncation level that minimizes the expected MSE for time-to-event data with time-varying treatments. The expected MSE is approximated by using either observed statistics as a proxy for the true unknown parameter or using cross-validation. Simulations confirm that simple weight truncation at high percentiles such as the 99th or 99.5th of the distribution of weights improves the IPTW estimators in most scenarios we considered. Our newly proposed approaches exhibit similarly good performance and may be applied in a wide range of settings.},
keywords = {IPTW estimator,Marginal structural model,Positivity assumption,Survival analysis,Weight truncation},
publisher = {Walter de Gruyter GmbH}}
@article{Robins2000_8748,
url = {https://journals.lww.com/epidem/Fulltext/2000/09000/Marginal_Structural_Models_and_Causal_Inference_in.11.aspx},
issn = {1044-3983},
year = {2000},
title = {{Marginal Structural Models and Causal Inference in Epidemiology}},
author = {Robins, James M and Hern{\'{a}}n, Miguel {\'{A}}ngel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
abstract = {In observational studies with exposures or treatments that vary over time, standard approaches for adjustment of confounding are biased when there exist time-dependent confounders that are also affected by previous treatment. This paper introduces marginal structural models, a new class of causal models that allow for improved adjustment of confounding in those situations. The parameters of a marginal structural model can be consistently estimated using a new class of estimators, the inverse-probability-of-treatment weighted estimators.},
keywords = {causality,confounding,counterfactuals,epidemiologic methods,intermediate variables,longitudinal data,structural models}}
@article{Sturmer2010TreatmentStudy_ca6b,
doi = {10.1093/aje/kwq198},
url = {https://pubmed.ncbi.nlm.nih.gov/20716704/},
issn = {14766256},
pmid = {20716704},
year = {2010},
pages = {843--854},
title = {{Treatment effects in the presence of unmeasured confounding: Dealing with observations in the tails of the propensity score distribution-A simulation study}},
author = {St{\"{u}}rmer, Til and Rothman, Kenneth J and Avorn, Jerry and Glynn, Robert J},
number = {7},
volume = {172},
journal = {American Journal of Epidemiology},
keywords = {bias (epidemiology),causal inference,cohort studies,confounding factors (epidemiology),epidemiologic methods,models,propensity score,research design,statistical},
publisher = {Oxford University Press}}
@article{Luque-Fernandez2020_94c7,
year = {2020},
title = {{Delta Method in Epidemiology: An Applied and Reproducible Tutorial}},
author = {Luque-Fernandez, M A},
journal = {GitHub repository}}
@article{Robins1986_d6f4,
doi = {https://doi.org/10.1016/0270-0255(86)90088-6},
url = {http://www.sciencedirect.com/science/article/pii/0270025586900886},
isbn = {0270-0255},
year = {1986},
pages = {1393--1512},
title = {{A new approach to causal inference in mortality studies with a sustained exposure period—application to control of the healthy worker survivor effect}},
author = {Robins, James},
number = {9},
volume = {7},
journal = {Mathematical Modelling}}
@article{doi:10.1002/sim.7628_5951,
doi = {10.1002/sim.7628},
url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/sim.7628},
year = {2018},
title = {{Targeted maximum likelihood estimation for a binary treatment: A tutorial}},
author = {Luque-Fernandez, Miguel Angel and Schomaker, Michael and Rachet, Bernard and Schnitzer, Mireille E},
volume = {2018},
journal = {Statistics in Medicine},
abstract = {When estimating the average effect of a binary treatment (or exposure) on an outcome, methods that incorporate propensity scores, the G-formula, or targeted maximum likelihood estimation (TMLE) are preferred over na{\"\i}ve regression approaches, which are biased under misspecification of a parametric outcome model. In contrast propensity score methods require the correct specification of an exposure model. Double-robust methods only require correct specification of either the outcome or the exposure model. Targeted maximum likelihood estimation is a semiparametric double-robust method that improves the chances of correct model specification by allowing for flexible estimation using (nonparametric) machine-learning methods. It therefore requires weaker assumptions than its competitors. We provide a step-by-step guided implementation of TMLE and illustrate it in a realistic scenario based on cancer epidemiology where assumptions about correct model specification and positivity (ie, when a study participant had 0 probability of receiving the treatment) are nearly violated. This article provides a concise and reproducible educational introduction to TMLE for a binary outcome and exposure. The reader should gain sufficient understanding of TMLE from this introductory tutorial to be able to apply the method in practice. Extensive R-code is provided in easy-to-read boxes throughout the article for replicability. Stata users will find a testing implementation of TMLE and additional material in the Appendix S1 and at the following GitHub repository:https://github.com/migariane/SIM-TMLE-tutorial},
keywords = {causal inference,ensemble Learning,machine learning,observational studies,targeted maximum likelihood estimation}}
@book{Efron1982_b84f,
year = {1982},
title = {{The jackknife, the bootstrap and other resampling plans}},
author = {Efron, Bradley},
volume = {38},
publisher = {SIAM}}
@article{Daniel2018,
doi = {10.1002/9781118445112.STAT08068},
year = {2018},
month = {aug},
pages = {1--14},
title = {{Double Robustness}},
author = {Daniel, Rhian M.},
journal = {Wiley StatsRef: Statistics Reference Online},
abstract = {Double robustness is a prevalent topic in current statistical thinking, especially in causal inference and missing data methods. The most popular class of doubly robust (DR) estimators—also known as locally efficient augmented inverse probability weighted (AIPW) estimators—possess additional properties, linked to but distinct from double robustness, which lead to tractable statistical inferences and other attractive features.},
publisher = {Wiley}}
@article{Rubin1974_a69a,
year = {1974},
pages = {688},
title = {{Estimating causal effects of treatments in randomized and nonrandomized studies.}},
author = {Rubin, Donald B},
number = {5},
volume = {66},
journal = {Journal of educational Psychology},
publisher = {American Psychological Association}}
@article{Connors1996_f0ca,
doi = {10.1001/jama.276.11.889},
url = {https://pubmed.ncbi.nlm.nih.gov/8782638/},
issn = {00987484},
pmid = {8782638},
year = {1996},
month = {sep},
pages = {889--897},
title = {{The effectiveness of right heart catheterization in the initial care of critically ill patients}},
author = {Connors, Alfred F. and Speroff, Theodore and Dawson, Neal V. and Thomas, Charles and Harrell, Frank E. and Wagner, Douglas and Desbiens, Norman and Goldman, Lee and Wu, Albert W. and Califf, Robert M. and Fulkerson, William J. and Vidaillet, Humberto and Broste, Steven and Bellamy, Paul and Lynn, Joanne and Knaus, William A.},
number = {11},
volume = {276},
journal = {Journal of the American Medical Association},
abstract = {Objective.- To examine the association between the use of right heart catheterization (RHC) during the first 24 hours of care in the intensive care unit (ICU) and subsequent survival, length of stay, intensity of care, and cost of care. Design.- Prospective cohort study. Setting.- Five US teaching hospitals between 1989 and 1994. Subjects.- A total of 5735 critically ill adult patients receiving care in an ICU for 1 of 9 prespecified disease categories. Main Outcome Measures.- Survival time, cost of care, intensity of care, and length of stay in the ICU and hospital, determined from the clinical record and from the National Death Index. A propensity score for RHC was constructed using multivariable logistic regression. Case-matching and multivariable regression modeling techniques were used to estimate the association of RHC with specific outcomes after adjusting for treatment selection using the propensity score. Sensitivity analysis was used to estimate the potential effect of an unidentified or missing covariate on the results. Results.- By case-matching analysis, patients with RHC had an increased 30-day mortality (odds ratio, 1.24; 95% confidence interval, 1.03- 1.49). The mean cost (25th, 50th, 75th percentiles) per hospital stay was $49300 ($17000, $30500, $56600) with RHC and $35 700 ($11 300, $20600, $39200) without RHC. Mean length of stay in the ICU was 14.8 (5, 9, 17) days with RHC and 13.0 (4, 7, 14) days without RHC. These findings were all confirmed by multivariable modeling techniques. Subgroup analysis did not reveal any patient group or site for which RHC was associated with improved outcomes. Patients with higher baseline probability of surviving 2 months had the highest relative risk of death following RHC. Sensitivity analysis suggested that a missing covariate would have to increase the risk of death 6-fold and the risk of RHC 6-fold for a true beneficial effect of RHC to be misrepresented as harmful. Conclusion.- In this observational study of critically ill patients, after adjustment for treatment selection bias, RHC was associated with increased mortality and increased utilization of resources. The cause of this apparent lack of benefit is unclear. The results of this analysis should be confirmed in other observational studies. These findings justify reconsideration of a randomized controlled trial of RHC and may guide patient selection for such a study.},
keywords = {A F Connors,APACHE,Aged,Catheterization,Cohort Studies,Critical Illness* / economics,Critical Illness* / mortality,Female,Health Care Costs,Health Care*,Hospital Mortality,Humans,Intensive Care Units* / economics,Length of Stay / economics,Linear Models,Logistic Models,MEDLINE,Male,Middle Aged,Multicenter Study,Multivariate Analysis,NCBI,NIH,NLM,National Center for Biotechnology Information,National Institutes of Health,National Library of Medicine,Non-U.S. Gov't,Outcome and Process Assessment,Prognosis,Proportional Hazards Models,Prospective Studies,PubMed Abstract,Research Support,Sensitivity and Specificity,Survival Rate,Swan-Ganz* / economics,T Speroff,United States,W A Knaus,doi:10.1001/jama.276.11.889,pmid:8782638},
publisher = {JAMA}}
@book{Efron1993_4b16,
url = {http://www.loc.gov/catdir/enhancements/fy0730/93004489-d.html},
isbn = {0412042312},
year = {1993},
title = {{An introduction to the bootstrap}},
author = {Efron, Bradley and Tibshirani, Robert},
volume = {57},
address = {New York},
publisher = {Chapman & Hall}}
@article{Zivich2020a,
url = {https://zenodo.org/record/3339870/export/hx https://github.com/pzivich/Python-for-Epidemiologists},
year = {2020},
title = {{Python for Epidemiologists (v0.9.0)}},
author = {Zivich, Paul N},
journal = {Zenodo},
publisher = {Zenodo}}
@article{Diaz2020,
doi = {10.1093/BIOSTATISTICS/KXZ042},
url = {https://pubmed.ncbi.nlm.nih.gov/31742333/},
file = {::},
issn = {1468-4357},
pmid = {31742333},
year = {2020},
month = {apr},
pages = {353--358},
title = {{Machine learning in the estimation of causal effects: targeted minimum loss-based estimation and double/debiased machine learning}},
author = {D{\'{i}}az, Iv{\'{a}}n},
number = {2},
volume = {21},
journal = {Biostatistics (Oxford, England)},
abstract = {In recent decades, the fields of statistical and machine learning have seen a revolution in the development of data-adaptive regression methods that have optimal performance under flexible, sometimes minimal, assumptions on the true regression functions. These developments have impacted all areas of applied and theoretical statistics and have allowed data analysts to avoid the biases incurred under the pervasive practice of parametric model misspecification. In this commentary, I discuss issues around the use of data-adaptive regression in estimation of causal inference parameters. To ground ideas, I focus on two estimation approaches with roots in semi-parametric estimation theory: targeted minimum loss-based estimation (TMLE; van der Laan and Rubin, 2006) and double/debiased machine learning (DML; Chernozhukov and others, 2018). This commentary is not comprehensive, the literature on these topics is rich, and there are many subtleties and developments which I do not address. These two frameworks represent only a small fraction of an increasingly large number of methods for causal inference using machine learning. To my knowledge, they are the only methods grounded in statistical semi-parametric theory that also allow unrestricted use of data-adaptive regression techniques.},
keywords = {Biostatistics*,Causality,Data Interpretation,Humans,Iv{\'{a}}n D{\'{i}}az,MEDLINE,Machine Learning*,Models,NCBI,NIH,NLM,National Center for Biotechnology Information,National Institutes of Health,National Library of Medicine,PubMed Abstract,Statistical*,doi:10.1093/biostatistics/kxz042,pmid:31742333},
publisher = {Biostatistics}}
@inproceedings{Canty_f9c6,
title = {{Resampling Methods in R : The boot Package}},
author = {Canty, Angelo J}}
@techreport{Dominici_d082,
url = {https://www.goodreads.com/shelf/show/causality},
file = {::},
title = {{FROM CONTROLLED TO UNDISCIPLINED DATA: ESTIMATING CAUSAL EFFECTS IN THE ERA OF DATA SCIENCE USING A POTENTIAL OUTCOME FRAMEWORK}},
author = {Dominici, Francesca and Bargagli-Stoffi, Falco J and Mealli, Fabrizia},
eprint = {2012.06865v1},
arxivId = {2012.06865v1},
abstract = {This paper discusses the fundamental principles of causal inference-the area of statistics that estimates the effect of specific occurrences, treatments, interventions, and exposures on a given outcome from experimental and observational data. We explain the key assumptions required to identify causal effects, and highlight the challenges associated with the use of observational data. We emphasize that experimental thinking is crucial in causal inference. The quality of the data (not necessarily the quantity), the study design, the degree to which the assumptions are met, and the rigor of the statistical analysis allow us to credibly infer causal effects. Although we advocate leveraging the use of big data and the application of machine learning (ML) algorithms for estimating causal effects, they are not a substitute of thoughtful study design. Concepts are illustrated via examples.},
archivePrefix = {arXiv}}
@article{Horvitz1952_79e5,
doi = {10.2307/2280784},
issn = {01621459},
year = {1952},
month = {dec},
pages = {663},
title = {{A Generalization of Sampling Without Replacement From a Finite Universe}},
author = {Horvitz, D. G. and Thompson, D. J.},
number = {260},
volume = {47},
journal = {Journal of the American Statistical Association},
abstract = {Many researchers have proposed that the near space immediately surrounding the body is represented differently than more distant space. Indeed, it has often been suggested that near space encompasses that within arm's reach. The present study used a line bisection task in healthy adults to investigate the effects of tool use on space perception, and the nature of the transition between near and far space. Subjects bisected lines at four distances controlled for both veridical and angular size using a laser pointer and a set of sticks. When the laser pointer was used, a left to right shift in bias was observed as stimuli were moved from near to far space. When a tool was used, however, a leftward bias was observed at all distances, similar to that observed with the laser pointer in near space. These results suggest that the tool expanded the range of near space. Additionally, the transition from near to far space was gradual, with no abrupt shift at arm's length (or at any other distance). In contrast to theories describing near space as that within arm's reach, these findings suggest that the representation of near space is less rigid, extending with tool use and gradually transitioning into far space.},
publisher = {JSTOR}}
@article{Chernozhukov2018,
doi = {10.1111/ectj.12097},
issn = {1368423X},
year = {2018},
title = {{Double/debiased machine learning for treatment and structural parameters}},
author = {Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Duflo, Esther and Hansen, Christian and Newey, Whitney and Robins, James},
journal = {Econometrics Journal},
abstract = {We revisit the classic semi-parametric problem of inference on a low-dimensional parameter $\theta$0 in the presence of high-dimensional nuisance parameters $\eta$0. We depart from the classical setting by allowing for $\eta$0 to be so high-dimensional that the traditional assumptions (e.g. Donsker properties) that limit complexity of the parameter space for this object break down. To estimate $\eta$0, we consider the use of statistical or machine learning (ML) methods, which are particularly well suited to estimation in modern, very high-dimensional cases. ML methods perform well by employing regularization to reduce variance and trading off regularization bias with overfitting in practice. However, both regularization bias and overfitting in estimating $\eta$0 cause a heavy bias in estimators of $\theta$0 that are obtained by naively plugging ML estimators of $\eta$0 into estimating equations for $\theta$0. This bias results in the naive estimator failing to be N-1/2 consistent, where N is the sample size. We show that the impact of regularization bias and overfitting on estimation of the parameter of interest $\theta$0 can be removed by using two simple, yet critical, ingredients: (1) using Neyman-orthogonal moments/scores that have reduced sensitivity with respect to nuisance parameters to estimate $\theta$0; (2) making use of cross-fitting, which provides an efficient form of data-splitting. We call the resulting set of methods double or debiased ML (DML). We verify that DML delivers point estimators that concentrate in an N-1 -neighbourhood of the true parameter values and are approximately unbiased and normally distributed, which allows construction of valid confidence statements. The generic statistical theory of DML is elementary and simultaneously relies on only weak theoretical requirements, which will admit the use of a broad array of modern ML methods for estimating the nuisance parameters, such as random forests, lasso, ridge, deep neural nets, boosted trees, and various hybrids and ensembles of these methods. We illustrate the general theory by applying it to provide theoretical properties of the following: DML applied to learn the main regression parameter in a partially linear regression model; DML applied to learn the coefficient on an endogenous variable in a partially linear instrumental variables model; DML applied to learn the average treatment effect and the average treatment effect on the treated under unconfoundedness; DML applied to learn the local average treatment effect in an instrumental variables setting. In addition to these theoretical applications, we also illustrate the use of DML in three empirical examples.}}
@article{Greenland2015_5872,
doi = {10.1007/s10654-015-9995-7},
url = {https://link.springer.com/article/10.1007/s10654-015-9995-7},
issn = {15737284},
pmid = {25687168},
year = {2015},
month = {oct},
pages = {1101--1110},
title = {{Limitations of individual causal models, causal graphs, and ignorability assumptions, as illustrated by random confounding and design unfaithfulness}},
author = {Greenland, Sander and Mansournia, Mohammad Ali},
number = {10},
volume = {30},
journal = {European Journal of Epidemiology},
abstract = {We describe how ordinary interpretations of causal models and causal graphs fail to capture important distinctions among ignorable allocation mechanisms for subject selection or allocation. We illustrate these limitations in the case of random confounding and designs that prevent such confounding. In many experimental designs individual treatment allocations are dependent, and explicit population models are needed to show this dependency. In particular, certain designs impose unfaithful covariate-treatment distributions to prevent random confounding, yet ordinary causal graphs cannot discriminate between these unconfounded designs and confounded studies. Causal models for populations are better suited for displaying these phenomena than are individual-level models, because they allow representation of allocation dependencies as well as outcome dependencies across individuals. Nonetheless, even with this extension, ordinary graphical models still fail to capture distinctions between hypothetical superpopulations (sampling distributions) and observed populations (actual distributions), although potential-outcome models can be adapted to show these distinctions and their consequences.},
keywords = {Causal graphs,Confounding,Directed acyclic graphs,Ignorability,Inverse probability weighting,Unfaithfulness},
publisher = {Springer Netherlands}}
@article{Goetghebeur2020,
doi = {10.1002/sim.8741},
url = {www.ofcaus.org},
file = {::},
issn = {10970258},
pmid = {32964526},
year = {2020},
month = {dec},
pages = {4922--4948},
title = {{Formulating causal questions and principled statistical answers}},
author = {Goetghebeur, Els and le Cessie, Saskia and {De Stavola}, Bianca and Moodie, Erica E.M. and Waernbaum, Ingeborg},
eprint = {1906.12100},
number = {30},
volume = {39},
arxivId = {1906.12100},
journal = {Statistics in Medicine},
abstract = {Although review papers on causal inference methods are now available, there is a lack of introductory overviews on what they can render and on the guiding criteria for choosing one particular method. This tutorial gives an overview in situations where an exposure of interest is set at a chosen baseline (“point exposure”) and the target outcome arises at a later time point. We first phrase relevant causal questions and make a case for being specific about the possible exposure levels involved and the populations for which the question is relevant. Using the potential outcomes framework, we describe principled definitions of causal effects and of estimation approaches classified according to whether they invoke the no unmeasured confounding assumption (including outcome regression and propensity score-based methods) or an instrumental variable with added assumptions. We mainly focus on continuous outcomes and causal average treatment effects. We discuss interpretation, challenges, and potential pitfalls and illustrate application using a “simulation learner,” that mimics the effect of various breastfeeding interventions on a child's later development. This involves a typical simulation component with generated exposure, covariate, and outcome data inspired by a randomized intervention study. The simulation learner further generates various (linked) exposure types with a set of possible values per observation unit, from which observed as well as potential outcome data are generated. It thus provides true values of several causal effects. R code for data generation and analysis is available on www.ofcaus.org, where SAS and Stata code for analysis is also provided.},
keywords = {causation,instrumental variable,inverse probability weighting,matching,potential outcomes,propensity score},
publisher = {John Wiley and Sons Ltd},
archivePrefix = {arXiv}}
@misc{105a6637-2fd8-45cb-8626-8c68a7fb287e,
url = {https://www.springer.com/gp/book/9780387251455},
title = {{All of Nonparametric Statistics | Larry Wasserman | Springer}},
urldate = {2021-06-23}}
@article{Schuler2017,
doi = {10.1093/aje/kww165},
url = {https://academic.oup.com/aje/article/185/1/65/2662306},
file = {::},
issn = {14766256},
pmid = {27941068},
year = {2017},
month = {jan},
pages = {65--73},
title = {{Targeted maximum likelihood estimation for causal inference in observational studies}},
author = {Schuler, Megan S. and Rose, Sherri},
number = {1},
volume = {185},
journal = {American Journal of Epidemiology},
abstract = {Estimation of causal effects using observational data continues to grow in popularity in the epidemiologic literature. While many applications of causal effect estimation use propensity score methods or G-computation, targeted maximum likelihood estimation (TMLE) is a well-established alternative method with desirable statistical properties. TMLE is a doubly robust maximum-likelihood-based approach that includes a secondary "targeting" step that optimizes the bias-variance tradeoff for the target parameter. Under standard causal assumptions, estimates can be interpreted as causal effects. Because TMLE has not been as widely implemented in epidemiologic research, we aim to provide an accessible presentation of TMLE for applied researchers. We give stepby-step instructions for using TMLE to estimate the average treatment effect in the context of an observational study. We discuss conceptual similarities and differences between TMLE and 2 common estimation approaches (G-computation and inverse probability weighting) and present findings on their relative performance using simulated data. Our simulation study compares methods under parametric regression misspecification; our results highlight TMLE's property of double robustness. Additionally, we discuss best practices for TMLE implementation, particularly the use of ensembled machine learning algorithms. Our simulation study demonstrates all methods using super learning, highlighting that incorporation of machine learning may outperform parametric regression in observational data settings.},
keywords = {Causal inference,Machine learning,Observational studies,Super learner,Targeted maximum likelihood estimation},
publisher = {Oxford University Press}}
@article{Kavroudakis2015,
year = {2015},
title = {{Sms: An R package for the construction of microdata for geographical analysis}},
author = {Kavroudakis, Dimitris and Others},
number = {i02},
volume = {68},
journal = {Journal of Statistical Software},
publisher = {Foundation for Open Access Statistics}}
@article{Hernan2000,
doi = {10.1097/00001648-200009000-00012},
url = {https://pubmed.ncbi.nlm.nih.gov/10955409/},
issn = {10443983},
pmid = {10955409},
year = {2000},
pages = {561--570},
title = {{Marginal structural models to estimate the causal effect of zidovudine on the survival of HIV-positive men}},
author = {Hern{\'{a}}n, Miguel {\'{A}}ngel and Brumback, Babette and Robins, James M.},
number = {5},
volume = {11},
journal = {Epidemiology},
abstract = {Standard methods for survival analysis, such as the time-dependent Cox model, may produce biased effect estimates when there exist time-dependent confounders that are themselves affected by previous treatment or exposure. Marginal structural models are a new class of causal models the parameters of which are estimated through inverse-probability-of-treatment weighting; these models allow for appropriate adjustment for confounding. We describe the marginal structural Cox proportional hazards model and use it to estimate the causal effect of zidovudine on the survival of human immuno-deficiency virus-positive men participating in the Multicenter AIDS Cohort Study. In this study, CD4 lymphocyte count is both a time-dependent confounder of the causal effect of zidovudine on survival and is affected by past zidovudine treatment. The crude mortality rate ratio (95% confidence interval) for zidovudine was 3.6 (3.0-4.3), which reflects the presence of confounding. After controlling for baseline CD4 count and other baseline covariates using standard methods, the mortality rate ratio decreased to 2.3 (1.9-2.8). Using a marginal structural Cox model to control further for time-dependent confounding due to CD4 count and other time-dependent covariates, the mortality rate ratio was 0.7 (95% conservative confidence interval = 0.6-1.0). We compare marginal structural models with previously proposed causal methods.},
keywords = {AIDS,Causality,Confounding,Counterfactuals,Epidemiologic methods,Intermediate variables,Longitudinal data,Structural models,Survival analysis},
publisher = {Epidemiology}}
@article{Jung2019_fba3,
doi = {10.3389/fpsyg.2019.02215},
url = {https://www.frontiersin.org/article/10.3389/fpsyg.2019.02215/full},
issn = {1664-1078},
year = {2019},
pages = {2215},
title = {{Comparison of Bootstrap Confidence Interval Methods for GSCA Using a Monte Carlo Simulation}},
author = {Jung, Kwanghee and Lee, Jaehoon and Gupta, Vibhuti and Cho, Gyeongcheol},
volume = {10},
journal = {Frontiers in Psychology},
keywords = {Monte Carlo simulation,bootstrap methods,confidence intervals,generalized structured component analysis (GSCA),structural equation modeling (SEM)},
publisher = {Frontiers Media S.A.}}
@misc{Bruin2011_5994,
url = {http://www.ats.ucla.edu/stat/stata/ado/analysis/},
year = {2011},
title = {{newtest: command to compute new test @ONLINE}},
author = {Bruin, J}}
@article{Sturmer2010,
doi = {10.1093/aje/kwq198},
url = {/pmc/articles/PMC3025652/ /pmc/articles/PMC3025652/?report=abstract https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3025652/},
file = {::},
issn = {14766256},
pmid = {20716704},
year = {2010},
month = {oct},
pages = {843--854},
title = {{Treatment effects in the presence of unmeasured confounding: Dealing with observations in the tails of the propensity score distribution-A simulation study}},
author = {St{\"{u}}rmer, Til and Rothman, Kenneth J. and Avorn, Jerry and Glynn, Robert J.},
number = {7},
volume = {172},
journal = {American Journal of Epidemiology},
abstract = {Frailty, a poorly measured confounder in older patients, can promote treatment in some situations and discourage it in others. This can create unmeasured confounding and lead to nonuniform treatment effects over the propensity score (PS). The authors compared bias and mean squared error for various PS implementations under PS trimming, thereby excluding persons treated contrary to prediction. Cohort studies were simulated with a binary treatment T as a function of 8 covariates X. Two of the covariates were assumed to be unmeasured strong risk factors for the outcome and present in persons treated contrary to prediction. The outcome Y was simulated as a Poisson function of T and all X's. In analyses based on measured covariates only, the range of PS's was trimmed asymmetrically according to the percentile of PS in treated patients at the lower end and in untreated patients at the upper end. PS trimming reduced bias due to unmeasured confounders and mean squared error in most scenarios assessed. Treatment effect estimates based on PS range restrictions do not correspond to a causal parameter but may be less biased by such unmeasured confounding. Increasing validity based on PS trimming may be a unique advantage of PS's over conventional outcome models. {\textcopyright} 2010 The Author.},
keywords = {bias (epidemiology),causal inference,cohort studies,confounding factors (epidemiology),epidemiologic methods,models,propensity score,research design,statistical},
publisher = {Oxford University Press}}
@article{Robins_2000_b909,
doi = {10.1097/00001648-200009000-00011},
url = {http://dx.doi.org/10.1097/00001648-200009000-00011},
issn = {1044-3983},
year = {2000},
month = {sep},
pages = {550--560},
title = {{Marginal Structural Models and Causal Inference in Epidemiology}},
author = {Robins, James M and Hern{\'{a}}n, Miguel {\'{A}}ngel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
publisher = {Ovid Technologies (Wolters Kluwer Health)}}
@article{Cai2019_71ff,
url = {https://arxiv.org/pdf/1905.10299.pdf},
year = {2019},
title = {{Nonparametric Bootstrap Inference for the Targeted Highly Adaptive LASSO Estimator}},
author = {Cai, Weixin and van der Laan, Mark},
abstract = {The Highly-Adaptive-LASSO Targeted Minimum Loss Estimator (HAL-TMLE) is an efficient plug-in estimator of a pathwise differentiable parameter in a statistical model that at minimal (and possibly only) assumes that the sectional variation norm of the true nuisance functional parameters (i.e., the relevant part of data distribution) are finite. It relies on an initial estimator (HAL-MLE) of the nuisance functional parameters by minimizing the empirical risk over the parameter space under the constraint that the sectional variation norm of the candidate functions are bounded by a constant, where this constant can be selected with cross-validation. In this article, we establish that the nonparametric bootstrap for the HAL-TMLE, fixing the value of the sectional variation norm at a value larger or equal than the cross-validation selector, provides a consistent method for estimating the normal limit distribution of the HAL-TMLE. In order to optimize the finite sample coverage of the nonparametric bootstrap confidence intervals, we propose a selection method for this sectional variation norm that is based on running the nonparametric bootstrap for all values of the sectional variation norm larger than the one selected by cross-validation, and subsequently determining a value at which the width of the resulting confidence intervals reaches a plateau. We demonstrate our method for 1) nonparametric estimation of the average treatment effect based on observing on each unit a covariate vector, binary treatment, and outcome, and for 2) nonparametric estimation of the integral of the square of the multivariate density of the data distribution. In addition, we also present simulation results for these two examples demonstrating the excellent finite sample coverage of bootstrap-based confidence intervals.}}
@article{Levy2018_ceda,
url = {https://arxiv.org/pdf/1811.04573.pdf},
year = {2018},
title = {{An Easy Implementation of CV-TMLE}},
author = {Levy, Jonathan},
journal = {arXiv},
abstract = {In the world of targeted learning, cross-validated targeted maximum likelihood estimators, CV-TMLE [Zheng:2010aa], has a distinct advantage over TMLE [Laan:2006aa] in that one less condition is required of CV-TMLE in order to achieve asymptotic efficiency in the nonparametric or semiparametric settings. CV-TMLE as originally formulated, consists of averaging usually 10 (for 10-fold cross-validation) parameter estimates, each of which is performed on a validation set separate from where the initial fit was trained. The targeting step is usually performed as a pooled regression over all validation folds but in each fold, we separately evaluate any means as well as the parameter estimate. One nice thing about CV-TMLE, is that we average 10 plug-in estimates so the plug-in quality of preserving the natural parameter bounds is respected. Our adjustment of this procedure also preserves the plug-in characteristic as well as avoids the donsker condtion. The advantage of our procedure is the implementation of the targeting is identical to that of a regular TMLE, once all the validation set initial predictions have been formed. In short, we stack the validation set predictions and pretend as if we have a regular TMLE, which is not necessarily quite a plug-in estimator on each fold but overall will perform asymptotically the same and might have some slight advantage, a subject for future research. In the case of average treatment effect, treatment specific mean and mean outcome under a stochastic intervention, the procedure overlaps exactly with the originally formulated CV-TMLE with a pooled regression for the targeting.}}
@book{Wolfram1992_4f0d,
isbn = {020151012X},
year = {1992},
title = {{Mathematica reference guide}},
author = {Wolfram, Stephen},
address = {Reading, Mass.},
publisher = {Addison-Wesley Pub. Co.}}
@article{Rubin2011_2748,
url = {http://dx.doi.org/10.1198/016214504000001880},
year = {2005},
pages = {322--331},
title = {{Causal inference using potential outcomes}},
author = {Rubin, Donald B},
number = {469},
volume = {100},
journal = {Journal of the American Statistical Association},
abstract = {Causal effects are defined as comparisons of potential outcomes under different treatments on a common set of units. Observed values of the potential outcomes are revealed by the assignment mechanism---a probabilistic model for the treatment each unit receives as a function of covariates and potential outcomes. Fisher made tremendous contributions to causal inference through his work on the design of randomized experiments, but the potential outcomes perspective applies to other complex experiments and nonrandomized studies as well. As noted by Kempthorne in his 1976 discussion of Savage's Fisher lecture, Fisher never bridged his work on experimental design and his work on parametric modeling, a bridge that appears nearly automatic with an appropriate view of the potential outcomes framework, where the potential outcomes and covariates are given a Bayesian distribution to complete the model specification. Also, this framework crisply separates scientific inference for causal effects and decisions based on such inference, a distinction evident in Fisher's discussion of tests of significance versus tests in an accept/reject framework. But Fisher never used the potential outcomes framework, originally proposed by Neyman in the context of randomized experiments, and as a result he provided generally flawed advice concerning the use of the analysis of covariance to adjust for posttreatment concomitants in randomized trials.},
publisher = {Taylor & Francis}}
@book{Buhlmann2016_84ec,
year = {2016},
title = {{Handbook of big data}},
author = {B{\"{u}}hlmann, Peter and Drineas, Petros and van der Laan, Mark and Kane, Michael},
publisher = {CRC Press}}
@article{Austin2009,
doi = {10.1002/sim.3697},
url = {/pmc/articles/PMC3472075/ /pmc/articles/PMC3472075/?report=abstract https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3472075/},
file = {::},
issn = {02776715},
pmid = {19757444},
year = {2009},
month = {nov},
pages = {3083--3107},
title = {{Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples}},
author = {Austin, Peter C.},
number = {25},
volume = {28},
journal = {Statistics in Medicine},
abstract = {The propensity score is a subject's probability of treatment, conditional on observed baseline covariates. Conditional on the true propensity score, treated and untreated subjects have similar distributions of observed baseline covariates. Propensity-score matching is a popular method of using the propensity score in the medical literature. Using this approach, matched sets of treated and untreated subjects with similar values of the propensity score are formed. Inferences about treatment effect made using propensity-score matching are valid only if, in the matched sample, treated and untreated subjects have similar distributions of measured baseline covariates. In this paper we discuss the following methods for assessing whether the propensity score model has been correctly specified: comparing means and prevalences of baseline characteristics using standardized differences; ratios comparing the variance of continuous covariates between treated and untreated subjects; comparison of higher order moments and interactions; five-number summaries; and graphical methods such as quantile-quantile plots, side-byside boxplots, and non-parametric density plots for comparing the distribution of baseline covariates between treatment groups. We describe methods to determine the sampling distribution of the standardized difference when the true standardized difference is equal to zero, thereby allowing one to determine the range of standardized differences that are plausible with the propensity score model having been correctly specified. We highlight the limitations of some previously used methods for assessing the adequacy of the specification of the propensity-score model. In particular, methods based on comparing the distribution of the estimated propensity score between treated and untreated subjects are uninformative. Copyright {\textcopyright} 2009 John Wiley & Sons, Ltd.},
keywords = {Balance,Bias,Goodness-of-fit,Matching,Observational study,Propensity score,Propensity-score matching,Standardized difference},
publisher = {Wiley-Blackwell}}
@article{Rosenbaum1983_19ad,
year = {1983},
pages = {41--55},
title = {{The central role of the propensity score in observational studies for causal effects}},
author = {Rosenbaum, Paul R and Rubin, Donald B},
number = {1},
volume = {70},
journal = {Biometrika},
publisher = {Biometrika Trust}}
@article{Chernozhukov2018a,
doi = {10.1111/ectj.12097},
issn = {1368423X},
year = {2018},
title = {{Double/debiased machine learning for treatment and structural parameters}},
author = {Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Duflo, Esther and Hansen, Christian and Newey, Whitney and Robins, James},
journal = {Econometrics Journal},
abstract = {We revisit the classic semi-parametric problem of inference on a low-dimensional parameter $\theta$0 in the presence of high-dimensional nuisance parameters $\eta$0. We depart from the classical setting by allowing for $\eta$0 to be so high-dimensional that the traditional assumptions (e.g. Donsker properties) that limit complexity of the parameter space for this object break down. To estimate $\eta$0, we consider the use of statistical or machine learning (ML) methods, which are particularly well suited to estimation in modern, very high-dimensional cases. ML methods perform well by employing regularization to reduce variance and trading off regularization bias with overfitting in practice. However, both regularization bias and overfitting in estimating $\eta$0 cause a heavy bias in estimators of $\theta$0 that are obtained by naively plugging ML estimators of $\eta$0 into estimating equations for $\theta$0. This bias results in the naive estimator failing to be N-1/2 consistent, where N is the sample size. We show that the impact of regularization bias and overfitting on estimation of the parameter of interest $\theta$0 can be removed by using two simple, yet critical, ingredients: (1) using Neyman-orthogonal moments/scores that have reduced sensitivity with respect to nuisance parameters to estimate $\theta$0; (2) making use of cross-fitting, which provides an efficient form of data-splitting. We call the resulting set of methods double or debiased ML (DML). We verify that DML delivers point estimators that concentrate in an N-1 -neighbourhood of the true parameter values and are approximately unbiased and normally distributed, which allows construction of valid confidence statements. The generic statistical theory of DML is elementary and simultaneously relies on only weak theoretical requirements, which will admit the use of a broad array of modern ML methods for estimating the nuisance parameters, such as random forests, lasso, ridge, deep neural nets, boosted trees, and various hybrids and ensembles of these methods. We illustrate the general theory by applying it to provide theoretical properties of the following: DML applied to learn the main regression parameter in a partially linear regression model; DML applied to learn the coefficient on an endogenous variable in a partially linear instrumental variables model; DML applied to learn the average treatment effect and the average treatment effect on the treated under unconfoundedness; DML applied to learn the local average treatment effect in an instrumental variables setting. In addition to these theoretical applications, we also illustrate the use of DML in three empirical examples.}}
@article{Basu2011AnOne,
doi = {10.1007/978-1-4419-5825-9{\_}24},
year = {2011},
pages = {167--206},
title = {{An Essay on the Logical Foundations of Survey Sampling, Part One*}},
author = {Basu, D},
journal = {Selected Works of Debabrata Basu},
publisher = {Springer New York}}
@article{Robins1999_2641,
doi = {10.2307/20118224},
url = {https://www.jstor.org/stable/20118224 http://www.jstor.org/stable/20118224},
year = {1999},
pages = {151--179},
title = {{Association, Causation, and Marginal Structural Models}},
author = {Robins, James M.},
number = {1/2},
volume = {121},
journal = {Synthese},
publisher = {Springer}}
@article{Naimi2017_cf55,
url = {http://arxiv.org/abs/1711.07137},
file = {::},
year = {2017},
month = {nov},
title = {{Challenges in Obtaining Valid Causal Effect Estimates with Machine Learning Algorithms}},
author = {Naimi, Ashley I and Mishler, Alan E and Kennedy, Edward H},
eprint = {1711.07137},
arxivId = {1711.07137},
journal = {arXiv},
abstract = {Unlike parametric regression, machine learning (ML) methods do not generally require precise knowledge of the true data generating mechanisms. As such, numerous authors have advocated for ML methods to estimate causal effects. Unfortunately, ML algorithms can perform worse than parametric regression. We demonstrate the performance of ML-based single- and double-robust estimators. We use 100 Monte Carlo samples with sample sizes of 200, 1200, and 5000 to investigate bias and confidence interval coverage under several scenarios. In a simple confounding scenario, confounders were related to the treatment and the outcome via parametric models. In a complex confounding scenario, the simple confounders were transformed to induce complicated nonlinear relationships. In the simple scenario, when ML algorithms were used, double-robust estimators were superior to single-robust estimators. In the complex scenario, single-robust estimators with ML algorithms were at least as biased as estimators using misspecified parametric models. Double-robust estimators were less biased, but coverage was well below nominal. The use of sample splitting, inclusion of confounder interactions, reliance on a richly specified ML algorithm, and use of doubly robust estimators was the only explored approach that yielded negligible bias and nominal coverage. Our results suggest that ML based singly robust methods should be avoided.},
keywords = {causal inference,doubly-robust estimation,epidemiologic methods,machine learning,nonparametric methods,semiparametric theory},
archivePrefix = {arXiv}}
@article{Hernan2004_bd9f,
doi = {10.1136/jech.2002.006361},
url = {https://pubmed.ncbi.nlm.nih.gov/15026432 https://www.ncbi.nlm.nih.gov/pmc/articles/PMC1732737/},
issn = {0143-005X},
year = {2004},
month = {apr},
pages = {265--271},
title = {{A definition of causal effect for epidemiological research}},
author = {Hern{\'{a}}n, M A},
number = {4},
volume = {58},
journal = {Journal of epidemiology and community health},
abstract = {Estimating the causal effect of some exposure on some outcome is the goal of many epidemiological studies. This article reviews a formal definition of causal effect for such studies. For simplicity, the main description is restricted to dichotomous variables and assumes that no random error attributable to sampling variability exists. The appendix provides a discussion of sampling variability and a generalisation of this causal theory. The difference between association and causation is described-the redundant expression "causal effect" is used throughout the article to avoid confusion with a common use of "effect" meaning simply statistical association-and shows why, in theory, randomisation allows the estimation of causal effects without further assumptions. The article concludes with a discussion on the limitations of randomised studies. These limitations are the reason why methods for causal inference from observational data are needed.},
keywords = {*Causality,*Epidemiologic Studies,Humans,Randomized Controlled Trials as Topic/*standards,Research Design/standards},
language = {eng},
publisher = {BMJ Group}}
@article{Diaz2020a,
doi = {10.1093/biostatistics/kxz042},
issn = {14684357},
pmid = {31742333},
year = {2020},
title = {{Machine learning in the estimation of causal effects: targeted minimum loss-based estimation and double/debiased machine learning}},
author = {D{\'{i}}az, Iv{\'{a}}n},
journal = {Biostatistics (Oxford, England)},
abstract = {In recent decades, the fields of statistical and machine learning have seen a revolution in the development of data-adaptive regression methods that have optimal performance under flexible, sometimes minimal, assumptions on the true regression functions. These developments have impacted all areas of applied and theoretical statistics and have allowed data analysts to avoid the biases incurred under the pervasive practice of parametric model misspecification. In this commentary, I discuss issues around the use of data-adaptive regression in estimation of causal inference parameters. To ground ideas, I focus on two estimation approaches with roots in semi-parametric estimation theory: targeted minimum loss-based estimation (TMLE; van der Laan and Rubin, 2006) and double/debiased machine learning (DML; Chernozhukov and others, 2018). This commentary is not comprehensive, the literature on these topics is rich, and there are many subtleties and developments which I do not address. These two frameworks represent only a small fraction of an increasingly large number of methods for causal inference using machine learning. To my knowledge, they are the only methods grounded in statistical semi-parametric theory that also allow unrestricted use of data-adaptive regression techniques.},
keywords = {Causal inference,Double/debiased machine learning,Machine learning,Targeted minimum loss-based estimation}}
@article{Basu2011,
doi = {10.1007/978-1-4419-5825-9_24},
file = {::},
year = {2011},
pages = {167--206},
title = {{An Essay on the Logical Foundations of Survey Sampling, Part One*}},
author = {Basu, D.},
journal = {Selected Works of Debabrata Basu},
abstract = {In this paper, the statistical model for sample surveys is first put in the conventional set-up of ($\Omega$, $\alpha$, p ), and it is is shown that a maximal sufficiency reduction is always possible for a sample survey model. The corresponding minimal sufficient statistic is derived. We examine the role of the sufficiency and likelihood principles in the analysis of survey data and arrive at the revolutionary but reasonable conclusion that, once the sample has been drawn, the inference should not depend in any way on the sampling design. This poses the problem of designing a survey which will yield a good (representative) sample. The randomisation principle is examined from this view point and it is noticed that there is very little, if any, use for it in survey designs.},
publisher = {Springer New York}}
@article{Robins2000a,
doi = {10.1097/00001648-200009000-00011},
url = {http://europepmc.org/article/med/10955408},
issn = {10443983},
pmid = {10955408},
year = {2000},
month = {sep},
pages = {550--560},
title = {{Marginal structural models and causal inference in epidemiology}},
author = {Robins, James M. and Hern{\'{a}}n, Miguel {\'{A}}ngel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
abstract = {In observational studies with exposures or treatments that vary over time, standard approaches for adjustment of confounding are biased when there exist time-dependent confounders that are also affected by previous treatment. This paper introduces marginal structural models, a new class of causal models that allow for improved adjustment of confounding in those situations. The parameters of a marginal structural model can be consistently estimated using a new class of estimators, the inverse-probability-of-treatment weighted estimators.},
keywords = {Causality,Confounding,Counterfactuals,Epidemiologic methods,Intermediate variables,Longitudinal data,Structural models}}
@article{Gruber2012,
doi = {10.18637/jss.v051.i13},
url = {https://www.jstatsoft.org/index.php/jss/article/view/v051i13/v51i13.pdf https://www.jstatsoft.org/index.php/jss/article/view/v051i13},
file = {::},
issn = {15487660},
year = {2012},
month = {nov},
pages = {1--35},
title = {{tmle: An R package for targeted maximum likelihood estimation}},
author = {Gruber, Susan and van der Laan, Mark J.},
number = {13},
volume = {51},
journal = {Journal of Statistical Software},
abstract = {Targeted maximum likelihood estimation (TMLE) is a general approach for constructing an efficient double-robust semi-parametric substitution estimator of a causal effect parameter or statistical association measure. tmle is a recently developed R package that implements TMLE of the effect of a binary treatment at a single point in time on an outcome of interest, controlling for user supplied covariates, including an additive treatment effect, relative risk, odds ratio, and the controlled direct effect of a binary treatment controlling for a binary intermediate variable on the pathway from treatment to the outcome. Estimation of the parameters of a marginal structural model is also available. The package allows outcome data with missingness, and experimental units that contribute repeated records of the point-treatment data structure, thereby allowing the analysis of longitudinal data structures. Relevant factors of the likelihood may be modeled or fit data-adaptively according to user specifications, or passed in from an external estimation procedure. Effect estimates, variances, p values, and 95% confidence intervals are provided by the software.},
keywords = {Causal inference,Controlled direct effect,MSM,R,TMLE,Targeted maximum likelihood estimation},
publisher = {American Statistical Association}}
@book{Hajek1971,
year = {1971},
pages = {236},
title = {{Comment on An essay on the logical foundations of survey sampling by Basu, D. in Foundations of Statistical Inference (Godambe, V.P. and Sprott, D.A. eds.)}},
author = {Hajek, J.},
abstract = {Comment on An essay on the logical foundations of survey sampling by Basu, D. in Foundations of Statistical Inference (Godambe, V.P. and Sprott, D.A. eds.), p. 236. Holt, Rinehart and Winston.},
publisher = {Holt, Rinehart and Winston}}
@article{Dorie2019_1b36,
url = {http://dx.doi.org/10.1214/18-STS688},
year = {2019},
month = {feb},
pages = {94--99},
title = {{Rejoinder: Response to Discussions and a Look Ahead}},
author = {Dorie, Vincent and Hill, Jennifer and Shalit, Uri and Scott, Marc and Cervone, Dan},
number = {1},
volume = {34},
journal = {Statistical Science},
publisher = {Institute of Mathematical Statistics}}
@article{Cattaneo2010,
url = {https://econpapers.repec.org/RePEc:eee:econom:v:155:y:2010:i:2:p:138-154},
issn = {0304-4076},
year = {2010},
pages = {138--154},
title = {{Efficient semiparametric estimation of multi-valued treatment effects under ignorability}},
author = {Cattaneo, Matias D.},
number = {2},
volume = {155},
journal = {Journal of Econometrics},
abstract = {This paper studies the efficient estimation of a large class of multi-valued treatment effects as implicitly defined by a collection of possibly over-identified non-smooth moment conditions when the treatment assignment is assumed to be ignorable. Two estimators are introduced together with a set of sufficient conditions that ensure their -consistency, asymptotic normality and efficiency. Under mild assumptions, these conditions are satisfied for the Marginal Mean Treatment Effect and the Marginal Quantile Treatment Effect, estimands of particular importance for empirical applications. Previous results for average and quantile treatments effects are encompassed by the methods proposed here when the treatment is dichotomous. The results are illustrated by an empirical application studying the effect of maternal smoking intensity during pregnancy on birth weight, and a Monte Carlo experiment.},
keywords = {Multi,valued treatment effects Unconfoundedness Semipara},
publisher = {Elsevier}}
@article{article_7b30,
doi = {10.1214/09-SS057},
year = {2009},
pages = {96--146},
title = {{Causal Inference in Statistics: An Overview}},
author = {Pearl, Judea},
volume = {3},
journal = {Statistics Surveys}}
@article{Chernozhukov2018b,
doi = {10.1111/ectj.12097},
issn = {1368423X},
year = {2018},
title = {{Double/debiased machine learning for treatment and structural parameters}},
author = {Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Duflo, Esther and Hansen, Christian and Newey, Whitney and Robins, James},
journal = {Econometrics Journal},
abstract = {We revisit the classic semi-parametric problem of inference on a low-dimensional parameter $\theta$0 in the presence of high-dimensional nuisance parameters $\eta$0. We depart from the classical setting by allowing for $\eta$0 to be so high-dimensional that the traditional assumptions (e.g. Donsker properties) that limit complexity of the parameter space for this object break down. To estimate $\eta$0, we consider the use of statistical or machine learning (ML) methods, which are particularly well suited to estimation in modern, very high-dimensional cases. ML methods perform well by employing regularization to reduce variance and trading off regularization bias with overfitting in practice. However, both regularization bias and overfitting in estimating $\eta$0 cause a heavy bias in estimators of $\theta$0 that are obtained by naively plugging ML estimators of $\eta$0 into estimating equations for $\theta$0. This bias results in the naive estimator failing to be N-1/2 consistent, where N is the sample size. We show that the impact of regularization bias and overfitting on estimation of the parameter of interest $\theta$0 can be removed by using two simple, yet critical, ingredients: (1) using Neyman-orthogonal moments/scores that have reduced sensitivity with respect to nuisance parameters to estimate $\theta$0; (2) making use of cross-fitting, which provides an efficient form of data-splitting. We call the resulting set of methods double or debiased ML (DML). We verify that DML delivers point estimators that concentrate in an N-1 -neighbourhood of the true parameter values and are approximately unbiased and normally distributed, which allows construction of valid confidence statements. The generic statistical theory of DML is elementary and simultaneously relies on only weak theoretical requirements, which will admit the use of a broad array of modern ML methods for estimating the nuisance parameters, such as random forests, lasso, ridge, deep neural nets, boosted trees, and various hybrids and ensembles of these methods. We illustrate the general theory by applying it to provide theoretical properties of the following: DML applied to learn the main regression parameter in a partially linear regression model; DML applied to learn the coefficient on an endogenous variable in a partially linear instrumental variables model; DML applied to learn the average treatment effect and the average treatment effect on the treated under unconfoundedness; DML applied to learn the local average treatment effect in an instrumental variables setting. In addition to these theoretical applications, we also illustrate the use of DML in three empirical examples.}}
@book{Wasserman2006,
doi = {10.1007/0-387-30623-4},
year = {2006},
title = {{All of Nonparametric Statistics}},
author = {Wasserman, Larry},
abstract = {Aimed at Masters or PhD level students in statistics, computer science, and engineering, this comprehensive text provides the reader with a single book where ...},
booktitle = {All of Nonparametric Statistics},
publisher = {Springer New York}}
@article{Coyle2020_e4df,
url = {http://arxiv.org/abs/2006.07333},
year = {2020},
title = {{Targeting Learning: Robust Statistics for Reproducible Research}},
author = {Coyle, Jeremy R and Hejazi, Nima S and Malenica, Ivana and Phillips, Rachael V and Arnold, Benjamin F and Mertens, Andrew and Benjamin-Chung, Jade and Cai, Weixin and Dayal, Sonali and Colford, John M and Hubbard, Alan E and van der Laan, Mark J},
eprint = {2006.07333},
arxivId = {2006.07333},
journal = {arXiv},
archivePrefix = {arXiv}}
@book{Wackerly2002_8ac6,
year = {2002},
title = {{Mathematical Statistics with Applications}},
author = {Wackerly, Dennis D and III, William Mendenhall and Scheaffer, Richard L},
publisher = {Duxbury Advanced Series}}
@article{van2007_8425,
doi = {10.2202/1544-6115.1309},
url = {https://pubmed.ncbi.nlm.nih.gov/17910531/},
issn = {15446115},
pmid = {17910531},
year = {2007},
month = {sep},
title = {{Super learner}},
author = {{Van Der Laan}, Mark J. and Polley, Eric C. and Hubbard, Alan E. and der Laan, Mark J and Polley, Eric C. and Hubbard, Alan E.},
number = {1},
volume = {6},
journal = {Statistical applications in genetics and molecular biology},
abstract = {When trying to learn a model for the prediction of an outcome given a set of covariates, a statistician has many estimation procedures in their toolbox. A few examples of these candidate learners are: least squares, least angle regression, random forests, and spline regression. Previous articles (van der Laan and Dudoit (2003); van der Laan et al. (2006); Sinisi et al. (2007)) theoretically validated the use of cross validation to select an optimal learner among many candidate learners. Motivated by this use of cross validation, we propose a new prediction method for creating a weighted combination of many candidate learners to build the super learner. This article proposes a fast algorithm for constructing a super learner in prediction which uses V-fold cross-validation to select weights to combine an initial set of candidate learners. In addition, this paper contains a practical demonstration of the adaptivity of this so called super learner to various true data generating distributions. This approach for construction of a super learner generalizes to any parameter which can be defined as a minimizer of a loss function. Copyright {\textcopyright}2007 The Berkeley Electronic Press. All rights reserved.},
keywords = {Cross-validation,Loss-based estimation,Machine learning,Prediction},
publisher = {Berkeley Electronic Press}}
@article{doi:10.2105/AJPH.2018.304916_f08f,
doi = {10.2105/AJPH.2018.304916},
url = {https://doi.org/10.2105/AJPH.2018.304916},
year = {2019},
pages = {e12--e13},
title = {{Effect Modification and Collapsibility in Evaluations of Public Health Interventions}},
annote = {PMID: 30726131},
author = {Luque-Fernandez, Miguel Angel and Redondo-Sanchez, Daniel and Schomaker, Michael},
number = {3},
volume = {109},
journal = {American Journal of Public Health},
abstract = {The Evaluating Public Health Interventions AJPH series offers excellent practical guidance to public health researchers. The eighth part of the series provides a valuable introduction to effect estimations of time-invariant public health interventions. In their commentary Spiegelman and Zhou suggest that, in terms of bias and efficiency, there is no advantage to using modern causal inference methods over classical multivariable modeling. However, this statement is not always true. Most important, both effect modification and collapsibility are critical concepts when assessing the validity of using regression for causal effect estimation.Suppose that one is interested in the effect of combined radiotherapy and chemotherapy versus chemotherapy only on one-year mortality among patients diagnosed with colorectal cancer. A clinician may ask: how different would the risk of death have been had everyone received dual therapy as compared with if everyone had experienced monotherapy? The causal marginal odds ratio (MOR) offers an answer to this question. Each individual has a pair of potential outcomes: the outcome he or she would have experienced had he or she been exposed to dual treatment (A = 1), denoted Y(1), and the outcome had he or she been unexposed, Y(0). The MOR is defined as[P(Y(1) = 1)/(1 - P(Y(1) = 1))]/[P(Y(0) = 1)/(1 - P(Y(0) = 1))].A common approach would be to use logistic regression to model the odds of mortality given the intervention and adjust for confounders (W) such as clinical stage and comorbidities. Note that this regression will provide an estimate of the conditional odds ratio (COR), which is[P(Y = 1 A = 1,W) / (1 - P(Y = 1 A = 1,W))] / [P(Y = 1 A = 0,W) / (1 - P(Y = 1 A = 0,W))]. The MOR and COR are typically not identical. First, if there is effect modification (e.g., if the effect of dual therapy is different between patients with no comorbidities and those who have hypertension), logistic regression including an interaction term will not provide a marginal effect estimate but only the conditional effect of the interaction term between dual therapy and hypertension. Second, the odds ratio is noncollapsible, which means that the MOR is not necessarily equal to the stratum-specific odds ratio (i.e., the COR). This holds even when a covariate is related to the outcome but not the intervention and is thus not a confounder.Extended note: Monte Carlo simulations and code supporting the letter can be found at https://github.com/migariane/hetmor}}
@article{Luque-Fernandez2018a,
doi = {10.1093/aje/kwx317},
url = {https://pubmed.ncbi.nlm.nih.gov/29020131/},
file = {::},
issn = {14766256},
pmid = {29020131},
year = {2018},
month = {apr},
pages = {871--878},
title = {{Data-Adaptive Estimation for Double-Robust Methods in Population-Based Cancer Epidemiology: Risk Differences for Lung Cancer Mortality by Emergency Presentation}},
author = {Luque-Fernandez, Miguel Angel and Belot, Aur{\'{e}}lien and Valeri, Linda and Cerulli, Giovanni and Maringe, Camille and Rachet, Bernard},
number = {4},
volume = {187},
journal = {American Journal of Epidemiology},
abstract = {In this paper, we propose a structural framework for population-based cancer epidemiology and evaluate the performance of double-robust estimators for a binary exposure in cancer mortality. We conduct numerical analyses to study the bias and efficiency of these estimators. Furthermore, we compare 2 different model selection strategies based on 1) Akaike's Information Criterion and the Bayesian Information Criterion and 2) machine learning algorithms, and we illustrate double-robust estimators' performance in a real-world setting. In simulations with correctly specified models and near-positivity violations, all but the naive estimators had relatively good performance. However, the augmented inverse-probability-of-treatment weighting estimator showed the largest relative bias. Under dual model misspecification and near-positivity violations, all double-robust estimators were biased. Nevertheless, the targeted maximum likelihood estimator showed the best bias-variance trade-off, more precise estimates, and appropriate 95% confidence interval coverage, supporting the use of the data-adaptive model selection strategies based on machine learning algorithms. We applied these methods to estimate adjusted 1-year mortality risk differences in 183,426 lung cancer patients diagnosed after admittance to an emergency department versus persons with a nonemergency cancer diagnosis in England (2006-2013). The adjusted mortality risk (for patients diagnosed with lung cancer after admittance to an emergency department) was 16% higher in men and 18% higher in women, suggesting the importance of interventions targeting early detection of lung cancer signs and symptoms.},
keywords = {cancer epidemiology,causality,machine learning,population-based data,statistics,targeted maximum likelihood estimation},
publisher = {Oxford University Press}}
@article{Levy2018a,
issn = {23318422},
year = {2018},
title = {{An Easy Implementation of CV-TMLE}},
author = {Levy, Jonathan},
eprint = {1811.04573},
arxivId = {1811.04573},
journal = {arXiv},
abstract = {In the world of targeted learning, cross-validated targeted maximum likelihood estimators, CV-TMLE (Zheng and van der Laan 2010), has a distinct advantage over TMLE (van der Laan and Rubin 2006) in that one less condition is required of CV-TMLE in order to achieve asymptotic efficiency in the nonparametric or semiparametric settings. CV-TMLE as originally formulated, consists of averaging usually 10 (for 10-fold cross-validation) parameter estimates, each of which is performed on a validation set separate from where the initial fit was trained. The targeting step is usually performed as a pooled regression over all validation folds but in each fold, we separately evaluate any means as well as the parameter estimate. One nice thing about CV-TMLE, is that we average 10 plug-in estimates so the plug-in quality of preserving the natural parameter bounds is respected. Our adjustment of this procedure also preserves the plug-in characteristic as well as avoids the donsker condtion. The advantage of our procedure is the implementation of the targeting is identical to that of a regular TMLE, once all the validation set initial predictions have been formed. In short, we stack the validation set predictions and pretend as if we have a regular TMLE, which is not necessarily quite a plug-in estimator on each fold but overall will perform asymptotically the same and might have some slight advantage, a subject for future research. In the case of average treatment effect, treatment specific mean and mean outcome under a stochastic intervention, the procedure overlaps exactly with the originally formulated CV-TMLE with a pooled regression for the targeting.},
archivePrefix = {arXiv}}
@article{Austin2009BalanceSamples_4b17,
doi = {10.1002/sim.3697},
url = {/pmc/articles/PMC3472075/ /pmc/articles/PMC3472075/?report=abstract https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3472075/},
issn = {02776715},
pmid = {19757444},
year = {2009},
pages = {3083--3107},
title = {{Balance diagnostics for comparing the distribution of baseline covariates between treatment groups in propensity-score matched samples}},
author = {Austin, Peter C},
number = {25},
volume = {28},
journal = {Statistics in Medicine},
keywords = {Balance,Bias,Goodness-of-fit,Matching,Observational study,Propensity score,Propensity-score matching,Standardized difference},
publisher = {Wiley-Blackwell}}
@book{Vaart1998_8d8c,
url = {http://www.loc.gov/catdir/toc/cam024/98015176.html},
isbn = {0521496039 (hardcover)},
year = {1998},
title = {{Asymptotic statistics}},
author = {van der Vaart, A W},
address = {Cambridge, UK},
publisher = {Cambridge University Press}}
@article{Zivich2020_25b3,
url = {http://arxiv.org/abs/2004.10337},
year = {2020},
title = {{Machine learning for causal inference: on the use of cross-fit estimators}},
author = {Zivich, Paul N and Breskin, Alexander},
eprint = {2004.10337},
arxivId = {2004.10337},
journal = {arXiv},
archivePrefix = {arXiv}}
@book{Herberg1962_afba,
year = {1962},
title = {{Elementary mathematical analysis}},
annote = {LDR 00693cam 2200217u 4500
001 7501732
005 20070605181558.0
008 820522s1962 maua 000 0 eng
906 $a0$bcbc$cpremunv$du$encip$f19$gy-gencatlg
035 $9(DLC) 62008029
010 $a 62008029
040 $aDLC$cCarP$dDLC
050 00 $aQA39$b.H44 1962
100 1 $aHerberg, Theodore,$d1904- [from old catalog]
245 00 $aElementary mathematical analysis
260 $aBoston,$bHeath$c[c1962]
300 $a414 p.$billus.$c24 cm.
650 0 $aMathematics.
700 1 $aBristol, James D., [from old catalog]$ejoint author.
740 $aMathematical analysis.
991 $bc-GenColl$hQA39$i.H44 1962$tCopy 1$wPREM},
author = {Herberg, Theodore and Bristol, James D},
address = {Boston},
publisher = {Heath}}
@article{Robins1994_e0c2,
url = {http://www.jstor.org/stable/2290910},
year = {1994},
pages = {846--866},
title = {{Estimation of Regression Coefficients When Some Regressors Are Not Always Observed}},
author = {Robins, James M and Rotnitzky, Andrea and Zhao, Lue Ping},
number = {427},
volume = {89},
journal = {Journal of the American Statistical Association},
abstract = {In applied problems it is common to specify a model for the conditional mean of a response given a set of regressors. A subset of the regressors may be missing for some study subjects either by design or happenstance. In this article we propose a new class of semiparametric estimators, based on inverse probability weighted estimating equations, that are consistent for parameter vector $\alpha$0 of the conditional mean model when the data are missing at random in the sense of Rubin and the missingness probabilities are either known or can be parametrically modeled. We show that the asymptotic variance of the optimal estimator in our class attains the semiparametric variance bound for the model by first showing that our estimation problem is a special case of the general problem of parameter estimation in an arbitrary semiparametric model in which the data are missing at random and the probability of observing complete data is bounded away from 0, and then deriving a representation for the efficient score, the semiparametric variance bound, and the influence function of any regular, asymptotically linear estimator in this more general estimation problem. Because the optimal estimator depends on the unknown probability law generating the data, we propose locally and globally adaptive semiparametric efficient estimators. We compare estimators in our class with previously proposed estimators. We show that each previous estimator is asymptotically equivalent to some, usually inefficient, estimator in our class. This equivalence is a consequence of a proposition stating that every regular asymptotic linear estimator of $\alpha$0 is asymptotically equivalent to some estimator in our class. We compare various estimators in a small simulation study and offer some practical recommendations.},
publisher = {[American Statistical Association, Taylor & Francis, Ltd.]}}
@misc{Ridgeway2013_5e9b,
year = {2013},
title = {{twang: Toolkit for Weighting and Analysis of Nonequivalent Groups. R package version 1.3-20}},
author = {Ridgeway, G and McCaffrey, D and Morral, A and Griffin, B A and Burgette, L}}
@article{Bang2005_c3b6,
year = {2005},
pages = {962--973},
title = {{Doubly robust estimation in missing data and causal inference models}},
author = {Bang, Heejung and Robins, James M},
number = {4},
volume = {61},
journal = {Biometrics},
publisher = {Wiley Online Library}}
@article{Keil2014_2b2b,
doi = {10.1097/EDE.0000000000000160},
issn = {15315487},
pmid = {25140837},
year = {2014},
title = {{The parametric g-formula for time-to-event data: Intuition and a worked example}},
author = {Keil, Alexander P. and Edwards, Jessie K. and Richardson, David B. and Naimi, Ashley I. and Cole, Stephen R.},
journal = {Epidemiology},
abstract = {Background: The parametric g-formula can be used to estimate the effect of a policy, intervention, or treatment. Unlike standard regression approaches, the parametric g-formula can be used to adjust for time-varying confounders that are affected by prior exposures. To date, there are few published examples in which the method has been applied. Methods: We provide a simple introduction to the parametric g-formula and illustrate its application in an analysis of a small cohort study of bone marrow transplant patients in which the effect of treatment on mortality is subject to time-varying confounding. Results: Standard regression adjustment yields a biased estimate of the effect of treatment on mortality relative to the estimate obtained by the g-formula. Conclusions: The g-formula allows estimation of a relevant parameter for public health officials: the change in the hazard of mortality under a hypothetical intervention, such as reduction of exposure to a harmful agent or introduction of a beneficial new treatment. We present a simple approach to implement the parametric g-formula that is sufficiently general to allow easy adaptation to many settings of public health relevance.}}
@misc{Cole2008a,
doi = {10.1093/aje/kwn164},
url = {https://academic.oup.com/aje/article/168/6/656/88658},
file = {::},
issn = {00029262},
pmid = {18682488},
year = {2008},
month = {sep},
pages = {656--664},
title = {{Constructing inverse probability weights for marginal structural models}},
author = {Cole, Stephen R. and Hern{\'{a}}n, Miguel A.},
number = {6},
volume = {168},
abstract = {The method of inverse probability weighting (henceforth, weighting) can be used to adjust for measured confounding and selection bias under the four assumptions of consistency, exchangeability, positivity, and no misspecification of the model used to estimate weights. In recent years, several published estimates of the effect of time-varying exposures have been based on weighted estimation of the parameters of marginal structural models because, unlike standard statistical methods, weighting can appropriately adjust for measured time-varying confounders affected by prior exposure. As an example, the authors describe the last three assumptions using the change in viral load due to initiation of antiretroviral therapy among 918 human immunodeficiency virus-infected US men and women followed for a median of 5.8 years between 1996 and 2005. The authors describe possible tradeoffs that an epidemiologist may encounter when attempting to make inferences. For instance, a tradeoff between bias and precision is illustrated as a function of the extent to which confounding is controlled. Weight truncation is presented as an informal and easily implemented method to deal with these tradeoffs. Inverse probability weighting provides a powerful methodological tool that may uncover causal effects of exposures that are otherwise obscured. However, as with all methods, diagnostics and sensitivity analyses are essential for proper use. {\textcopyright} The Author 2008. Published by the Johns Hopkins Bloomberg School of Public Health. All rights reserved.},
keywords = {Bias (epidemiology),Causality,Confounding factors (epidemiology),Probability weighting,Regression model},
booktitle = {American Journal of Epidemiology},
publisher = {Oxford Academic}}
@book{Tsiatis2006,
doi = {10.1007/0-387-37345-4},
year = {2006},
title = {{Semiparametric Theory and Missing Data}},
author = {Tsiatis, Anastasios A},
abstract = {* A more theoretical book on the same subject as the book on statistical learning by Hastie/Tibshirani/Friedman},
keywords = {Mathematical Physics and Mathematics},
booktitle = {Semiparametric Theory and Missing Data},
publisher = {Springer Science and Business Media LLC}}
@misc{Kennedy2016_5390,
year = {2016},
pages = {141--167},
title = {{Semiparametric theory and empirical processes in causal inference}},
author = {Kennedy, Edward H},
booktitle = {Statistical Causal Inferences and Their Applications in Public Health Research},
publisher = {Springer}}
@article{Sturmer2010TreatmentStudyb_c788,
doi = {10.1093/aje/kwq198},
url = {/pmc/articles/PMC3025652/ /pmc/articles/PMC3025652/?report=abstract https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3025652/},
issn = {14766256},
pmid = {20716704},
year = {2010},
pages = {843--854},
title = {{Treatment effects in the presence of unmeasured confounding: Dealing with observations in the tails of the propensity score distribution-A simulation study}},
author = {St{\"{u}}rmer, Til and Rothman, Kenneth J and Avorn, Jerry and Glynn, Robert J},
number = {7},
volume = {172},
journal = {American Journal of Epidemiology},
keywords = {bias (epidemiology),causal inference,cohort studies,confounding factors (epidemiology),epidemiologic methods,models,propensity score,research design,statistical},
publisher = {Oxford University Press}}
@article{Zivich2019,
doi = {10.5281/ZENODO.3339870},
url = {https://zenodo.org/record/3339870},
year = {2019},
month = {jul},
title = {{pzivich/Python-for-Epidemiologists: Updates for v0.8.0}},
author = {Zivich, Paul}}
@article{Fisher2018_bd6b,
year = {2018},
title = {{Visually communicating and teaching intuition for influence functions}},
author = {Fisher, Aaron and Kennedy, Edward H},
journal = {arXiv preprint arXiv:1810.03260}}
@article{Efron1983_707f,
year = {1983},
pages = {36--48},
title = {{A leisurely look at the bootstrap, the jackknife, and cross-validation}},
author = {Efron, Bradley and Gong, Gail},
number = {1},
volume = {37},
journal = {The American Statistician},
publisher = {Taylor & Francis}}
@article{Hampel1974_89d3,
year = {1974},
pages = {383--393},
title = {{The influence curve and its role in robust estimation}},
author = {Hampel, Frank R},
number = {346},
volume = {69},
journal = {Journal of the American Statistical Association},
publisher = {Taylor & Francis}}
@article{MA2021,
doi = {10.1093/IJE/DYAA260},
url = {https://pubmed.ncbi.nlm.nih.gov/33351919/},
file = {::},
issn = {1464-3685},
pmid = {33351919},
year = {2021},
month = {feb},
pages = {346--351},
title = {{Reflection on modern methods: demystifying robust standard errors for epidemiologists}},
author = {MA, Mansournia and M, Nazemipour and AI, Naimi and GS, Collins and MJ, Campbell},
number = {1},
volume = {50},
journal = {International journal of epidemiology},
abstract = {All statistical estimates from data have uncertainty due to sampling variability. A standard error is one measure of uncertainty of a sample estimate (such as the mean of a set of observations or a regression coefficient). Standard errors are usually calculated based on assumptions underpinning the statistical model used in the estimation. However, there are situations in which some assumptions of the statistical model including the variance or covariance of the outcome across observations are violated, which leads to biased standard errors. One simple remedy is to use robust standard errors, which are robust to violations of certain assumptions of the statistical model. Robust standard errors are frequently used in clinical papers (e.g. to account for clustering of observations), although the underlying concepts behind robust standard errors and when to use them are often not well understood. In this paper, we demystify robust standard errors using several worked examples in simple situations in which model assumptions involving the variance or covariance of the outcome are misspecified. These are: (i) when the observed variances are different, (ii) when the variance specified in the model is wrong and (iii) when the assumption of independence is wrong.},
keywords = {Cluster Analysis,Epidemiologists*,Humans,MEDLINE,Maryam Nazemipour,Michael J Campbell,Models,Mohammad Ali Mansournia,NCBI,NIH,NLM,National Center for Biotechnology Information,National Institutes of Health,National Library of Medicine,PubMed Abstract,Statistical*,Uncertainty,doi:10.1093/ije/dyaa260,pmid:33351919},
publisher = {Int J Epidemiol}}
@book{Agresti2010_0640,
isbn = {9780470082898 (cloth)},
year = {2010},
title = {{Analysis of ordinal categorical data}},
author = {Agresti, Alan},
address = {Hoboken, N.J.},
publisher = {Wiley}}
@article{Gruber2009,
url = {https://biostats.bepress.com/ucbbiostat/paper252},
year = {2009},
month = {aug},
title = {{Targeted Maximum Likelihood Estimation: A Gentle Introduction}},
author = {Gruber, Susan and van der Laan, Mark},
journal = {U.C. Berkeley Division of Biostatistics Working Paper Series}}
@article{MA2021ReflectionEpidemiologists_c979,
doi = {10.1093/IJE/DYAA260},
url = {https://pubmed.ncbi.nlm.nih.gov/33351919/},
issn = {1464-3685},
pmid = {33351919},
year = {2021},
pages = {346--351},
title = {{Reflection on modern methods: demystifying robust standard errors for epidemiologists}},
author = {MA, Mansournia and M, Nazemipour and AI, Naimi and GS, Collins and MJ, Campbell},
number = {1},
volume = {50},
journal = {International journal of epidemiology},
keywords = {Cluster Analysis,Epidemiologists*,Humans,MEDLINE,Maryam Nazemipour,Michael J Campbell,Models,Mohammad Ali Mansournia,NCBI,NIH,NLM,National Center for Biotechnology Information,National Institutes of Health,National Library of Medicine,PubMed Abstract,Statistical*,Uncertainty,doi:10.1093/ije/dyaa260,pmid:33351919},
publisher = {Int J Epidemiol}}
@article{Gill1989,
url = {https://www.jstor.org/stable/4616127?seq=1},
year = {1989},
pages = {97--128},
title = {{Non- and Semi-Parametric Maximum Likelihood Estimators and the Von Mises Method (Part 1)}},
author = {Gill, Richard D},
number = {2},
volume = {16},
journal = {Scandinavian Journal of Statistics}}
@misc{R2020_969d,
url = {http://www.r-project.org/},
year = {2020},
title = {{R: A Language and Environment for Statistical Computing}},
annote = {{ISBN} 3-900051-07-0},
author = {{R Core Team}},
address = {Vienna, Austria},
institution = {R Foundation for Statistical Computing}}
@article{Sturmer2010a,
doi = {10.1093/aje/kwq198},
url = {https://pubmed.ncbi.nlm.nih.gov/20716704/},
file = {::},
issn = {14766256},
pmid = {20716704},
year = {2010},
month = {oct},
pages = {843--854},
title = {{Treatment effects in the presence of unmeasured confounding: Dealing with observations in the tails of the propensity score distribution-A simulation study}},
author = {St{\"{u}}rmer, Til and Rothman, Kenneth J. and Avorn, Jerry and Glynn, Robert J.},
number = {7},
volume = {172},
journal = {American Journal of Epidemiology},
abstract = {Frailty, a poorly measured confounder in older patients, can promote treatment in some situations and discourage it in others. This can create unmeasured confounding and lead to nonuniform treatment effects over the propensity score (PS). The authors compared bias and mean squared error for various PS implementations under PS trimming, thereby excluding persons treated contrary to prediction. Cohort studies were simulated with a binary treatment T as a function of 8 covariates X. Two of the covariates were assumed to be unmeasured strong risk factors for the outcome and present in persons treated contrary to prediction. The outcome Y was simulated as a Poisson function of T and all X's. In analyses based on measured covariates only, the range of PS's was trimmed asymmetrically according to the percentile of PS in treated patients at the lower end and in untreated patients at the upper end. PS trimming reduced bias due to unmeasured confounders and mean squared error in most scenarios assessed. Treatment effect estimates based on PS range restrictions do not correspond to a causal parameter but may be less biased by such unmeasured confounding. Increasing validity based on PS trimming may be a unique advantage of PS's over conventional outcome models. {\textcopyright} 2010 The Author.},
keywords = {bias (epidemiology),causal inference,cohort studies,confounding factors (epidemiology),epidemiologic methods,models,propensity score,research design,statistical},
publisher = {Oxford University Press}}
@article{Oehlert1992_2f94,
doi = {10.1080/00031305.1992.10475842},
issn = {15372731},
year = {1992},
pages = {27--29},
title = {{A note on the delta method}},
author = {Oehlert, Gary W.},
number = {1},
volume = {46},
journal = {American Statistician},
abstract = {The delta method is an intuitive technique for approximating the moments of functions of random variables. This note reviews the delta method and conditions under which delta-method approximate moments are accurate. {\textcopyright} 1992 American Statistical Association.},
keywords = {Approximate moments,Asymptotic approximation,Taylor series}}
@article{Brenner1997,
doi = {10.1097/00001648-199707000-00014},
url = {https://www.jstor.org/stable/3702586},
issn = {10443983},
pmid = {9209859},
year = {1997},
pages = {429--434},
title = {{Controlling for continuous confounders in epidemiologic research}},
author = {Brenner, Hermann and Blettner, Maria},
number = {4},
volume = {8},
journal = {Epidemiology},
abstract = {Multiple regression models are commonly used to control for confounding in epidemiologic research. Parametric regression models, such as multiple logistic regression, are powerful tools to control for multiple covariates provided that the covariate risk associations are correctly specified. Residual confounding may result, however, from inappropriate specification of the confounder-risk association. In this paper, we illustrate the order of magnitude of residual confounding that may occur with traditional approaches to control for continuous confounders in multiple logistic regression, such as inclusion of a single linear term or categorization of the confounder, under a variety of assumptions on the confounder-risk association. We show that inclusion of the confounder as a single linear term often provides satisfactory control for confounding even in situations in which the model assumptions are clearly violated. In contrast, categorization of the confounder may often lead to serious residual confounding if the number of categories is small. Alternative strategies to control for confounding, such as polynomial regression or linear spline regression, are a useful supplement to the more traditional approaches.},
keywords = {Biostatistics,Confounding,Epidemiologic methods,Logistic regression}}
@article{Chernozhukov2018c,
doi = {10.1111/ECTJ.12097},
url = {https://academic.oup.com/ectj/article/21/1/C1/5056401},
file = {::},
issn = {1368-4221},
year = {2018},
month = {feb},
pages = {C1--C68},
title = {{Double/debiased machine learning for treatment and structural parameters}},
author = {Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Duflo, Esther and Hansen, Christian and Newey, Whitney and Robins, James},
number = {1},
volume = {21},
journal = {The Econometrics Journal},
abstract = {We revisit the classic semi-parametric problem of inference on a low-dimensional parameter $\theta$0 in the presence of high-dimensional nuisance parameters $\eta$0. We depart from the classical setting by allowing for $\eta$0 to be so high-dimensional that the traditional assumptions (e.g. Donsker properties) that limit complexity of the parameter space for this object break down. To estimate $\eta$0, we consider the use of statistical or machine learning (ML) methods, which are particularly well suited to estimation in modern, very high-dimensional cases. ML methods perform well by employing regularization to reduce variance and trading off regularization bias with overfitting in practice. However, both regularization bias and overfitting in estimating $\eta$0 cause a heavy bias in estimators of $\theta$0 that are obtained by naively plugging ML estimators of $\eta$0 into estimating equations for $\theta$0. This bias results in the naive estimator failing to be N-1/2 consistent, where N is the sample size. We show that the impact of regularization bias and overfitting on estimation of the parameter of interest $\theta$0 can be removed by using two simple, yet critical, ingredients: (1) using Neyman-orthogonal moments/scores that have reduced sensitivity with respect to nuisance parameters to estimate $\theta$0; (2) making use of cross-fitting, which provides an efficient form of data-splitting. We call the resulting set of methods double or debiased ML (DML). We verify that DML delivers point estimators that concentrate in an N-1 -neighbourhood of the true parameter values and are approximately unbiased and normally distributed, which allows construction of valid confidence statements. The generic statistical theory of DML is elementary and simultaneously relies on only weak theoretical requirements, which will admit the use of a broad array of modern ML methods for estimating the nuisance parameters, such as random forests, lasso, ridge, deep neural nets, boosted trees, and various hybrids and ensembles of these methods. We illustrate the general theory by applying it to provide theoretical properties of the following: DML applied to learn the main regression parameter in a partially linear regression model; DML applied to learn the coefficient on an endogenous variable in a partially linear instrumental variables model; DML applied to learn the average treatment effect and the average treatment effect on the treated under unconfoundedness; DML applied to learn the local average treatment effect in an instrumental variables setting. In addition to these theoretical applications, we also illustrate the use of DML in three empirical examples.},
publisher = {Oxford Academic}}
@article{Polley2010_c8c5,
url = {https://biostats.bepress.com/ucbbiostat/paper266},
year = {2010},
month = {may},
title = {{Super Learner In Prediction}},
author = {Polley, Eric and van der Laan, Mark},
journal = {U.C. Berkeley Division of Biostatistics Working Paper Series}}
@article{Lunceford2004_4926,
url = {http://dx.doi.org/10.1002/sim.1903},
year = {2004},
pages = {2937--2960},
title = {{Stratification and weighting via the propensity score in estimation of causal treatment effects: a comparative study}},
author = {Lunceford, Jared K and Davidian, Marie},
number = {19},
volume = {23},
journal = {Statistics in Medicine},
publisher = {John Wiley & Sons, Ltd.}}
@article{Schuler2017TargetedStudies_0f59,
doi = {10.1093/aje/kww165},
url = {https://academic.oup.com/aje/article/185/1/65/2662306},
issn = {14766256},
pmid = {27941068},
year = {2017},
pages = {65--73},
title = {{Targeted maximum likelihood estimation for causal inference in observational studies}},
author = {Schuler, Megan S and Rose, Sherri},
number = {1},
volume = {185},
journal = {American Journal of Epidemiology},
keywords = {Causal inference,Machine learning,Observational studies,Super learner,Targeted maximum likelihood estimation},
publisher = {Oxford University Press}}
@book{Armitage2005_1fc4,
url = {http://www.loc.gov/catdir/toc/ecip054/2004028292.html},
isbn = {047084907X (set : cloth)},
year = {2005},
title = {{Encyclopedia of biostatistics}},
author = {Armitage, P and Colton, Theodore},
address = {Chichester, West Sussex, England},
publisher = {John Wiley}}
@article{DorfmanTheRevisited_bd7a,
title = {{The l-l:ijek Estimator Revisited}},
author = {Dorfman, Alan H and Valliant, Richard and Bureau, U S},
keywords = {Horvitz-Thompson estimator,balanced sample,best linear unbiased predictor,ratio estimator,robustness,superpopulation model}}
@article{Gutman2015_4ac7,
year = {2015},
month = {nov},
pages = {3381--3398},
title = {{Estimation of causal effects of binary treatments in unconfounded studies}},
author = {Gutman, Roee and Rubin, Donald B},
number = {26},
volume = {34},
journal = {Stat Med},
abstract = {Estimation of causal effects in non-randomized studies comprises two distinct phases: design, without outcome data, and analysis of the outcome data according to a specified protocol. Recently, Gutman and Rubin (2013) proposed a new analysis-phase method for estimating treatment effects when the outcome is binary and there is only one covariate, which viewed causal effect estimation explicitly as a missing data problem. Here, we extend this method to situations with continuous outcomes and multiple covariates and compare it with other commonly used methods (such as matching, subclassification, weighting, and covariance adjustment). We show, using an extensive simulation, that of all methods considered, and in many of the experimental conditions examined, our new 'multiple-imputation using two subclassification splines' method appears to be the most efficient and has coverage levels that are closest to nominal. In addition, it can estimate finite population average causal effects as well as non-linear causal estimands. This type of analysis also allows the identification of subgroups of units for which the effect appears to be especially beneficial or harmful.},
keywords = {Rubin causal model,causal inference,multiple imputation,propensity score,spline,subgroup analysis}}
@incollection{Daniel2018a,
doi = {10.1002/9781118445112.stat08068},
url = {https://onlinelibrary.wiley.com/doi/full/10.1002/9781118445112.stat08068 https://onlinelibrary.wiley.com/doi/abs/10.1002/9781118445112.stat08068 https://onlinelibrary.wiley.com/doi/10.1002/9781118445112.stat08068},
year = {2018},
month = {aug},
pages = {1--14},
title = {{Double Robustness}},
author = {Daniel, Rhian M.},
abstract = {Double robustness is a prevalent topic in current statistical thinking, especially in causal inference and missing data methods. The most popular class of doubly robust (DR) estimators—also known as locally efficient augmented inverse probability weighted (AIPW) estimators—possess additional properties, linked to but distinct from double robustness, which lead to tractable statistical inferences and other attractive features.},
keywords = {adaptive estimation,causal inference,convergence,data,inverse probability weighting,local efficiency,missing data,nuisance functionals,outcome regression},
booktitle = {Wiley StatsRef: Statistics Reference Online},
publisher = {Wiley}}
@article{Robins2000b,
doi = {10.1097/00001648-200009000-00011},
url = {http://europepmc.org/article/med/10955408},
issn = {10443983},
pmid = {10955408},
year = {2000},
month = {sep},
pages = {550--560},
title = {{Marginal structural models and causal inference in epidemiology}},
author = {Robins, James M. and Hern{\'{a}}n, Miguel {\'{A}}ngel and Brumback, Babette},
number = {5},
volume = {11},
journal = {Epidemiology},
abstract = {In observational studies with exposures or treatments that vary over time, standard approaches for adjustment of confounding are biased when there exist time-dependent confounders that are also affected by previous treatment. This paper introduces marginal structural models, a new class of causal models that allow for improved adjustment of confounding in those situations. The parameters of a marginal structural model can be consistently estimated using a new class of estimators, the inverse-probability-of-treatment weighted estimators.},
keywords = {Causality,Confounding,Counterfactuals,Epidemiologic methods,Intermediate variables,Longitudinal data,Structural models}}
@article{zbMATH03224097,
issn = {0528-2195},
year = {1959},
pages = {387--423},
title = {{Optimum strategy and other problems in probability sampling}},
author = {Hajek, J},
volume = {84},
journal = {{\v{C}}as. P{\v{e}}stov{\'{a}}n\'{\i} Mat.}}
@book{Boos2013_09ac,
isbn = {9781461448174 (hdbk.)},
year = {2013},
title = {{Essential statistical inference: theory and methods}},
author = {Boos, Dennis D and Stefanski, L A},
abstract = {"This book is for students and researchers who have had a first year graduate level mathematical statistics course. It covers classical likelihood, Bayesian, and permutation inference; an introduction to basic asymptotic distribution theory; and modern topics like M-estimation, the jackknife, and the bootstrap. R code is woven throughout the text, and there are a large number of examples and problems. An important goal has been to make the topics accessible to a wide audience, with little overt reliance on measure theory"},
publisher = {Springer}}
@article{Goetghebeur2020FormulatingAnswers_5daa,
doi = {10.1002/sim.8741},
url = {www.ofcaus.org},
issn = {10970258},
pmid = {32964526},
year = {2020},
pages = {4922--4948},
title = {{Formulating causal questions and principled statistical answers}},
author = {Goetghebeur, Els and le Cessie, Saskia and {De Stavola}, Bianca and Moodie, Erica E M and Waernbaum, Ingeborg},
eprint = {1906.12100},
number = {30},
volume = {39},
arxivId = {1906.12100},
journal = {Statistics in Medicine},
keywords = {causation,instrumental variable,inverse probability weighting,matching,potential outcomes,propensity score},
publisher = {John Wiley and Sons Ltd},
archivePrefix = {arXiv}}
@article{Breiman1996_55bd,
year = {1996},
pages = {49--64},
title = {{Stacked regressions}},
author = {Breiman, Leo},
number = {1},
volume = {24},
journal = {Machine learning},
publisher = {Springer}}
@misc{Cole2008_f276,
doi = {10.1093/aje/kwn164},
url = {https://academic.oup.com/aje/article/168/6/656/88658},
file = {::},
issn = {00029262},
pmid = {18682488},
year = {2008},
month = {sep},
pages = {656--664},
title = {{Constructing inverse probability weights for marginal structural models}},
author = {Cole, Stephen R. and Hern{\'{a}}n, Miguel A.},
number = {6},
volume = {168},
abstract = {The method of inverse probability weighting (henceforth, weighting) can be used to adjust for measured confounding and selection bias under the four assumptions of consistency, exchangeability, positivity, and no misspecification of the model used to estimate weights. In recent years, several published estimates of the effect of time-varying exposures have been based on weighted estimation of the parameters of marginal structural models because, unlike standard statistical methods, weighting can appropriately adjust for measured time-varying confounders affected by prior exposure. As an example, the authors describe the last three assumptions using the change in viral load due to initiation of antiretroviral therapy among 918 human immunodeficiency virus-infected US men and women followed for a median of 5.8 years between 1996 and 2005. The authors describe possible tradeoffs that an epidemiologist may encounter when attempting to make inferences. For instance, a tradeoff between bias and precision is illustrated as a function of the extent to which confounding is controlled. Weight truncation is presented as an informal and easily implemented method to deal with these tradeoffs. Inverse probability weighting provides a powerful methodological tool that may uncover causal effects of exposures that are otherwise obscured. However, as with all methods, diagnostics and sensitivity analyses are essential for proper use. {\textcopyright} The Author 2008. Published by the Johns Hopkins Bloomberg School of Public Health. All rights reserved.},
keywords = {Bias (epidemiology),Causality,Confounding factors (epidemiology),Probability weighting,Regression model},
booktitle = {American Journal of Epidemiology},
publisher = {Oxford Academic}}
@article{Neugebauer2005_901c,
year = {2005},
pages = {405--426},
title = {{Why prefer double robust estimators in causal inference?}},
author = {Neugebauer, Romain and van der Laan, Mark},
number = {1},
volume = {129},
journal = {Journal of Statistical Planning and Inference},
publisher = {Elsevier}}
@article{Keil2019,
url = {https://arxiv.org/abs/1805.08058},
year = {2019},
title = {{Super learning in the SAS system}},
author = {Keil, Alexander P. and Westreich, Daniel and Edwards, Jessie K. and Cole, Stephen R.},
eprint = {1805.08058},
arxivId = {1805.08058},
journal = {arXiv},
archivePrefix = {arXiv}}
@misc{Cole2008ConstructingModels_526f,
doi = {10.1093/aje/kwn164},
url = {https://academic.oup.com/aje/article/168/6/656/88658},
issn = {00029262},
pmid = {18682488},
year = {2008},
pages = {656--664},
title = {{Constructing inverse probability weights for marginal structural models}},
author = {Cole, Stephen R and Hern{\'{a}}n, Miguel A},
number = {6},
volume = {168},
keywords = {Bias (epidemiology),Causality,Confounding factors (epidemiology),Probability weighting,Regression model},
booktitle = {American Journal of Epidemiology},
publisher = {Oxford Academic}}
@article{VanderLaan2006_aeb9,
year = {2006},
title = {{Targeted maximum likelihood learning}},
author = {van der Laan, Mark J and Rubin, Daniel},
number = {1},
volume = {2},
journal = {The International Journal of Biostatistics}}
@book{VanderLaan2011v2,
isbn = {9781441997814 (alk. paper)},
year = {2011},
title = {{Targeted learning: causal inference for observational and experimental data}},
author = {van der Laan, M J and Rose, Sherri},
address = {New York},
publisher = {Springer Series in Statistics}}
@misc{Luque-Fernandez2019,
url = {https://zenodo.org/record/2560828},
year = {2019},
title = {{migariane/meltmle: Ensemble Learning Targeted Maximum Likelihood Estimation for Stata users | Zenodo}},
author = {Luque-Fernandez, Miguel Angel},
urldate = {2020-11-01},
booktitle = {Zenodo}}
@article{Rubin2007_362c,
year = {2007},
month = {jan},
pages = {20--36},
title = {{The design versus the analysis of observational studies for causal effects: parallels with the design of randomized trials}},
author = {Rubin, Donald B},
number = {1},
volume = {26},
journal = {Stat Med},
abstract = {For estimating causal effects of treatments, randomized experiments are generally considered the gold standard. Nevertheless, they are often infeasible to conduct for a variety of reasons, such as ethical concerns, excessive expense, or timeliness. Consequently, much of our knowledge of causal effects must come from non-randomized observational studies. This article will advocate the position that observational studies can and should be designed to approximate randomized experiments as closely as possible. In particular, observational studies should be designed using only background information to create subgroups of similar treated and control units, where 'similar' here refers to their distributions of background variables. Of great importance, this activity should be conducted without any access to any outcome data, thereby assuring the objectivity of the design. In many situations, this objective creation of subgroups of similar treated and control units, which are balanced with respect to covariates, can be accomplished using propensity score methods. The theoretical perspective underlying this position will be presented followed by a particular application in the context of the US tobacco litigation. This application uses propensity score methods to create subgroups of treated units (male current smokers) and control units (male never smokers) who are at least as similar with respect to their distributions of observed background characteristics as if they had been randomized. The collection of these subgroups then 'approximate' a randomized block experiment with respect to the observed covariates.}}
@article{Mansournia2020_6c1f,
doi = {10.1093/ije/dyaa260},
url = {https://academic.oup.com/ije/advance-article/doi/10.1093/ije/dyaa260/6044447},
issn = {0300-5771},
year = {2020},
title = {{Reflections on modern methods: demystifying robust standard errors for epidemiologists}},
author = {Mansournia, Mohammad Ali and Nazemipour, Maryam and Naimi, Ashley I and Collins, Gary S and Campbell, Michael J},
journal = {International Journal of Epidemiology},
keywords = {Robust standard error,clustering,heteroscedasticity,model-based standard error},
publisher = {Oxford University Press (OUP)}}
@article{Webster-Clark2021,
doi = {10.1002/sim.8866},
url = {https://onlinelibrary.wiley.com/doi/full/10.1002/sim.8866 https://onlinelibrary.wiley.com/doi/abs/10.1002/sim.8866 https://onlinelibrary.wiley.com/doi/10.1002/sim.8866},
issn = {10970258},
pmid = {33377193},
year = {2021},
month = {mar},
pages = {1718--1735},
title = {{Using propensity scores to estimate effects of treatment initiation decisions: State of the science}},
author = {Webster-Clark, Michael and St{\"{u}}rmer, Til and Wang, Tiansheng and Man, Kenneth and Marinac-Dabic, Danica and Rothman, Kenneth J. and Ellis, Alan R. and Gokhale, Mugdha and Lunt, Mark and Girman, Cynthia and Glynn, Robert J.},
number = {7},
volume = {40},
journal = {Statistics in Medicine},
abstract = {Confounding can cause substantial bias in nonexperimental studies that aim to estimate causal effects. Propensity score methods allow researchers to reduce bias from measured confounding by summarizing the distributions of many measured confounders in a single score based on the probability of receiving treatment. This score can then be used to mitigate imbalances in the distributions of these measured confounders between those who received the treatment of interest and those in the comparator population, resulting in less biased treatment effect estimates. This methodology was formalized by Rosenbaum and Rubin in 1983 and, since then, has been used increasingly often across a wide variety of scientific disciplines. In this review article, we provide an overview of propensity scores in the context of real-world evidence generation with a focus on their use in the setting of single treatment decisions, that is, choosing between two therapeutic options. We describe five aspects of propensity score analysis: alignment with the potential outcomes framework, implications for study design, estimation procedures, implementation options, and reporting. We add context to these concepts by highlighting how the types of comparator used, the implementation method, and balance assessment techniques have changed over time. Finally, we discuss evolving applications of propensity scores.},
keywords = {comparative effectiveness research,propensity scores,real-world data,real-world evidence,review},
publisher = {John Wiley and Sons Ltd}}
@article{Kennedy2017_3cbc,
year = {2017},
pages = {1229--1245},
title = {{Non-parametric methods for doubly robust estimation of continuous treatment effects}},
author = {Kennedy, Edward H and Ma, Zongming and McHugh, Matthew D and Small, Dylan S},
number = {4},
volume = {79},
journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
publisher = {Wiley Online Library}}
@article{Dorfman,
file = {::},
title = {{The l-l:ijek Estimator Revisited}},
author = {Dorfman, Alan H and Valliant, Richard and Bureau, U S},
keywords = {Horvitz-Thompson estimator,balanced sample,best linear unbiased predictor,ratio estimator,robustness,superpopulation model}}
@article{VerHoef2012_950c,
url = {http://dx.doi.org/10.1080/00031305.2012.687494},
year = {2012},
month = {may},
pages = {124--127},
title = {{Who Invented the Delta Method?}},
author = {{Ver Hoef}, Jay M},
number = {2},
volume = {66},
journal = {The American Statistician},
publisher = {Informa UK Limited}}
@book{Rothman2008_c4e4,
url = {http://www.loc.gov/catdir/enhancements/fy0743/2007036316-d.html},
isbn = {9780781755641},
year = {2008},
title = {{Modern epidemiology}},
annote = {LDR 04418cam 22005054a 4500
001 14993679
005 20090306202840.0
008 070904s2008 pauab b 001 0 eng
906 $a7$bcbc$corignew$d1$eecip$f20$gy-gencatlg
925 0 $aacquire$b2 shelf copy$xpolicy default
955 $djb01 2007-09-05$ejb01 2007-09-05 to Dewey$aaa27 2007-09-05$axe07 2009-02-26 2 copies rec'd., to CIP ver.$axh00 2009-03-04 to USPL/STM$fxh14 2009-03-06 Z-CipVer$gxh14 2009-03-06 copy 1-2 to BCCD
010 $a 2007036316
015 $aGBA784175$2bnb
016 7 $a101315741$2DNLM
016 7 $a014100824$2Uk
020 $a9780781755641
020 $a0781755646
035 $a(OCoLC)169455558
042 $apcc
050 00 $aRA652.2.M3$bR67 2008
060 00 $a2008 E-277
060 10 $aWA 105$bR846m 2008
082 00 $a614.4$222
100 1 $aRothman, Kenneth J.
245 10 $aModern epidemiology /$cKenneth J. Rothman, Sander Greenland, Timothy L. Lash.
250 $a3rd ed., thoroughly rev. and updated.
260 $aPhiladelphia :$bWolters Kluwer Health/Lippincott Williams & Wilkins,$cc2008.
300 $ax, 758 p. :$bill., map ;$c27 cm.
500 $a2nd ed. edited by Kenneth J. Rothman and Sander Greenland.
504 $aIncludes bibliographical references (p. 683-732) and index.
505 0 $aIntroduction / Kenneth J. Rothman, Sander Greenland, and Timothy L. Lash -- Section I: Basic concepts -- Causation and causal inference / Kenneth J. Rothman ... [et al.] -- Measures of occurrence / Sander Greenland and Kenneth J. Rothman -- Measures of effect and measures of association / Sander Greenland, Kenneth J. Rothman, and Timothy L. Lash -- Concepts of interaction / Sander Greenland, Timothy L. Lash, and Kenneth J. Rothman --
505 0 $aSection II: Study design and conduct -- Types of epidemiologic studies / Kenneth J. Rothman, Sander Greenland, and Timothy L. Lash -- Cohort studies / Kenneth J. Rothman and Sander Greenland -- Case-control studies / Kenneth J. Rothman, Sander Greenland, and Timothy L. Lash -- Validity in epidemiologic studies / Kenneth J. Rothman, Sander Greenland, and Timothy L. Lash -- Precision and statistics in epidemiologic studies / Kenneth J. Rothman, Sander Greenland, and Timothy L. Lash -- Design strategies to improve study accuracy / Kenneth J. Rothman, Sander Greenland, and Timothy L. Lash -- Causal diagrams / M. Maria Glymour and Sander Greenland --
505 0 $aSection III: Data analysis -- Fundamentals of epidemiologic data analysis / Sander Greenland and Kenneth J. Rothman -- Introduction to categorical statistics / Sander Greenland and Kenneth J. Rothman -- Introduction to stratified analysis / Sander Greenland and Kenneth J. Rothman -- Applications of stratified analysis methods / Sander Greenland -- Analysis of polytomous exposures and outcomes / Sander Greenland -- Introduction to bayesian statistics / Sander Greenland -- Bias analysis / Sander Greenland and Timothy L. Lash -- Introduction to regression models / Sander Greenland -- Introduction to regression modeling / Sander Greenland --
505 0 $aSection IV: Special topics -- Surveillance / James W. Buehler -- Using secondary data / J{\o}rn Olsen -- Field methods in epidemiology / Patricia Hartge and Jack Cahill -- Ecologic studies / Hal Morgenstern -- Social epidemiology / Jay S. Kaufman -- Infectious disease epidemiology / C. Robert Horsburgh, Jr., and Barbara E. Mahon -- Genetic and molecular epidemiology / Muin J. Khoury, Robert Millikan, and Marta Gwinn -- Nutritional epidemiology / Walter C. Willett -- Environmental epidemiology / Irva Hertz-Picciotto -- Methodologic issues in reproductive epidemiology / Clarice R. Weinberg and Allen J. Wilcox -- Clinical epidemiology / Noel S. Weiss -- Meta-analysis / Sander Greenland and Keith O'Rourke.
650 0 $aEpidemiology$xStatistical methods.
650 0 $aEpidemiology$xResearch$xMethodology.
650 12 $aEpidemiology.
650 22 $aEpidemiologic Methods.
700 1 $aGreenland, Sander,$d1951-
700 1 $aLash, Timothy L.
856 42 $3Publisher description$uhttp://www.loc.gov/catdir/enhancements/fy0743/2007036316-d.html
856 41 $3Table of contents only$uhttp://www.loc.gov/catdir/enhancements/fy0828/2007036316-t.html
035 $a(OCoLC)ocn169455558
040 $aDNLM/DLC$cDLC$dNLM$dBAKER$dUKM$dC#P$dYDXCP$dBWX$dCOU$dMUQ$dBTCTA$dDLC
952 $aTo LC: Prev. ed. LCCN 9723369},
author = {Rothman, Kenneth J and Greenland, Sander and Lash, Timothy L},
address = {Philadelphia},
publisher = {Wolters Kluwer Health/Lippincott Williams & Wilkins}}
@article{Gruber2011_37e4,
year = {2011},
title = {{tmle: An R Package for Targeted Maximum Likelihood Estimation}},
author = {Gruber, Susan and van der Laan, Mark},
journal = {U.C. Berkeley Division of Biostatistics Working Paper Series}}
@incollection{Zheng2011,
doi = {10.1007/978-1-4419-9782-1_27},
year = {2011},
title = {{Cross-Validated Targeted Minimum-Loss-Based Estimation}},
author = {Zheng, Wenjing and van der Laan, Mark J.},
abstract = {In previous chapters, we introduced targeted maximum likelihood estimation in semiparametric models, which incorporates adaptive estimation (e.g., loss-based super learning) of the relevant part of the data-generating distribution and subsequently carries out a targeted bias reduction by maximizing the log-likelihood, or minimizing another loss-specific empirical risk, over a “clever” parametric working model through the initial estimator, treating the initial estimator as offset. This updating process may need to be iterated to convergence. The target parameter of the resulting updated estimator is then evaluated, and is called the targeted minimum-loss- based estimator (also TMLE) of the target parameter of the data-generating distribution. This estimator is, by definition, a substitution estimator, and, under regularity conditions, is a double robust semiparametric efficient estimator.}}
@article{Gruber2012Tmle:Estimation_aba8,
doi = {10.18637/jss.v051.i13},
url = {https://www.jstatsoft.org/index.php/jss/article/view/v051i13/v51i13.pdf https://www.jstatsoft.org/index.php/jss/article/view/v051i13},
issn = {15487660},
year = {2012},
pages = {1--35},
title = {{tmle: An R package for targeted maximum likelihood estimation}},
author = {Gruber, Susan and van der Laan, Mark J},
number = {13},
volume = {51},
journal = {Journal of Statistical Software},
keywords = {Causal inference,Controlled direct effect,MSM,R,TMLE,Targeted maximum likelihood estimation},
publisher = {American Statistical Association}}
@article{Luque-Fernandez2018Data-AdaptivePresentation_bd53,
doi = {10.1093/aje/kwx317},
url = {https://pubmed.ncbi.nlm.nih.gov/29020131/},
issn = {14766256},
pmid = {29020131},
year = {2018},
pages = {871--878},
title = {{Data-Adaptive Estimation for Double-Robust Methods in Population-Based Cancer Epidemiology: Risk Differences for Lung Cancer Mortality by Emergency Presentation}},
author = {Luque-Fernandez, Miguel Angel and Belot, Aur{\'{e}}lien and Valeri, Linda and Cerulli, Giovanni and Maringe, Camille and Rachet, Bernard},
number = {4},
volume = {187},
journal = {American Journal of Epidemiology},
keywords = {cancer epidemiology,causality,machine learning,population-based data,statistics,targeted maximum likelihood estimation},
publisher = {Oxford University Press}}
@article{Freedman2006_15c5,
url = {http://www.jstor.org/stable/27643806},
year = {2006},
pages = {299--302},
title = {{On the So-Called "Huber Sandwich Estimator" and "Robust Standard Errors"}},
author = {Freedman, David A},
number = {4},
volume = {60},
journal = {The American Statistician},
abstract = {The "Huber Sandwich Estimator" can be used to estimate the variance of the MLE when the underlying model is incorrect. If the model is nearly correct, so are the usual standard errors, and robustification is unlikely to help much. On the other hand, if the model is seriously in error, the sandwich may help on the variance side, but the parameters being estimated by the MLE are likely to be meaningless{\^{a}}€''except perhaps as descriptive statistics.},
publisher = {[American Statistical Association, Taylor & Francis, Ltd.]}}
@article{Kang2007_def0,
doi = {10.1214/07-STS227},
url = {https://projecteuclid.org/euclid.ss/1207580167 http://www.jstor.org/stable/27645858},
issn = {08834237},
year = {2007},
month = {nov},
pages = {523--539},
title = {{Demystifying Double Robustness: A Comparison of Alternative Strategies for Estimating a Population Mean from Incomplete Data}},
author = {Tsiatis, Anastasios A and Davidian, Marie and Kang, Joseph D.Y. Y and Schafer, Joseph L.},
number = {4},
volume = {22},
journal = {Statistical Science},
abstract = {When outcomes are missing for reasons beyond an investigator's control, there are two different ways to adjust a parameter estimate for covariates that may be related both to the outcome and to missingness. One approach is to model the relationships between the covariates and the outcome and use those relationships to predict the missing values. Another is to model the probabilities of missingness given the covariates and incorporate them into a weighted or stratified estimate. Doubly robust (DR) procedures apply both types of model simultaneously and produce a consistent estimate of the parameter if either of the two models has been correctly specified. In this article, we show that DR estimates can be constructed in many ways. We compare the performance of various DR and non-DR estimates of a population mean in a simulated example where both models are incorrect but neither is grossly misspecified. Methods that use inverse-probabilities as weights, whether they are DR or not, are sensitive to misspecification of the propensity model when some estimated propensities are small. Many DR methods perform better than simple inverse-probability weighting. None of the DR methods we tried, however, improved upon the performance of simple regression-based prediction of the missing values. This study does not represent every missing-data problem that will arise in practice. But it does demonstrate that, in at least some settings, two wrong models are not better than one.},
keywords = {Causal inference,Missing data,Model-assisted survey estimation,Propensity score,Weighted estimating equations},
publisher = {Institute of Mathematical Statistics}}
@article{Luque-Fernandez2018_d1d3,
doi = {10.1002/sim.7628},
url = {http://doi.wiley.com/10.1002/sim.7628},
file = {::},
issn = {02776715},
year = {2018},
month = {jul},
pages = {2530--2546},
title = {{Targeted maximum likelihood estimation for a binary treatment: A tutorial}},
author = {Luque-Fernandez, Miguel Angel and Schomaker, Michael and Rachet, Bernard and Schnitzer, Mireille E.},
number = {16},
volume = {37},
journal = {Statistics in Medicine},
abstract = {When estimating the average effect of a binary treatment (or exposure) on an outcome, methods that incorporate propensity scores, the G-formula, or targeted maximum likelihood estimation (TMLE) are preferred over na{\"{i}}ve regression approaches, which are biased under misspecification of a parametric outcome model. In contrast propensity score methods require the correct specification of an exposure model. Double-robust methods only require correct specification of either the outcome or the exposure model. Targeted maximum likelihood estimation is a semiparametric double-robust method that improves the chances of correct model specification by allowing for flexible estimation using (nonparametric) machine-learning methods. It therefore requires weaker assumptions than its competitors. We provide a step-by-step guided implementation of TMLE and illustrate it in a realistic scenario based on cancer epidemiology where assumptions about correct model specification and positivity (ie, when a study participant had 0 probability of receiving the treatment) are nearly violated. This article provides a concise and reproducible educational introduction to TMLE for a binary outcome and exposure. The reader should gain sufficient understanding of TMLE from this introductory tutorial to be able to apply the method in practice. Extensive R-code is provided in easy-to-read boxes throughout the article for replicability. Stata users will find a testing implementation of TMLE and additional material in the Appendix S1 and at the following GitHub repository: https://github.com/migariane/SIM-TMLE-tutorial.},
keywords = {causal inference,ensemble Learning,machine learning,observational studies,targeted maximum likelihood estimation},
publisher = {John Wiley and Sons Ltd}}
@misc{chernozhukov2018double,
year = {2018},
title = {Double/debiased machine learning for treatment and structural parameters},
author = {Chernozhukov, Victor and Chetverikov, Denis and Demirer, Mert and Duflo, Esther and Hansen, Christian and Newey, Whitney and Robins, James},
publisher = {Oxford University Press Oxford, UK}}
@article{kennedy2021semiparametric,
year = {2021},
title = {Semiparametric counterfactual density estimation},
author = {Kennedy, Edward H and Balakrishnan, Sivaraman and Wasserman, Larry},
journal = {arXiv preprint arXiv:2102.12034}}
@article{westling2023inference,
year = {2023},
pages = {1--26},
title = {Inference for treatment-specific survival curves using machine learning},
author = {Westling, Ted and Luedtke, Alex and Gilbert, Peter B and Carone, Marco},
number = {just-accepted},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis}}
@article{wen2023intervention,
year = {2023},
pages = {509--523},
title = {Intervention treatment distributions that depend on the observed treatment process and model double robustness in causal survival analysis},
author = {Wen, Lan and Marcus, Julia L and Young, Jessica G},
number = {3},
volume = {32},
journal = {Statistical Methods in Medical Research},
publisher = {SAGE Publications Sage UK: London, England}}
@article{vansteelandt2022assumption,
year = {2022},
pages = {1--10},
title = {Assumption-lean Cox regression},
author = {Vansteelandt, Stijn and Dukes, Oliver and Van Lancker, Kelly and Martinussen, Torben},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis}}
@article{bhattacharya2022semiparametric,
year = {2022},
pages = {13325--13400},
title = {Semiparametric inference for causal effects in graphical models with hidden variables},
author = {Bhattacharya, Rohit and Nabi, Razieh and Shpitser, Ilya},
number = {1},
volume = {23},
journal = {The Journal of Machine Learning Research},
publisher = {JMLRORG}}
@article{stotland2004risk,
year = {2004},
pages = {220--226},
title = {Risk factors and obstetric complications associated with macrosomia},
author = {Stotland, NE and Caughey, AB and Breed, EM and Escobar, GJ},
number = {3},
volume = {87},
journal = {International Journal of Gynecology \& Obstetrics},
publisher = {Wiley Online Library}}
@article{berard1998fetal,
year = {1998},
pages = {51--59},
title = {Fetal macrosomia: risk factors and outcome: A study of the outcome concerning 100 cases $>$ 4500 g},
author = {Berard, J and Dufour, P and Vinatier, D and Subtil, D and Vanderstichele, S and Monnier, JC and Puech, F},
number = {1},
volume = {77},
journal = {European Journal of Obstetrics \& Gynecology and Reproductive Biology},
publisher = {Elsevier}}
@article{salafia1995intrauterine,
year = {1995},
pages = {1049--1057},
title = {Intrauterine growth restriction in infants of less than thirty-two weeks' gestation: associated placental pathologic features},
author = {Salafia, Carolyn M and Minior, Victoria K and Pezzullo, John C and Popek, Edwina J and Rosenkrantz, Ted S and Vintzileos, Anthony M},
number = {4},
volume = {173},
journal = {American Journal of Obstetrics and Gynecology},
publisher = {Elsevier}}
@article{salafia1995very,
year = {1995},
pages = {106--110},
title = {The very low birthweight infant: maternal complications leading to preterm birth, placental lesions, and intrauterine growth},
author = {Salafia, Carolyn M and Ernst, Linda M and Pezzullo, John C and Wolf, Edward J and Rosenkrantz, Ted S and Vintzileos, Anthony M},
number = {02},
volume = {12},
journal = {American Journal of Perinatology},
publisher = {{\copyright} 1995 by Thieme Medical Publishers, Inc.}}
@article{palmsten2018subclinical,
year = {2018},
pages = {54--60},
title = {Subclinical and clinical chorioamnionitis, fetal vasculitis, and risk for preterm birth: A cohort study},
author = {Palmsten, Kristin and Nelson, Katharine K and Laurent, Louise C and Park, Soojin and Chambers, Christina D and Parast, Mana M},
volume = {67},
journal = {Placenta},
publisher = {Elsevier}}
@incollection{robins2000sensitivity,
year = {2000},
pages = {1--94},
title = {Sensitivity analysis for selection bias and unmeasured confounding in missing data and causal inference models},
author = {Robins, James M and Rotnitzky, Andrea and Scharfstein, Daniel O},
booktitle = {Statistical Models in Epidemiology, the Environment, and Clinical Trials},
publisher = {Springer}}
@article{sjolander2022sensitivity,
year = {2022},
pages = {441--479},
title = {Sensitivity analysis for causal effects with generalized linear models},
author = {Sj{\"o}lander, Arvid and Gabriel, Erin E and Cioc{\u{a}}nea-Teodorescu, Iuliana},
number = {1},
volume = {10},
journal = {Journal of Causal Inference},
publisher = {De Gruyter}}
@article{zhou2023sensitivity,
year = {2023},
pages = {744--760},
title = {Sensitivity analysis of unmeasured confounding in causal inference based on exponential tilting and super learner},
author = {Zhou, Mi and Yao, Weixin},
number = {3},
volume = {50},
journal = {Journal of Applied Statistics},
publisher = {Taylor \& Francis}}
@book{tsiatis2006semiparametric,
year = {2006},
title = {Semiparametric Theory and Missing Data},
author = {Tsiatis, Anastasios A},
publisher = {Springer}}
@article{lu2023flexible,
year = {2023},
title = {Flexible sensitivity analysis for causal inference in observational studies subject to unmeasured confounding},
author = {Lu, Sizhu and Ding, Peng},
journal = {arXiv preprint arXiv:2305.17643}}
@article{wang2021new,
year = {2021},
pages = {2153--2177},
title = {A new principle for tuning-free Huber regression},
author = {Wang, Lili and Zheng, Chao and Zhou, Wen and Zhou, Wen-Xin},
number = {4},
volume = {31},
journal = {Statistica Sinica},
publisher = {JSTOR}}
@book{van2000asymptotic,
year = {2000},
title = {Asymptotic Statistics},
author = {Van der Vaart, Aad W},
publisher = {Cambridge University Press}}
@article{rotnitzky2021characterization,
year = {2021},
pages = {231--238},
title = {Characterization of parameters with a mixed bias property},
author = {Rotnitzky, Andrea and Smucler, Ezequiel and Robins, James M},
number = {1},
volume = {108},
journal = {Biometrika},
publisher = {Oxford University Press}}
@article{rosenbaum1987sensitivity,
year = {1987},
pages = {13--26},
title = {Sensitivity analysis for certain permutation inferences in matched observational studies},
author = {Rosenbaum, Paul R},
number = {1},
volume = {74},
journal = {Biometrika},
publisher = {Oxford University Press}}
@incollection{diaz2018sensitivity,
year = {2018},
pages = {511--522},
title = {Sensitivity Analysis},
author = {D{\'\i}az, Iv{\'a}n and Luedtke, Alexander R and van der Laan, Mark J},
booktitle = {Targeted Learning in Data Science},
publisher = {Springer}}
@article{scharfstein2003generalized,
year = {2003},
pages = {601--613},
title = {Generalized additive selection models for the analysis of studies with potentially nonignorable missing outcome data},
author = {Scharfstein, Daniel O and Irizarry, Rafael A},
number = {3},
volume = {59},
journal = {Biometrics},
publisher = {Wiley Online Library}}
@article{scharfstein1999adjusting,
year = {1999},
pages = {1096--1120},
title = {Adjusting for nonignorable drop-out using semiparametric nonresponse models},
author = {Scharfstein, Daniel O and Rotnitzky, Andrea and Robins, James M},
number = {448},
volume = {94},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis}}
@article{armstrong2014fast,
year = {2014},
pages = {128--133},
title = {A fast resample method for parametric and semiparametric models},
author = {Armstrong, Timothy B and Bertanha, Marinho and Hong, Han},
number = {2},
volume = {179},
journal = {Journal of Econometrics},
publisher = {Elsevier},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{giacomini2013warp,
year = {2013},
pages = {567--589},
title = {A warp-speed method for conducting Monte Carlo experiments involving bootstrap estimators},
author = {Giacomini, Raffaella and Politis, Dimitris N and White, Halbert},
number = {03},
volume = {29},
journal = {Econometric Theory},
publisher = {Cambridge Univ Press},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{hall2000weighted,
year = {2000},
pages = {137--144},
title = {A weighted bootstrap approach to bootstrap iteration},
author = {Hall, Peter and Maesono, Yoshihiko},
number = {1},
volume = {62},
journal = {Journal of the Royal Statistical Society: Series B (Statistical Methodology)},
publisher = {Wiley Online Library},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@book{efron1994introduction,
year = {1994},
title = {An Introduction to the Bootstrap},
author = {Efron, Bradley and Tibshirani, Robert J},
publisher = {CRC press},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{diciccio1991approximations,
year = {1991},
pages = {891--902},
title = {Approximations of marginal tail probabilities for a class of smooth functions with applications to Bayesian and conditional inference},
author = {Diciccio, Thomas J and Martin, Michael A},
number = {4},
volume = {78},
journal = {Biometrika},
publisher = {Biometrika Trust},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{diciccio1996bootstrap,
year = {1996},
pages = {189--212},
title = {Bootstrap confidence intervals},
author = {DiCiccio, Thomas J and Efron, Bradley},
journal = {Statistical Science},
publisher = {JSTOR},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@book{davison1997bootstrap,
year = {1997},
title = {Bootstrap Methods and Their Application},
author = {Davison, Anthony Christopher and Hinkley, David Victor},
volume = {1},
publisher = {Cambridge University Press},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{nankervis2005computational,
year = {2005},
pages = {461--475},
title = {Computational algorithms for double bootstrap confidence intervals},
author = {Nankervis, John C},
number = {2},
volume = {49},
journal = {Computational Statistics \& Data Analysis},
publisher = {Elsevier},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{chang2015double,
year = {2015},
pages = {203-214},
title = {Double-bootstrap methods that use a single double-bootstrap simulation},
author = {Chang, Jinyuan and Hall, Peter},
journal = {Biometrika},
publisher = {Biometrika Trust},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{diciccio1992fast,
year = {1992},
pages = {285--295},
title = {Fast and accurate approximate double bootstrap confidence intervals},
author = {DiCiccio, Thomas J and Martin, Michael A and Young, G Alastair},
number = {2},
volume = {79},
journal = {Biometrika},
publisher = {Biometrika Trust},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{davidson2007improving,
year = {2007},
pages = {3259--3281},
title = {Improving the reliability of bootstrap tests with the fast double bootstrap},
author = {Davidson, Russell and MacKinnon, James G},
number = {7},
volume = {51},
journal = {Computational Statistics \& Data Analysis},
publisher = {Elsevier},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{hall1988bootstrap,
year = {1988},
pages = {661--671},
title = {On bootstrap resampling and iteration},
author = {Hall, Peter and Martin, Michael A},
number = {4},
volume = {75},
journal = {Biometrika},
publisher = {Biometrika Trust},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{hall1986bootstrap,
year = {1986},
pages = {1431--1452},
title = {On the bootstrap and confidence intervals},
author = {Hall, Peter},
journal = {The Annals of Statistics},
publisher = {JSTOR},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{beran1987prepivoting,
year = {1987},
pages = {457--468},
title = {Prepivoting to reduce level error of confidence sets},
author = {Beran, Rudolf},
number = {3},
volume = {74},
journal = {Biometrika},
publisher = {Biometrika Trust},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{daniels1954saddlepoint,
year = {1954},
pages = {631--650},
title = {Saddlepoint approximations in statistics},
author = {Daniels, Henry E},
journal = {The Annals of Mathematical Statistics},
publisher = {JSTOR},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{daniels1987tail,
year = {1987},
pages = {37--48},
title = {Tail probability approximations},
author = {Daniels, Henry E},
journal = {International Statistical Review/Revue Internationale de Statistique},
publisher = {JSTOR},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@book{hall1992bootstrap,
year = {1992},
title = {The Bootstrap and Edgeworth Expansion},
author = {Hall, Peter},
publisher = {Springer-Verlag, New York},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@book{tu1995jackknife,
year = {1995},
title = {The Jackknife and bootstrap},
author = {Tu, Dongsheng and Shao, Jun},
publisher = {Springer Series in Statistics, New York},
date-added = {2021-04-14 19:30:48 -0600},
date-modified = {2021-04-14 19:30:48 -0600}}
@article{albuquerque2004influence,
year = {2004},
pages = {31--42},
title = {Influence of maternal tobacco smoking during pregnancy on uterine, umbilical and fetal cerebral artery blood flows},
author = {Albuquerque, Cheryl A and Smith, Karen R and Johnson, Cherie and Chao, Rex and Harding, Richard},
number = {1},
volume = {80},
journal = {Early Human Development},
publisher = {Elsevier},
date-added = {2021-04-13 09:58:58 -0600},
date-modified = {2021-04-13 09:58:58 -0600}}
@article{gozubuyuk2017epidemiology,
year = {2017},
pages = {100--107},
title = {Epidemiology, pathophysiology, clinical evaluation, and treatment of carbon monoxide poisoning in child, infant, and fetus},
author = {Gozubuyuk, Atilla Alp and Dag, Huseyin and Ka{\c{c}}ar, Alper and Karakurt, Yakup and Arica, Vefik},
number = {1},
volume = {4},
journal = {Northern Clinics of Istanbul},
publisher = {Istanbul Northern Anatolian Association of Public Hospitals},
date-added = {2021-04-13 09:55:30 -0600},
date-modified = {2021-04-13 09:55:30 -0600}}
@article{caravati1988fetal,
year = {1988},
pages = {714--717},
title = {Fetal toxicity associated with maternal carbon monoxide poisoning},
author = {Caravati, E Martin and Adams, Carol J and Joyce, Steven M and Schafer, Nathan C},
number = {7},
volume = {17},
journal = {Annals of Emergency Medicine},
publisher = {Elsevier},
date-added = {2021-04-13 09:54:49 -0600},
date-modified = {2021-04-13 09:54:49 -0600}}
@article{lehtovirta1978acute,
year = {1978},
pages = {729--731},
title = {The acute effect of smoking on intervillous blood flow of the placenta},
author = {Lehtovirta, P and Forss, M},
number = {10},
volume = {85},
journal = {BJOG: An International Journal of Obstetrics \& Gynaecology},
publisher = {Wiley Online Library},
date-added = {2021-04-13 09:54:17 -0600},
date-modified = {2021-04-13 09:54:17 -0600}}
@article{bush2000quantitative,
year = {2000},
pages = {247--256},
title = {A quantitative study on the effects of maternal smoking on placental morphology and cadmium concentration},
author = {Bush, PG and Mayhew, TM and Abramovich, DR and Aggett, PJ and Burke, MD and Page, KR},
number = {2-3},
volume = {21},
journal = {Placenta},
publisher = {Elsevier},
date-added = {2021-04-13 09:52:44 -0600},
date-modified = {2021-04-13 09:52:44 -0600}}
@article{larsen2002stereologic,
year = {2002},
pages = {531--537},
title = {Stereologic examination of placentas from mothers who smoke during pregnancy},
author = {Larsen, Lise G and Clausen, Helle V and J{\o}nsson, Lisbeth},
number = {3},
volume = {186},
journal = {American Journal of Obstetrics and Gynecology},
publisher = {Elsevier},
date-added = {2021-04-13 09:52:00 -0600},
date-modified = {2021-04-13 09:52:00 -0600}}
@article{burton1989morphometric,
year = {1989},
pages = {907--915},
title = {Morphometric differences between the placental vasculature of non-smokers, smokers and ex-smokers},
author = {Burton, Graham J and Palmer, Marion E and Dalton, Kevin J},
number = {8},
volume = {96},
journal = {BJOG: An International Journal of Obstetrics \& Gynaecology},
publisher = {Wiley Online Library},
date-added = {2021-04-13 09:51:28 -0600},
date-modified = {2021-04-13 10:08:28 -0600}}
@article{van2007super,
year = {2007},
pages = {Article 25},
title = {Super learner},
author = {van der Laan, Mark J and Polley, Eric C and Hubbard, Alan E},
number = {1},
volume = {6},
journal = {Statistical Applications in Genetics and Molecular Biology},
publisher = {De Gruyter},
date-added = {2021-04-13 08:00:25 -0600},
date-modified = {2021-04-13 08:00:25 -0600}}
@article{ma2013efficient,
year = {2013},
pages = {250},
title = {Efficient estimation in sufficient dimension reduction},
author = {Ma, Yanyuan and Zhu, Liping},
number = {1},
volume = {41},
journal = {The Annals of Statistics},
publisher = {NIH Public Access},
date-added = {2021-04-13 07:49:39 -0600},
date-modified = {2021-04-13 07:49:39 -0600}}
@article{ma2012semiparametric,
year = {2012},
pages = {168--179},
title = {A semiparametric approach to dimension reduction},
author = {Ma, Yanyuan and Zhu, Liping},
number = {497},
volume = {107},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis Group},
date-added = {2021-04-13 07:49:04 -0600},
date-modified = {2021-04-13 07:49:04 -0600}}
@article{li1991sliced,
year = {1991},
pages = {316--327},
title = {Sliced inverse regression for dimension reduction},
author = {Li, Ker-Chau},
number = {414},
volume = {86},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis Group},
date-added = {2021-04-13 07:48:24 -0600},
date-modified = {2021-04-13 07:48:24 -0600}}
@article{huang2017effective,
year = {2017},
pages = {1296--1310},
title = {An effective semiparametric estimation approach for the sufficient dimension reduction model},
author = {Huang, Ming-Yueh and Chiang, Chin-Tsang},
number = {519},
volume = {112},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis},
date-added = {2021-04-13 07:47:41 -0600},
date-modified = {2021-04-13 07:47:41 -0600}}
@article{bhattacharya2020semipar,
year = {2020},
title = {Semiparametric inference for causal effects in graphical models with hidden variables},
author = {Bhattacharya, Rohit and Nabi, Razieh and Shpitser, Ilya},
journal = {arXiv preprint arXiv: 2003.12659}}
@article{vanderweele2011bias,
year = {2011},
pages = {42--52},
title = {Bias formulas for sensitivity analysis of unmeasured confounding for general outcomes, treatments, and confounders},
author = {VanderWeele, Tyler J and Arah, Onyebuchi A},
journal = {Epidemiology},
publisher = {JSTOR}}
@article{veitch2020sense,
year = {2020},
pages = {10999--11009},
title = {Sense and sensitivity analysis: Simple post-hoc analysis of bias due to unobserved confounding},
author = {Veitch, Victor and Zaveri, Anisha},
volume = {33},
journal = {Advances in Neural Information Processing Systems}}
@article{yadlowsky2018bounds,
year = {2018},
title = {Bounds on the conditional and average treatment effect with unobserved confounding factors},
author = {Yadlowsky, Steve and Namkoong, Hongseok and Basu, Sanjay and Duchi, John and Tian, Lu},
journal = {arXiv preprint arXiv:1808.09521}}
@article{zhao2019sensitivity,
year = {2019},
pages = {735--761},
title = {Sensitivity analysis for inverse probability weighting estimators via the percentile bootstrap},
author = {Zhao, Qingyuan and Small, Dylan S and Bhattacharya, Bhaswar B},
number = {4},
volume = {81},
journal = {Journal of the Royal Statistical Society: Series B},
publisher = {Wiley Online Library}}
@article{cinelli2020making,
year = {2020},
pages = {39--67},
title = {Making sense of sensitivity: Extending omitted variable bias},
author = {Cinelli, Carlos and Hazlett, Chad},
number = {1},
volume = {82},
journal = {Journal of the Royal Statistical Society: Series B},
publisher = {Wiley Online Library}}
@article{ding2016sensitivity,
year = {2016},
pages = {368},
title = {Sensitivity analysis without assumptions},
author = {Ding, Peng and VanderWeele, Tyler J},
number = {3},
volume = {27},
journal = {Epidemiology},
publisher = {Wolters Kluwer Health}}
@article{zhang2019semiparametric,
year = {2019},
title = {A semiparametric approach to model-based sensitivity analysis in observational studies},
author = {Zhang, Bo and Tchetgen Tchetgen, Eric J},
journal = {arXiv preprint arXiv:1910.14130}}
@article{zhang2022semi,
year = {2022},
pages = {S668--S691},
title = {A semi-parametric approach to model-based sensitivity analysis in observational studies},
author = {Zhang, Bo and Tchetgen Tchetgen, Eric J},
number = {Supplement\_2},
volume = {185},
journal = {Journal of the Royal Statistical Society Series A},
publisher = {Oxford University Press}}
@article{manski1990nonparametric,
year = {1990},
pages = {319--323},
title = {Nonparametric bounds on treatment effects},
author = {Manski, Charles F},
number = {2},
volume = {80},
journal = {The American Economic Review},
publisher = {JSTOR}}
@article{robins1989analysis,
year = {1989},
pages = {113--159},
title = {The analysis of randomized and non-randomized AIDS treatment trials using a new approach to causal inference in longitudinal studies},
author = {Robins, James M},
journal = {Health Service Research Methodology: A Focus on AIDS},
publisher = {US Public Health Service, National Center for Health Services Research}}
@article{rosenbaum1983assessing,
year = {1983},
pages = {212--218},
title = {Assessing sensitivity to an unobserved binary covariate in an observational study with binary outcome},
author = {Rosenbaum, Paul R and Rubin, Donald B},
number = {2},
volume = {45},
journal = {Journal of the Royal Statistical Society: Series B},
publisher = {Wiley Online Library}}
@article{imbens2003sensitivity,
year = {2003},
pages = {126--132},
title = {Sensitivity to exogeneity assumptions in program evaluation},
author = {Imbens, Guido W},
number = {2},
volume = {93},
journal = {American Economic Review}}
@article{carnegie2016assessing,
year = {2016},
pages = {395--420},
title = {Assessing sensitivity to unmeasured confounding using a simulated potential confounder},
author = {Carnegie, Nicole Bohme and Harada, Masataka and Hill, Jennifer L},
number = {3},
volume = {9},
journal = {Journal of Research on Educational},
publisher = {Taylor \& Francis}}
@article{dorie2016flexible,
year = {2016},
pages = {3453--3470},
title = {A flexible, interpretable framework for assessing sensitivity to unmeasured confounding},
author = {Dorie, Vincent and Harada, Masataka and Carnegie, Nicole Bohme and Hill, Jennifer},
number = {20},
volume = {35},
journal = {Statistics in Medicine},
publisher = {Wiley Online Library}}
@article{franks2019flexible,
year = {2020},
pages = {1730--1746},
title = {Flexible sensitivity analysis for observational studies without observable implications},
author = {Franks, AlexanderM and D'Amour, Alexander and Feller, Avi},
volume = {115},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis}}
@article{robins1999association,
year = {1999},
pages = {151--179},
title = {Association, causation, and marginal structural models},
author = {Robins, James M},
journal = {Synthese},
publisher = {JSTOR}}
@article{bonvini2022sensitivity,
year = {2022},
pages = {1540--1550},
title = {Sensitivity analysis via the proportion of unmeasured confounding},
author = {Bonvini, Matteo and Kennedy, Edward H},
number = {539},
volume = {117},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis}}
@article{cornfield1959smoking,
year = {1959},
pages = {173--203},
title = {Smoking and lung cancer: recent evidence and a discussion of some questions},
author = {Cornfield, Jerome and Haenszel, William and Hammond, E Cuyler and Lilienfeld, Abraham M and Shimkin, Michael B and Wynder, Ernst L},
number = {1},
volume = {22},
journal = {Journal of the National Cancer Institute},
publisher = {Oxford University Press}}
@article{gastwirth1998dual,
year = {1998},
pages = {907--920},
title = {Dual and simultaneous sensitivity analysis for matched pairs},
author = {Gastwirth, Joseph L and Krieger, Abba M and Rosenbaum, Paul R},
number = {4},
volume = {85},
journal = {Biometrika},
publisher = {Oxford University Press}}
@article{diaz2013sensitivity,
year = {2013},
pages = {149--160},
title = {Sensitivity analysis for causal inference under unmeasured confounding and measurement error problems},
author = {D{\'\i}az, Iv{\'a}n and van der Laan, Mark J},
number = {2},
volume = {9},
journal = {The International Journal of Biostatistics},
publisher = {De Gruyter}}
@article{dorn2022sharp,
year = {2022},
pages = {1--13},
title = {Sharp sensitivity analysis for inverse propensity weighting via quantile balancing},
author = {Dorn, Jacob and Guo, Kevin},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis}}
@article{shen2011sensitivity,
year = {2011},
pages = {822--837},
title = {Sensitivity analysis for causal inference using inverse probability weighting},
author = {Shen, Changyu and Li, Xiaochun and Li, Lingling and Were, Martin C},
number = {5},
volume = {53},
journal = {Biometrical Journal},
publisher = {Wiley Online Library}}
@article{lin1998assessing,
year = {1998},
pages = {948--963},
title = {Assessing the sensitivity of regression results to unmeasured confounders in observational studies},
author = {Lin, Danyu Y and Psaty, Bruce M and Kronmal, Richard A},
journal = {Biometrics},
publisher = {JSTOR}}
@article{luedtke2015statistics,
year = {2015},
title = {The statistics of sensitivity analyses},
author = {Luedtke, Alexander R and Diaz, Ivan and van der Laan, Mark J},
publisher = {bepress}}
@article{brumback2004sensitivity,
year = {2004},
pages = {749--767},
title = {Sensitivity analyses for unmeasured confounding assuming a marginal structural model for repeated measures},
author = {Brumback, Babette A and Hern{\'a}n, Miguel A and Haneuse, Sebastien JPA and Robins, James M},
number = {5},
volume = {23},
journal = {Statistics in Medicine},
publisher = {Wiley Online Library}}
@article{liu2013introduction,
year = {2013},
pages = {570--580},
title = {An introduction to sensitivity analysis for unobserved confounding in nonexperimental prevention research},
author = {Liu, Weiwei and Kuramoto, S Janet and Stuart, Elizabeth A},
number = {6},
volume = {14},
journal = {Prevention Science},
publisher = {Springer}}
@article{richardson2014nonparametric,
year = {2014},
pages = {596},
title = {Nonparametric bounds and sensitivity analysis of treatment effects},
author = {Richardson, Amy and Hudgens, Michael G and Gilbert, Peter B and Fine, Jason P},
number = {4},
volume = {29},
journal = {Statistical Science},
publisher = {NIH Public Access}}
@article{almond2005costs,
year = {2005},
pages = {1031--1083},
title = {The costs of low birth weight},
author = {Almond, Douglas and Chay, Kenneth Y and Lee, David S},
number = {3},
volume = {120},
journal = {The Quarterly Journal of Economics},
publisher = {MIT Press}}
@article{cattaneo2010efficient,
year = {2010},
pages = {138--154},
title = {Efficient semiparametric estimation of multi-valued treatment effects under ignorability},
author = {Cattaneo, Matias D},
number = {2},
volume = {155},
journal = {Journal of Econometrics},
publisher = {Elsevier}}
@article{chiang2012new,
year = {2012},
pages = {271--285},
title = {New estimation and inference procedures for a single-index conditional distribution model},
author = {Chiang, Chin-Tsang and Huang, Ming-Yueh},
volume = {111},
journal = {Journal of Multivariate Analysis},
publisher = {Elsevier}}
@article{wang2020,
year = {2012},
pages = {271--285},
title = {A new principle for tuning-free Huber regression},
author = {Wang, Lili and Zheng,Chao and Zhou, wen and Zhou, Wen-Xin},
volume = {111},
journal = {Journal of Multivariate Analysis},
publisher = {Elsevier}}
@article{HuangC2017Effective,
year = {2017},
pages = {1296--1310},
title = {An effective semiparametric estimation approach for the sufficient dimension reduction model},
author = {Huang, Ming-Yueh and Chiang, Chin-Tsang},
number = {519},
volume = {112},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis}}
@article{harding2003counterfactual,
year = {2003},
pages = {676--719},
title = {Counterfactual models of neighborhood effects: The effect of neighborhood poverty on dropping out and teenage pregnancy},
author = {Harding, David J},
number = {3},
volume = {109},
journal = {American journal of Sociology},
publisher = {The University of Chicago Press}}
@article{horowitz2004nonparametric,
year = {2004},
pages = {2412--2443},
title = {Nonparametric estimation of an additive model with a link function},
author = {Horowitz, Joel L and Mammen, Enno and others},
number = {6},
volume = {32},
journal = {The Annals of Statistics},
publisher = {Institute of Mathematical Statistics}}
@book{rosenbaum2002observational,
year = {2002},
title = {Observational Studies},
author = {Paul R. Rosenbaum},
publisher = {Springer-Verlag New York}}
@article{kitahata2009effect,
year = {2009},
pages = {1815--1826},
title = {Effect of early versus deferred antiretroviral therapy for HIV on survival},
author = {Kitahata, Mari M and Gange, Stephen J and Abraham, Alison G and Merriman, Barry and Saag, Michael S and Justice, Amy C and Hogg, Robert S and Deeks, Steven G and Eron, Joseph J and Brooks, John T and others},
number = {18},
volume = {360},
journal = {New England Journal of Medicine},
publisher = {Mass Medical Soc}}
@article{haviland2007combining,
year = {2007},
pages = {247},
title = {Combining propensity score matching and group-based trajectory analysis in an observational study.},
author = {Haviland, Amelia and Nagin, Daniel S and Rosenbaum, Paul R},
number = {3},
volume = {12},
journal = {Psychological Methods},
publisher = {American Psychological Association}}
@article{kennedy18sample_splitting,
year = {2020},
pages = {2008--2030},
title = {Sharp instruments for classifying compliers and generalizing causal effects},
author = {Kennedy, Edward H and Balakrishnan, Sivaraman and G'Sell, Max and others},
number = {4},
volume = {48},
journal = {Annals of Statistics},
publisher = {Institute of Mathematical Statistics}}
@article{egleston2007causal,
year = {2007},
pages = {526--545},
title = {Causal inference for non-mortality outcomes in the presence of death},
author = {Egleston, Brian L and Scharfstein, Daniel O and Freeman, Ellen E and West, Sheila K},
number = {3},
volume = {8},
journal = {Biostatistics},
publisher = {Oxford University Press}}
@article{frangakis2002principal,
year = {2002},
pages = {21--29},
title = {Principal stratification in causal inference},
author = {Frangakis, Constantine E and Rubin, Donald B},
number = {1},
volume = {58},
journal = {Biometrics},
publisher = {Wiley Online Library}}
@article{pineles2014systematic,
year = {2014},
pages = {807--823},
title = {Systematic review and meta-analysis of miscarriage and maternal exposure to tobacco smoke during pregnancy},
author = {Pineles, Beth L and Park, Edward and Samet, Jonathan M},
number = {7},
volume = {179},
journal = {American Journal of Epidemiology},
publisher = {Oxford University Press}}
@book{Bickel97semiparam,
year = {1993},
title = {Efficient and adaptive estimation for semiparametric models},
author = {Bickel, P.J. and Klaassen, C.A.J. and Ritov, Y. and Wellner, J.A.},
publisher = {Johns Hopkins University Press Baltimore}}
@article{Franks19Sensitivity,
year = {2019},
title = {Flexible sensitivity analysis for observational studies without observable implications},
author = {Alexander Franks and Alexander D'Amour and Avi Feller},
journal = {Journal of the American Statistical Association}}
@article{NLP,
year = {2017},
title = {Text as data},
author = {Gentzkow, M. and Kelley, B. and Taddy, M.},
journal = {Journal of Economic Literature}}
@article{Todd15,
year = {2015},
pages = {4329-4337},
title = {A data-mining framework for large scale analysis of dose-outcome relationships in a database of irradiated head and neck cancer patients.},
author = {Robertson, S.P. and Quon, H. and Kiess, A. P. and Moore, J. A. and Yang, W. and Cheng, Z. and Afonso, S. and Allen, M. and Richardson, M. and Choflet, A. and Sharabi, A. and McNutt, T. R.},
journal = {Med Phys}}
@article{MRI,
year = {2012},
title = {Brain imaging in Alzheimer disease.},
author = {Johnson, K. A. and Fox, N. C. and Sperling, R.A. and Klunk, W. E.},
journal = {Cold Spring Harb Perspect Med}}
@article{Ed18,
year = {2018},
title = {Visually communicating and teaching intuition for influence functions},
author = {Fisher, A. and Kennedy, E. H.},
journal = {arxiv preprint: 1810.03260}}
@article{CR82Stone,
year = {1982},
issue = {4},
pages = {1040-1053},
title = {Optimal global rates of convergence for nonparametric regression},
author = {Stone, C. J.},
volume = {10},
journal = {The Annals ofStatistics}}
@article{Dim10Dong,
year = {2010},
pages = {279-294},
title = {Dimension reduction for non-elliptically distributed predictors: Second-order moments},
author = {Dong, Y. and Li, B.},
volume = {97},
journal = {Biometrika}}
@article{Boots03Ye,
year = {2003},
pages = {968-979},
title = {Using the Bootstrap to Select one of a New Class of Dimension Reduction Methods},
author = {Ye, Z. and Weiss, R. E.},
volume = {98},
journal = {Journal of the American Statistical Association}}
@article{Sparsity07Li,
year = {2007},
pages = {603-613},
title = {Sparse Sufficient Dimension Reduction},
author = {Li, L.},
volume = {94},
journal = {Biometrika}}
@article{structural14stijn,
year = {2014},
pages = {707-731},
title = {Structural Nested Models and G-estimation: The Partially Realized Promise},
author = {Vansteelandt, S. and Joffe, M.},
number = {4},
volume = {29},
journal = {Statistical Science}}
@article{SIR91Li,
year = {1991},
pages = {316-342},
title = {Sliced Inverse Regression for Dimension Reduction (with discussion)},
author = {Li, KC.},
volume = {86},
journal = {Journal of the American Statistical Association}}
@article{SAVE91Cook,
year = {1991},
pages = {28-33},
title = {Discussion of Sliced Inverse Regression for Dimension Reduction},
author = {Cook, RD. and Weisberg, S.},
volume = {86},
journal = {Journal of the American Statistical Association}}
@article{DR07Li,
year = {2007},
pages = {997-1008},
title = {On Directional Regression for Dimension Reduction},
author = {Li, B. and Wang, S.},
volume = {102},
journal = {Journal of the American Statistical Association}}
@article{kernel07Zhu,
year = {1996},
pages = {1053-1068},
title = {Asymptotics for Kernel Estimation of Sliced Inverse Regression},
author = {Zhu, LX. and Fang, KT.},
volume = {3},
journal = {The Annals of Statistics}}
@article{average96Hardle,
year = {1989},
pages = {986-995},
title = {Investigating Smooth Multiple Regression by the Method of Average Derivatives},
author = {Hardle, W. and Stoker, TM.},
volume = {84},
journal = {Journal of the American Statistical Association}}
@article{NLS93Ichimura,
year = {1993},
pages = {71-120},
title = {Semiparametric Least Squares ({SLS}) and Weighted {SLS} Estimation of Single-Index Models},
author = {Ichimura, H.},
volume = {58},
journal = {Journal of Econometrics}}
@inproceedings{Cook98,
year = {1998},
pages = {168-170},
title = {Regression graphics: ideas for studying regressions through graphics},
author = {Cook, RD.},
publisher = {New York: Wiley}}
@article{PHD02Cook,
year = {2002},
pages = {455-474},
title = {Dimension Reduction for Conditional mean in regression},
author = {Cook, RD. and Li, B.},
volume = {30},
journal = {The Annals of Statistics}}
@article{MA12SDR,
year = {2012},
pages = {168-179},
title = {A semiparametric approach to dimension reduction},
author = {Ma, Y. and Zhu, L.},
volume = {107},
journal = {Journal of American Statistical Association}}
@article{comparison06hernan,
year = {2006},
issue = {3},
pages = {237-242},
title = {Comparison of Dynamic Treatment Regimes via Inverse Probability Weighting},
author = {Hernan, M. A. and Lanoy, E. and Costagliola, D. and Robins, J. M.},
volume = {98},
journal = {Basic and Clinical Pharmacology and Toxicology}}
@article{cortes95svm,
year = {1995},
issue = {3},
pages = {273-297},
title = {Support-vector networks},
author = {Cortes, C. and Vapnik, V.},
volume = {20},
journal = {Machine Learning}}
@article{chen16owl,
year = {2016},
pages = {1509-1521},
title = {Personalized Dose Finding Using Outcome Weighted Learning},
author = {Guanhua Chen and Donglin Zeng and Michael R. Kosorok},
number = {516},
volume = {111},
journal = {Journal of the American Statistical Association}}
@article{harcourt10risk,
year = {2015},
pages = {237-243},
title = {Risk as a proxy for race: the dangers of risk assessment},
author = {Bernard E. Harcourt},
number = {4},
volume = {27},
journal = {Federal Sentencing Reporter}}
@article{angwin16machine,
url = {https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing},
year = {2016},
title = {Machine Bias: There{\~O}s software used across the country to predict future criminals. And it{\~O}s biased against blacks.},
author = {Julia Angwin and Jeff Larson and Surya Mattu and Lauren Kirchner},
journal = {Propublica},
Bdsk-Url-1 = {https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing}}
@article{corbett-davies17algorithmic,
year = {2017},
title = {Algorithmic decision making and the cost of fairness},
author = {Sam Corbe-Davies and Emma Pierson and Avi Feller and Sharad Goel and Aziz Huq},
journal = {arxiv preprint: 1701.08230}}
@article{jabbari16fair,
year = {2016},
title = {Fair Learning in Markovian Environments},
author = {Shahin Jabbari and Matthew Joseph and Michael Kearns and Jamie Morgenstern and and Aaron Roth},
journal = {arxiv preprint: 1611.03071}}
@article{kamiran13quantifying,
year = {2013},
pages = {613-644},
title = {Quantifying explainable discrimination and removing illegal discrimination in automated decision making},
author = {Faisal Kamiran and Indre Zliobaite and Toon Calders},
number = {3},
volume = {35},
journal = {Knowledge and information systems}}
@article{shpitser17idf,
year = {2017},
title = {Identification in Causal Models With Hidden Variables},
author = {Ilya Shpitser},
journal = {Journal of the French Statistical Society (to appear)}}
@misc{carson96discrimination,
note = {70 FEP cases 921},
year = {1996},
title = {Carson vs {B}ethlehem {S}teel {C}orp.},
author = {7th {C}ircuit {C}ourt}}
@inproceedings{shpitser17idh,
year = {2017},
title = {Identification in Graphical Causal Models},
author = {Ilya Shpitser},
editors = {Steffen Lauritzen, Marloes Maathuis, Martin Wainwright, and Mathias Drton},
booktitle = {Handbook of Graphical Models}}
@inproceedings{pedreshi08discrimination,
year = {2008},
pages = {560-568},
title = {Discrimination-aware data mining},
author = {Dino Pedreshi and Salvatore Ruggieri and Franco Turini},
booktitle = {Proceedings of the 14th ACM SIGKDD international conference on knowledge discovery and data mining}}
@inproceedings{hardt16equality,
year = {2016},
pages = {3315 - 3323},
title = {Equality of opportunity in supervised learning},
author = {Moritz Hardt and Eric Price and Nati Srebro},
booktitle = {Advances In Neural Information Processing Systems}}
@inproceedings{feldman15certifying,
year = {2015},
pages = {259-268},
title = {Certifying and removing disparate impact},
author = {Michael Feldman and Sorelle A Friedler and John Moeller and Carlos Scheidegger and Suresh Venkatasubramanian},
booktitle = {Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
publisher = {ACM}}
@article{chen_harnessing_2007,
doi = {10.1186/gb-2007-8-10-r219},
url = {http://genomebiology.com/2007/8/10/R219},
issn = {1465-6906},
year = {2007},
pages = {R219},
title = {Harnessing naturally randomized transcription to infer regulatory relationships among genes},
author = {Lin Chen and Frank Emmert-Streib and John Storey},
volume = {8},
journal = {Genome Biology},
abstract = {We develop an approach utilizing randomized genotypes to rigorously infer causal regulatory relationships among genes at the transcriptional level, based on experiments in which genotyping and expression profiling are performed. This approach can be used to build transcriptional regulatory networks and to identify putative regulators of genes. We apply the method to an experiment in yeast, in which genes known to be in the same processes and functions are recovered in the resulting transcriptional regulatory network.},
keywords = {causality},
Bdsk-Url-1 = {http://genomebiology.com/2007/8/10/R219},
Bdsk-Url-2 = {https://doi.org/10.1186/gb-2007-8-10-r219}}
@incollection{drton08iterative,
doi = {10.1007/978-3-7908-2084-3_8},
url = {http://dx.doi.org/10.1007/978-3-7908-2084-3_8},
isbn = {978-3-7908-2083-6},
year = {2008},
pages = {93-104},
title = {Iterative Conditional Fitting for Discrete Chain Graph Models},
author = {Drton, Mathias},
editor = {Brito, Paula},
keywords = {categorical data; chain graph; conditional independence; graphical model},
language = {English},
booktitle = {COMPSTAT 2008},
publisher = {Physica-Verlag HD},
Bdsk-Url-1 = {http://dx.doi.org/10.1007/978-3-7908-2084-3_8}}
@misc{richardson17nested,
note = {{W}orking paper},
year = {2017},
title = {Nested {M}arkov Properties for Acyclic Directed Mixed Graphs},
author = {Thomas S. Richardson and Robin J. Evans and James M. Robins and Ilya Shpitser}}
@inproceedings{evans:didelez:15,
url = {http://ceur-ws.org/Vol-1504/uai2015aci_paper4.pdf},
year = {2015},
pages = {46--55},
title = {Recovering from Selection Bias using Marginal Structure in Discrete Models},
author = {Evans, R.~J. and Didelez, V.},
crossref = {UAI2015CI},
Bdsk-Url-1 = {http://ceur-ws.org/Vol-1504/uai2015aci_paper4.pdf}}
@misc{robins12respond,
year = {2012},
title = {Robins and {W}asserman Respond to a Nobel Prize Winner},
author = {James M. Robins and Larry Wasserman},
howpublished = {\small\url{https://normaldeviate.wordpress.com/2012/08/28/robins-and-wasserman-respond-to\\-a-nobel-prize-winner/}}}
@misc{tchetgen16discrete,
note = {{W}orking paper},
year = {2016},
title = {Discrete Choice Models for Nonmonotone Nonignorable Missing Data: Identification and Inference},
author = {Eric J. Tchetgen Tchetgen and Linbo Wang and BaoLuo Sun},
howpublished = {\url{https://arxiv.org/abs/1607.02631}}}
@misc{sadinle16itemwise,
note = {{W}orking paper},
year = {2016},
title = {Itemwise conditionally independent nonresponse modeling for incomplete multivariate data},
author = {Mauricio Sadinle and Jerome P. Reiter},
howpublished = {\url{https://arxiv.org/abs/1609.00656}}}
@article{chipman10bart,
year = {2010},
pages = {266-298},
title = {{BART}: Bayesian additive regression trees},
author = {Hugh A. Chipman and Edward I. George and Robert E. McCulloch},
number = {1},
volume = {4},
journal = {Annals of Applied Statistics}}
@article{caleb17quantifying,
year = {2017},
title = {Quantifying an Adherence Path-Specific Effect of Antiretroviral Therapy in the Nigeria PEPFAR Program},
author = {Caleb Miles and Ilya Shpitser and Phyllis Kanki and Seema Melone and Eric J. Tchetgen Tchetgen},
journal = {Journal of the American Statistical Association}}
@article{caleb16on,
year = {2016},
author = {Caleb Miles and Phyllis Kanki and Seema Meloni and Eric Tchetgen Tchetgen},
journal = {Journal of Causal Inference}}
@article{drton16generic,
year = {2016},
title = {Generic identifiability of linear structural equation models by ancestor decomposition},
author = {Drton, M. and Weihs, L.},
journal = {Scandinavian Journal of Statistics}}
@article{foygel12halftrek,
year = {2012},
pages = {1682-1713},
title = {Half-Trek Criterion for Generic Identifiability of Linear Structural Equation Models},
author = {Rina Foygel and Jan Draisma and Mathias Drton},
number = {3},
volume = {40},
journal = {Annals of Statistics}}
@article{drton11global,
year = {2011},
pages = {865-886},
title = {Global Identifiability of Linear Structural Equation Models},
author = {Mathias Drton and Rina Foygel and Seth Sullivant},
number = {2},
volume = {39},
journal = {Annals of Statistics}}
@article{imai10general,
year = {2010},
pages = {309-334},
title = {A General Approach to Causal Mediation Analysis},
author = {Kosuke Imai and Luke Keele and Dustin Tingley},
number = {4},
volume = {15},
journal = {Psychological Methods}}
@article{chen07semiparametric,
year = {2007},
pages = {413-421},
title = {A Semiparametric Odds Ratio Model for Measuring Association},
author = {Hua Yun Chen},
volume = {63},
journal = {biometrics}}
@article{mozeika14consistent,
year = {2014},
issue = {1},
title = {Consistent inference of a general model using the pseudolikelihood method},
author = {Mozeika, A. and Dikmen, O. and Piili, J.},
volume = {90},
journal = {Physical Review E: Statistical, Nonlinear, and Soft Matter Physics.}}
@unpublished{vanderlaan12networks,
note = {{W}orking paper},
year = {2012},
title = {Causal Inference for Networks.},
author = {Mark J. van der Laan}}
@article{robins97non,
year = {1997},
pages = {21-37},
title = {Non-response models for the analysis of non-monotone non-ignorable missing data},
author = {James M. Robins},
volume = {16},
journal = {Statistics in Medicine}}
@article{vinokur97mastery,
year = {1997},
pages = {867-877},
title = {Mastery and inoculation against setbacks as active ingredients in the jobs intervention for the unemployed},
author = {Vinokur, A. and Schul, Y.},
number = {5},
volume = {65},
journal = {Journal of Consulting and Clinical Psychology}}
@article{vanderweele14on,
year = {2014},
pages = {473-484},
title = {On causal interpretation of race in regressions adjusting for confounding and mediating variables},
author = {Tyler J. VanderWeele and Whitney R. Robinson},
number = {4},
volume = {25},
journal = {Epidemiology}}
@article{hudgens08toward,
year = {2008},
pages = {832-842},
title = {Toward Causal Inference With Interference},
author = {M.G. Hudgens and M.E. Halloran},
number = {482},
volume = {103},
journal = {Journal of the American Statistical Association}}
@inproceedings{garcia10identifying,
year = {2010},
title = {Identifying causal effects with computer algebra},
author = {Garcia-Puente, L. D. and Spielvogel, S. and Sullivant, S.},
editors = {P. Grnwald and P. Spirtes, eds.},
booktitle = {Proceedings of the Twenty-sixth Conference on Uncertainty in Artificial Intelligence (UAI)},
publisher = {AUAI Press}}
@inproceedings{robins97marginal,
year = {1997},
pages = {1-10},
title = {Marginal Structural Models},
author = {J. M. Robins},
booktitle = {American Statistical Association, Section on Bayesian Statistical Science}}
@inproceedings{robins89analysis,
year = {1989},
pages = {113-159},
title = {The analysis of randomized and non-randomized AIDS treatment trials using a new approach to causal inference in longitudinal studies},
author = {James M. Robins},
editor = {Sechrest, L. and Freeman, H. and Mulley, A.},
booktitle = {Health Service Research Methodology: A Focus on AIDS},
publisher = {NCHSR, U.S. Public Health Service}}
@article{robins92estimation,
year = {1992},
pages = {321-334},
title = {Estimation of the time-dependent accelerated failure time model in the presence of confounding factors},
author = {James M. Robins},
volume = {79},
journal = {Biometrika}}
@inproceedings{robins99on,
year = {1999},
pages = {305 -- 321},
title = {On the Impossibility of Inferring Causation from Association without Background Knowledge},
author = {James M. Robins and Larry Wasserman},
editor = {C. Glymour and G. Cooper},
booktitle = {Computation, Causation, and Discovery},
publisher = {Menlo Park, CA, CAmbridge, MA: AAAI Press/The MIT Press}}
@inproceedings{robins99testing,
year = {1999},
pages = {349 -- 405},
title = {Testing and estimation of direct effects by reparameterizing directed acyclic graphs with structural nested models},
author = {James M. Robins},
editor = {C. Glymour and G. Cooper},
booktitle = {Computation, Causation, and Discovery},
publisher = {Menlo Park, CA, CAmbridge, MA: AAAI Press/The MIT Press}}
@article{roweis99unifying,
year = {1999},
pages = {305--345},
title = {A Unifying Review of Linear {G}aussian Models},
author = {Sam Roweis and Zoubin Ghahramani},
number = {2},
volume = {11},
journal = {Neural Computation}}
@article{zongming08structural,
year = {2008},
pages = {2847--2880},
title = {Structural learning of chain graphs via decomposition},
author = {Zongming Ma and Xianchao Xie and Zhi Geng},
volume = {9},
journal = {Journal of Machine Learning Research}}
@article{beal04var,
year = {2004},
pages = {1--44},
title = {Variational {B}ayesian Learning of Directed Graphical Models with Hidden Variables},
author = {Matthew J. Beal and Zoubin Ghahramani},
number = {1},
volume = {1},
journal = {Bayesian Analysis}}
@article{shimizu06linear,
year = {2006},
pages = {2003--2030},
title = {A linear non-{G}aussian acyclic model for causal discovery},
author = {Shohei Shimizu and Patrik O. Hoyer and Aapo Hyv\"arinen and Antti J. Kerminen},
volume = {7},
journal = {Journal of Machine Learning Research}}
@article{hill11bayesian,
year = {2011},
title = {Bayesian Nonparametric Modeling for Causal Inference},
author = {Jennifer L. Hill},
number = {1},
volume = {20},
journal = {Journal of Computational and Graphical Statistics}}
@article{geiger:01,
year = {2001},
pages = {505--529},
title = {Stratified exponential families: graphical models and model selection},
author = {Geiger, D. and Heckerman, D. and King, H. and Meek, C.},
volume = {29},
journal = {Ann. Statist.},
optnumber = {2}}
@article{drton:sullivant,
year = {2007},
pages = {1273--1297},
title = {Algebraic statistical models},
author = {Drton, M. and Sullivant, S.},
volume = {17},
journal = {Statistica Sinica}}
@article{maathuis:2010,
year = {2010},
pages = {247--248},
title = {Predicting causal effects in large-scale systems from observational data},
author = {M. H. Maathuis and D. Colombo and M. Kalisch and P. B{\"{u}}hlmann},
volume = {7},
journal = {Nature Methods}}
@article{colombo:2012,
year = {1993},
pages = {294--321},
title = {Learning high-dimensional directed acyclic graphs with latent and selection variables},
author = {D. Colombo and M.H. Maathuis and M. Kalisch and T.S. Richardson},
volume = {40},
journal = {The Annals of Statistics}}
@article{lloyd82least,
year = {1982},
issue = {2},
pages = {129-137},
title = {Least squares quantization in PCM},
author = {S. P. Lloyd},
volume = {28},
journal = {IEEE Transactions on Information Theory}}
@article{baum66statistical,
year = {1966},
pages = {1554-1563},
title = {Statistical Inference for Probabilistic Functions of Finite State {M}arkov Chains},
author = {Leonard E. Baum and Ted Petrie},
number = {6},
volume = {37},
journal = {Annals of Mathematical Statistics}}
@article{ising25beitrag,
year = {1925},
issue = {1},
pages = {253-258},
title = {{B}eitrag zur {T}heorie des {F}erromagnetismus},
author = {Ernst Ising},
volume = {31},
journal = {Zeitschrift fr Physik}}
@article{bang05doubly,
year = {2005},
pages = {962-972},
title = {Doubly Robust Estimation in Missing Data and Causal Inference Models},
author = {Bang, H. and Robins, J. M.},
volume = {61},
journal = {Biometrics}}
@article{varin11overview,
year = {2011},
pages = {5-42},
title = {An overview of composite likelihood methods},
author = {Cristiano Varin and Nancy Reid and David Firth},
volume = {21},
journal = {Statistica Sinica}}
@article{besag75pseudo,
year = {1975},
pages = {179-195},
title = {Statistical Analysis of Lattice Data},
author = {Julian Besag},
number = {3},
volume = {24},
journal = {The Statistician}}
@article{de2012commentary,
year = {2012},
pages = {233--237},
title = {Commentary: Marginal Structural Models: The Way Forward for Life-course Epidemiology?},
author = {De Stavola, Bianca L and Daniel, Rhian M},
number = {2},
volume = {23},
journal = {Epidemiology},
publisher = {LWW}}
@article{nandi2012using,
year = {2012},
pages = {223},
title = {Using marginal structural models to estimate the direct effect of adverse childhood social conditions on onset of heart disease, diabetes, and stroke},
author = {Nandi, Arijit and Glymour, M Maria and Kawachi, Ichiro and VanderWeele, Tyler J},
number = {2},
volume = {23},
journal = {Epidemiology (Cambridge, Mass.)},
publisher = {NIH Public Access}}
@article{cole2008constructing,
year = {2008},
pages = {656--664},
title = {Constructing inverse probability weights for marginal structural models},
author = {Cole, Stephen R and Hernan, Miguel A},
number = {6},
volume = {168},
journal = {American journal of epidemiology},
publisher = {Oxford Univ Press}}
@article{vourli2015performance,
year = {2015},
pages = {254--270},
title = {Performance of the marginal structural models under various scenarios of incomplete marker's values: A simulation study},
author = {Vourli, Georgia and Touloumi, Giota},
number = {2},
volume = {57},
journal = {Biometrical Journal},
publisher = {Wiley Online Library}}
@article{rosenbaum2002covariance,
year = {2002},
pages = {286--327},
title = {Covariance adjustment in randomized experiments and observational studies},
author = {Rosenbaum, Paul R},
number = {3},
volume = {17},
journal = {Statistical Science},
publisher = {Institute of Mathematical Statistics}}
@article{li2011propensity,
year = {2011},
pages = {345--353},
title = {Propensity score-based sensitivity analysis method for uncontrolled confounding},
author = {Li, Lingling and Shen, Changyu and Wu, Ann C and Li, Xiaochun},
number = {3},
volume = {174},
journal = {American journal of epidemiology},
publisher = {Oxford University Press}}
@incollection{card95using,
year = {1995},
title = {Using Geographic Variation in College Proximity to Estimate the Return to Schooling},
author = {David Card},
editor = {Louis Christofides, E. Kenneth Grant and Robert Swindinsky},
booktitle = {Aspects of Labour Economics: Essays in Honour of John Vanderkamp},
publisher = {University of Toronto Press}}
@article{recht11simpler,
year = {2011},
pages = {3413-3430},
title = {A Simpler Approach to Matrix Completion},
author = {Benjamin Recht},
volume = {12},
journal = {Journal of Machine Learning Research}}
@inproceedings{newey94large,
year = {1994},
pages = {2111-2245},
title = {Chapter 35: Large sample estimation and hypothesis testing},
author = {Whitney Newey and Daniel McFadden},
booktitle = {Handbook of Econometrics, Vol.4},
publisher = {Elsevier Science}}
@inproceedings{lafferty01conditional,
year = {2001},
pages = {282 -- 289},
title = {Conditional random fields: Probabilistic models for segmenting and labeling sequence data},
author = {Lafferty, J. and McCallum, A. and Pereira, F.},
booktitle = {Proceedings of the Eighteenth International Conference on Machine Learning (ICML-01)},
publisher = {Morgan Kaufmann}}
@inproceedings{spirtes95cyclic,
year = {1995},
pages = {491-498},
title = {Directed cyclic graphical representations of feedback models},
author = {Peter Spirtes},
booktitle = {Proceedings of the Eleventh Conference on Uncertainty in Artificial Intelligence (UAI-95)},
publisher = {AUAI Press}}
@inproceedings{shpitser15missing,
year = {2015},
pages = {802-811},
title = {Missing Data as a Causal and Probabilistic Problem},
author = {Ilya Shpitser and Karthika Mohan and Judea Pearl},
booktitle = {Proceedings of the Thirty First Conference on Uncertainty in Artificial Intelligence (UAI-15)},
publisher = {AUAI Press}}
@article{shpitser15hierarchy,
year = {2016},
pages = {2433-2466},
title = {Causal Inference with a Graphical Hierarchy of Interventions},
author = {Ilya Shpitser and Eric {Tchetgen Tchetgen}},
eprint = {1411.2127},
number = {6},
volume = {44},
journal = {Annals of Statistics},
primaryclass = {stat},
archiveprefix = {arXiv}}
@unpublished{evans15smooth,
note = {Unpublished},
year = {2015},
title = {Smooth, identifiable supermodels of discrete {DAG} models with latent variables},
author = {Robin J. Evans and Thomas S. Richardson},
eprint = {1511.06813},
primaryclass = {stat},
archiveprefix = {arXiv}}
@unpublished{richardson15risk,
note = {In Review},
year = {2015},
title = {On Modeling and Estimation for the Relative Risk and Risk Difference},
author = {Thomas S. Richardson and James M. Robins and Linbo Wang},
eprint = {1510.02430},
primaryclass = {stat},
archiveprefix = {arXiv}}
@inproceedings{shpitser15segregated,
year = {2015},
title = {Segregated Graphs and Marginals of Chain Graph Models},
author = {Ilya Shpitser},
booktitle = {Advances in Neural Information Processing Systems 28},
publisher = {Curran Associates, Inc.}}
@article{koster02marginalizing,
year = {2002},
pages = {817-840},
title = {Marginalizing and Conditioning in Graphical Models},
author = {Jan T. A. Koster},
number = {6},
volume = {8},
journal = {Bernoulli}}
@article{wermuth11probability,
year = {2011},
pages = {845-879},
title = {Probability distributions with summary graph structure},
author = {Nanny Wermuth},
number = {3},
volume = {17},
journal = {Bernoulli}}
@article{sadeghi14markov,
year = {2014},
pages = {676-696},
title = {Markov properties for mixed graphs},
author = {Kayvan Sadeghi and Steffen Lauritzen},
number = {2},
volume = {20},
journal = {Bernoulli}}
@suppperiodical{shpitser15nep,
year = {2015},
title = {Supplementary materials for: Causal Inference with a Graphical Hierarchy of Interventions},
author = {Ilya Shpitser and Eric Tchetgen Tchetgen}}
@article{identification14jessica,
year = {2014},
pages = {1-19},
title = {Identification, Estimation and Approximation of Risk under interventions that depend on the natural value of treatment using observational data},
author = {Jessica G. Young and Miguel A. Hernan and James M. Robins},
number = {1},
volume = {3},
journal = {Epidemiologic Methods}}
@article{population08hubbard,
year = {2008},
pages = {35-47},
title = {Population Intervention Models in Causal Inference},
author = {Alan E. Hubbard and Mark J. Van Der Laan},
number = {1},
volume = {95},
journal = {Biometrika}}
@article{ogburn14interference,
year = {2014},
pages = {559-578},
title = {Causal Diagrams for Interference},
author = {Elizabeth L. Ogburn and Tyler J. VanderWeele},
number = {4},
volume = {29},
journal = {Statistical Science}}
@article{vanderlaan14connected,
year = {2014},
pages = {13-74},
title = {Causal Inference for a Population of Causally Connected Units},
author = {Mark J. van der Laan},
number = {1},
volume = {2},
journal = {Journal of Causal Inference}}
@article{murphy03optimal,
year = {2003},
pages = {331-366},
title = {Optimal Dynamic Treatment Regimes},
author = {Susan A. Murphy},
volume = {65},
journal = {Journal of the Royal Statistical Society (Series B)}}
@article{moodie07demystifying,
year = {2007},
pages = {447-455},
title = {Demystifying optimal dynamic treatment regimes},
author = {Erica E. M. Moodie and Thomas S. Richardson and David A. Stephens},
number = {2},
volume = {63},
journal = {Biometrics}}
@article{spohn12reversing,
year = {2012},
pages = {95-122},
title = {Reversing 30 years of discussion: why causal decision theorists should one-box},
author = {Wolfgang Spohn},
number = {1},
volume = {187},
journal = {Synthese}}
@article{bell64on,
year = {1964},
pages = {195-200},
title = {On the {E}instein {P}odolsky {R}osen Paradox},
author = {John Bell},
number = {3},
volume = {1},
journal = {Physics}}
@article{heitjan91ignorability,
year = {1991},
pages = {2244-2253},
title = {Ignorability and Coarse Data},
author = {Daniel F. Heitjan and Donald Rubin},
number = {4},
volume = {19},
journal = {Annals of Statistics}}
@article{principal07frangakis,
year = {2007},
pages = {641-662},
title = {Principal Stratification Designs to Estimate Input Data Missing Due to Death},
author = {Constantine E. Frangakis and Donald B. Rubin and Ming-Wen An and Ellen MacKenzie},
volume = {63},
journal = {Biometrics}}
@article{rubin76inference,
year = {1976},
pages = {581-592},
title = {Causal Inference and Missing Data (with discussion)},
author = {D. B. Rubin},
volume = {63},
journal = {Biometrika}}
@article{kaplan58nonparametric,
year = {1958},
issue = {282},
pages = {457-481},
title = {Nonparametric estimation from incomplete observations},
author = {E.L. Kaplan and P. Meier},
volume = {53},
journal = {Journal of the American Statistical Association}}
@article{dempster77maximum,
year = {1977},
issue = {1},
pages = {1-38},
title = {Maximum Likelihood from Incomplete Data via the {EM} Algorithm},
author = {A.P. Dempster and N.M. Laird and D.B. Rubin},
volume = {39},
journal = {Journal of the Royal Statistical Society, Series B}}
@article{drton09discrete,
year = {2009},
pages = {736-753},
title = {Discrete chain graph models},
author = {Mathias Drton},
number = {3},
volume = {15},
journal = {Bernoulli}}
@article{tchetgen12on,
year = {2012},
pages = {55-75},
title = {On Causal Inference in the Presence of Interference},
author = {Eric J. Tchetgen Tchetgen and Tyler J. VanderWeele},
number = {1},
volume = {21},
journal = {Statistical Methods in Medical Research}}
@article{lauritzen02chain,
year = {2002},
pages = {321--361},
title = {Chain graph models and their causal interpretations (with discussion)},
author = {Steffen L. Lauritzen and Thomas S. Richardson},
volume = {64},
journal = {Journal of the Royal Statistical Society: Series B}}
@article{vanderweele12components,
year = {2012},
pages = {751-761},
title = {Components of the indirect effect in vaccine trials: identification of contagion and infectiousness effects},
author = {Tyler J. VanderWeele and Eric J. Tchetgen Tchetgen and M. Elizabeth Halloran},
number = {5},
volume = {23},
journal = {Epidemiology}}
@article{halloran95causal,
year = {1995},
pages = {142-151},
title = {Causal inference for infectious diseases},
author = {M. Elizabeth Halloran and C. J. Struchiner},
volume = {6},
journal = {Epidemiology}}
@article{drton09likelihood,
year = {2009},
pages = {979--1012},
title = {Likelihood ratio tests and singularities},
author = {Mathias Drton},
number = {2},
volume = {37},
journal = {Annals of Statistics}}
@article{shpitser14behave,
year = {2014},
pages = {3-39},
title = {Introduction to Nested {M}arkov Models},
author = {Ilya Shpitser and Robin J. Evans and Thomas S. Richardson and James M. Robins},
number = {1},
volume = {41},
journal = {Behaviormetrika}}
@article{robins04effects,
year = {2004},
pages = {2191-2230},
title = {Effects of multiple interventions},
author = {James M. Robins and Miguel A. Hernan and Uwe Siebert},
number = {28},
volume = {2},
journal = {Comparative quantification of health risks : global and regional burden of disease attributable to selected major risk factors},
publisher = {Geneva: World Health Organization}}
@article{tchetgen14semi,
year = {2014},
title = {Estimation of a Semiparametric Natural Direct Effect Model Incorporating Baseline Covariates},
author = {Eric J. Tchetgen Tchetgen and Ilya Shpitser},
journal = {Biometrika (in Press)}}
@inproceedings{robins04optimal,
year = {2004},
title = {Optimal structural nested models for optimal sequential decisions},
author = {J. M. Robins},
editors = {Lin, D. Y. and Heagerty, P.},
booktitle = {Proceedings of the Second Seattle Symposium on Biostatistics},
publisher = {New York. Springer}}
@inproceedings{shpitser09ett,
year = {2009},
title = {Effects of treatment on the treated: identification and generalization},
author = {Ilya Shpitser and Judea Pearl},
volume = {25},
booktitle = {Uncertainty in Artificial Intelligence},
publisher = {AUAI Press}}
@article{richardson06markov,
year = {2006},
issue = {1-2},
pages = {107-136},
title = {Markov logic networks},
author = {Matthew Richardson and Pedro Domingos},
volume = {62},
journal = {Machine Learning}}
@inproceedings{milch07blog,
year = {2007},
title = {BLOG: Probabilistic Models with Unknown Objects},
author = {Brian Milch and Bhaskara Marthi and Stuart Russell and David Sontag and Daniel L. Ong and Andrey Kolobov},
booktitle = {Lise Getoor and Ben Taskar, eds. Statistical Relational Learning},
publisher = {Cambridge, MA: MIT Press}}
@unpublished{tchetgen11cond,
note = {Unpublished manuscript (http://www.bepress.com/harvardbiostat/paper130)},
year = {2011},
title = {Semiparametric Theory for Causal Mediation Analysis: efficiency bounds, multiple robustness, and sensitivity analysis},
author = {Eric J. Tchetgen Tchetgen and Ilya Shpitser}}
@book{hojsgaard12graphical,
year = {2012},
title = {Graphical Models with R},
author = {S¿ren H¿jsgaard and David Edwards and Steffen Lauritzen},
edition = {1st edition},
publisher = {Springer-Verlag New York}}
@book{tsiatis06missing,
year = {2006},
title = {Semiparametric Theory and Missing Data},
author = {Anastasios Tsiatis},
edition = {1st edition},
publisher = {Springer-Verlag New York}}
@book{wooldridge15introductory,
year = {2015},
title = {Introductory Econometrics: A Modern Approach},
author = {Jeffrey M. Wooldridge},
edition = {5th edition},
publisher = {South-Western, Mason, OH}}
@book{kenny06dyadic,
year = {2006},
title = {Dyadic Data Analysis},
author = {David A. Kenny and Deborah A. Kashy and William L. Cook},
publisher = {Guilford Press New York}}
@book{vinod10advances,
year = {2010},
title = {Advances in Social Science Research Using R},
author = {Hrishikesh D. Vinod},
publisher = {Springer-Verlag New York}}
@book{wasserman05all,
year = {2005},
title = {All Of Statistics (a Concise Course in Statistical Inference)},
author = {Larry Wasserman},
publisher = {Springer, New York}}
@book{erica13statistical,
year = {2013},
title = {Statistical Methods for Dynamic Treatment Regimes (Reinforcement Learning, Causal Inference, and Personalized Medicine)},
author = {Bibhas Chakraborty and Erica E. M. Moodie},
publisher = {Springer, New York}}
@book{koller09probabilistic,
year = {2009},
title = {Probabilistic Graphical Models: Principles and Techniques},
author = {Daphne Koller and Nir Friedman},
publisher = {The MIT Press, Cambridge MA}}
@book{van03unified,
year = {2003},
title = {Unified Methods for Censored Longitudinal Data and Causality},
author = {James M. Robins and Mark van der Laan},
publisher = {Springer-Verlag New York, Inc.}}
@book{fisher66identification,
year = {1966},
title = {The identification problem in econometrics},
author = {Franklin M. Fisher},
publisher = {McGraw-Hill Book Company}}
@inproceedings{eun09presence,
year = {2009},
title = {Detecting the Presence and Absence of Causal Relationships Between Expression of Yeast Genes with Very Few Samples},
author = {Eun Yong Kang and Ilya Shpitser and Hyun Min Kang and Chun Ye and Eleazar Eskin},
booktitle = {RECOMB}}
@article{dawid02influence,
year = {2002},
pages = {161-189},
title = {Influence diagrams for causal modelling and inference.},
author = {A.P. Dawid},
volume = {70},
journal = {International Statistical Review}}
@article{friedman2000ubn,
year = {2000},
pages = {601--620},
title = {{Using Bayesian Networks to Analyze Expression Data}},
author = {Friedman, N. and Linial, M. and Nachman, I. and Pe'er, D.},
number = {3-4},
volume = {7},
journal = {Journal of Computational Biology},
publisher = {Mary Ann Liebert, Inc.}}
@misc{peer2001isp,
year = {2001},
pages = {215--224},
title = {{Inferring subnetworks from perturbed expression profiles}},
author = {Pe'er, D. and Regev, A. and Elidan, G. and Friedman, N.},
number = {90001},
volume = {17},
journal = {Bioinformatics},
publisher = {Oxford University Press}}
@article{segal2003mni,
year = {2003},
pages = {166--76},
title = {{Module networks: identifying regulatory modules and their condition-specific regulators from gene expression data}},
author = {Segal, E. and Shapira, M. and Regev, A. and Pe'er, D. and Botstein, D. and Koller, D. and Friedman, N.},
number = {2},
volume = {34},
journal = {Nat Genet}}
@article{friedman2004icn,
year = {2004},
pages = {799},
title = {{Inferring Cellular Networks Using Probabilistic Graphical Models}},
author = {Friedman, N.},
number = {5659},
volume = {303},
journal = {Science's STKE},
publisher = {AAAS}}
@conference{hartemink2001ugm,
year = {2001},
pages = {422--433},
title = {{Using graphical models and genomic expression data to statistically validate models of genetic regulatory networks}},
author = {Hartemink, A.J. and Gifford, D.K. and Jaakkola, T.S. and Young, R.A.},
volume = {6},
booktitle = {Pac. Symp. Biocomput}}
@inproceedings{shpitser13sparse,
year = {2013},
pages = {576-585},
title = {Sparse Nested {M}arkov Models with Log-linear Parameters},
author = {Ilya Shpitser and Robin Evans and Thomas S. Richardson and James M. Robins},
booktitle = {Proceedings of the Twenty Ninth Conference on Uncertainty in Artificial Intelligence (UAI-13)},
publisher = {AUAI Press}}
@article{eun10presence,
year = {2010},
pages = {533-546},
title = {Detecting the Presence and Absence of Causal Relationships Between Expression of Yeast Genes with Very Few Samples},
author = {Eun Yong Kang and Chun Ye and Ilya Shpitser and Eleazar Eskin},
volume = {17(3)},
journal = {Journal of Computational Biology}}
@book{heckman92random,
year = {1992},
pages = {201-230},
title = {Randomization and social policy evaluation},
author = {J. J. Heckman},
publisher = {In: Evaluations: Welfare and Training Programs, Cambridge, MA: Harvard University Press}}
@inproceedings{richardson12markov,
year = {2012},
title = {Nested {M}arkov Properties for Acyclic Directed Mixed Graphs},
author = {Thomas S. Richardson and James M. Robins and Ilya Shpitser},
volume = {28},
booktitle = {{U}ncertainty in {A}rtificial {I}ntelligence},
publisher = {AUAI Press}}
@inproceedings{silva11mixed,
year = {2011},
title = {Mixed cumulative distribution networks},
author = {Silva, R. and Blundell, C. and Teh, Y.W.},
booktitle = {Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS 2011)}}
@article{chickering02equiv,
year = {2002},
pages = {445-498},
title = {Learning Equivalence Classes of Bayesian Network Structures},
author = {David Maxwell Chickering},
volume = {2},
journal = {Journal of Machine Learning Research}}
@article{vanderweele13on,
year = {2013},
pages = {196-220},
title = {On the definition of a confounder},
author = {Tyler J. Vander{W}eele and Ilya Shpitser},
number = {1},
volume = {41},
journal = {Annals of Statistics}}
@article{shpitser10complete,
year = {2010},
title = {A Complete Graphical Criterion for the Adjustment Formula in Mediation Analysis},
author = {Ilya Shpitser and Tyler J. VanderWeele},
journal = {International Journal of Biostatistics}}
@article{ackley85learning,
year = {1985},
pages = {147-169},
title = {A learning algorithm for {B}oltzmann machines},
author = {David H. Ackley and Geoffrey E. Hinton and Terrence J. Seinowski},
number = {1},
volume = {9},
journal = {Cognitive Science}}
@article{silva09hidden,
year = {2009},
pages = {1187--1238},
title = {The hidden life of latent variables: bayesian learning with mixed graph models},
author = {Ricardo Silva an Zoubin Ghahramani},
volume = {10},
journal = {Journal of Machine Learning Research}}
@inproceedings{shpitser12parameter,
year = {2012},
title = {Parameter and Structure Learning in Nested {M}arkov Models},
author = {Ilya Shpitser and Thomas S. Richardson and James M. Robins and Robin J. Evans},
booktitle = {Causal Structure Learning Workshop of the 28th Conference on Uncertainty in Artificial Intelligence (UAI-12)}}
@incollection{mohan13missing,
url = {http://papers.nips.cc/paper/4899-graphical-models-for-inference-with-missing-data.pdf},
year = {2013},
pages = {1277--1285},
title = {Graphical Models for Inference with Missing Data},
author = {Mohan, Karthika and Pearl, Judea and Tian, Jin},
editor = {C.J.C. Burges and L. Bottou and M. Welling and Z. Ghahramani and K.Q. Weinberger},
booktitle = {Advances in Neural Information Processing Systems 26},
publisher = {Curran Associates, Inc.},
Bdsk-Url-1 = {http://papers.nips.cc/paper/4899-graphical-models-for-inference-with-missing-data.pdf}}
@incollection{mohan14missing,
url = {http://papers.nips.cc/paper/5575-graphical-models-for-recovering-probabilistic-and-causal-queries-from-missing-data.pdf},
year = {2014},
pages = {1520--1528},
title = {Graphical Models for Recovering Probabilistic and Causal Queries from Missing Data},
author = {Mohan, Karthika and Pearl, Judea},
editor = {Z. Ghahramani and M. Welling and C. Cortes and N.D. Lawrence and K.Q. Weinberger},
booktitle = {Advances in Neural Information Processing Systems 27},
publisher = {Curran Associates, Inc.},
Bdsk-Url-1 = {http://papers.nips.cc/paper/5575-graphical-models-for-recovering-probabilistic-and-causal-queries-from-missing-data.pdf}}
@techreport{yudkowsky10tdt,
year = {2010},
title = {Timeless Decision Theory},
author = {Eliezer Yudkowsky},
institution = {Machine Intelligence Research Institute}}
@techreport{pearl14rec,
year = {2014},
title = {Recoverability and Testability of Missing data: Introduction and Summary of Results},
author = {Judea Pearl and Karthika Mohan},
institution = {UCLA Computer Science Department}}
@techreport{pearl13simpsons,
year = {2013},
title = {Understanding {S}impson's Paradox},
author = {Judea Pearl},
institution = {UCLA Computer Science Department}}
@techreport{shpitser12nested,
year = {2012},
title = {Parameter and Structure Learning in Nested {M}arkov Models},
author = {Ilya Shpitser and Thomas S. Richardson and James M. Robins and Robin Evans},
institution = {UAI Causal Structure Learning Workshop}}
@book{earwaker92helping,
year = {1992},
title = {Helping and supporting students: rethinking the issues.},
author = {J. Earwaker},
publisher = {Buckingham: SRHE and Open University Press}}
@book{biggs07teaching,
year = {2007},
title = {Teaching for Quality Learning at University},
author = {John Biggs and Catherine Tang},
publisher = {McGraw-Hill International}}
@book{gosling01pcap,
year = {2001},
title = {How to Use Learning Outcomes and Assessment Criteria},
author = {Gosling D. and Moon J.},
publisher = {Southern England Consortium for Credit Accumulation and Transfer (SEEC)}}
@misc{math6128url,
year = {2014},
title = {Southampton Mathematical Sciences {MATH 6128} Module Website},
howpublished = {\url{ http://www.southampton.ac.uk/maths/postgraduate/taught\_modules/math6128\_stochastic\_processes.page }}}
@misc{math2012url,
year = {2014},
title = {Southampton Mathematical Sciences {MATH 2012} Module Website},
howpublished = {\url{ http://www.southampton.ac.uk/maths/undergraduate/modules/math2012\_stochastic\_processes.page }}}
@article{evans14markovian,
year = {2014},
pages = {1-30},
title = {Markovian Acyclic Directed Mixed Graphs for Discrete Data},
author = {Robin J. Evans and Thomas S. Richardson},
journal = {Annals of Statistics}}
@article{hirano00assessing,
year = {2000},
issue = {1},
pages = {69-88},
title = {Assessing the effect of an influence vaccine in an encouragement design},
author = {Keisuke Hirano and Guido W. Imbens and Donald B. Rubin and Xiao-Hua Zhou},
volume = {1},
journal = {Biostatistics}}
@article{smith96constructing,
year = {1996},
issue = {1},
pages = {65-77},
title = {Constructing mathematical examinations to assess a range of knowledge and skills},
author = {Smith, G. and Wood, L. and Coupland, M. and Stephenson, B. and Crawford, K. and Ball, G.},
volume = {27},
journal = {international journal of mathematical education in science and technology}}
@inproceedings{studeny98bayesian,
year = {1998},
pages = {496-503},
title = {Bayesian Networks from the Point of View of Chain Graphs},
author = {Milan Studeny},
booktitle = {Proceedings of the Fourteenth Conference on Uncertainty in Artificial Intelligence (UAI-98)},
publisher = {Morgan Kaufmann, San Francisco, CA}}
@inproceedings{studeny92conditional,
year = {1992},
pages = {377-396},
title = {Conditional Independence Relations Have No Finite Complete Characterization},
author = {Milan Studeny},
booktitle = {Information Theory, Statistical Decision Functions and Random Processes. Transactions of the 11th Prague Conference vol. B},
publisher = {Kluwer, Dordrecht - Boston - London (also Academia, Prague)}}
@inproceedings{shpitser10on,
year = {2010},
pages = {527-536},
title = {On the Validity of Covariate Adjustment for Estimating Causal Effects},
author = {Ilya Shpitser and Tyler VanderWeele and James M. Robins},
booktitle = {Proceedings of the Twenty Sixth Conference on Uncertainty in Artificial Intelligence (UAI-10)},
publisher = {AUAI Press}}
@inproceedings{galbraith01conceptual,
year = {2001},
pages = {342-353},
title = {Conceptual and procedural demands embedded in modelling tasks},
author = {Galbraith, P. and Haines, C.},
booktitle = {Modelling and mathematics education: ICTMA9: applications in science and technology},
publisher = {Chichester, England: Horwood publishing}}
@book{polya81math,
year = {1981},
title = {Mathematical discovery},
author = {P\'olya, G.},
publisher = {New York: John Wiley \& Sons}}
@article{kadijevich99conceptual,
year = {1999},
pages = {59-64},
title = {Conceptual tasks in mathematical education},
author = {Kadijevich, Dj},
number = {1},
volume = {2},
journal = {The teaching of mathematics}}
@book{mullis01timss,
year = {2001},
title = {TIMSS assessment frameworks and specifications 2003},
author = {I.V.S. Mullis and M.O. Martin and T.A. Smith and R.A. Garden and K.D. Gregory and E.J. Gonzalez and S.J. Chrostowski and K.M. O'Connor},
publisher = {Chestnut Hill, MA: International Study Center, Boston College}}
@book{rubin87multiple,
year = {1987},
title = {Multiple Imputation for Nonresponse in Surveys},
author = {D. B. Rubin},
publisher = {New York: Wiley \& Sons}}
@book{freeman98planning,
year = {1998},
title = {Planning and implementing assessment.},
author = {Freeman, R. and Lewis, R.},
publisher = {London: Kogan Page}}
@article{kilpatrick93chain,
year = {1993},
pages = {31-46},
title = {The chain and the arrow: from the history of mathematics assessment.},
author = {Kilpatrick, J.},
journal = {Investigations into mathematics education: an ICMI study}}
@article{brickhouse00what,
year = {2000},
pages = {441-458},
title = {What Kind of a Girl Does Science? The Construction of School Science Identities},
author = {Nancy W. Brickhouse and Patricia Lowery and Katherine Schultz},
number = {5},
volume = {37},
journal = {Journal of Research in Science Teaching}}
@article{chinn02asian,
year = {2002},
pages = {302-323},
title = {Asian and Pacific Islander Women Scientists and Engineers: A Narrative Exploration of Model Minority, Gender, and Racial Stereotypes},
author = {Pauline W.U. Chinn},
number = {4},
volume = {39},
journal = {Journal of Research in Science Teaching}}
@article{plucker96secondary,
year = {1996},
pages = {737-751},
title = {Secondary Science and Mathematics Teachers and Gender Equity: Attitudes and Attempted Interventions},
author = {Jonathan A. Plucker},
number = {7},
volume = {33},
journal = {Journal of Research in Science Teaching}}
@article{labudde00girls,
year = {2000},
title = {{G}irls and physics: teaching and learning strategies tested by classroom interventions in grade 11},
author = {Peter Labudde and Walter Herzog and Markus P. Neuenschwander and Enrico Violi and Charlotte Gerber},
number = {2},
volume = {22},
journal = {International Journal of Science Education}}
@article{brotman08girls,
year = {2008},
pages = {971--1002},
title = {Girls and Science: A Review of Four Themes in the Science Education Literature},
author = {Jennie S. Brotman and Felicia M. Moore},
number = {9},
volume = {45},
journal = {Journal of Research in Science Teaching}}
@article{imai10id,
year = {2010},
pages = {1-144},
title = {Identification, Inference and Sensitivity Analysis for Causal Mediation Effects},
author = {Kosuke Imai and Luke Keele and Teppei Yamamoto},
number = {1},
volume = {25},
journal = {Statistical Science}}
@article{thomas13swig,
year = {2013},
title = {Single World Intervention Graphs ({SWIG}s): A Unification of the Counterfactual and Graphical Approaches to Causality},
author = {Thomas S. Richardson and Jamie M. Robins},
journal = {preprint: \url{http://www.csss.washington.edu/Papers/wp128.pdf}}}
@article{tyler13on,
year = {2013},
pages = {196-220},
title = {On the Definition of a Confounder},
author = {Tyler J VanderWeele and Ilya Shpitser},
number = {1},
volume = {41},
journal = {Annals of Statistics}}
@article{van2006targeted,
year = {2006},
pages = {Article 11},
title = {Targeted maximum likelihood learning},
author = {van Der Laan, Mark J and Rubin, Daniel},
number = {1},
volume = {2},
journal = {The International Journal of Biostatistics},
publisher = {De Gruyter}}
@article{holland86statistics,
year = {1986},
issue = {396},
pages = {945-960},
title = {Statistics and Causal Inference},
author = {Paul W. Holland},
volume = {81},
journal = {Journal of the American Statistical Association}}
@article{robins94estimation,
year = {1994},
pages = {846-866},
title = {Estimation of regression coefficients when some regressors are not always observed},
author = {James M. Robins and Andrea Rotnitzky and Lue P. Zhao},
volume = {89},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis, Milton Park}}
@article{robins87graphical,
year = {1987},
issue = {2},
pages = {139-161},
title = {A graphical approach to the identification and estimation of causal parameters in mortality studies with sustained exposure periods},
author = {J. M. Robins},
volume = {40},
journal = {Journal of Chronic Diseases}}
@article{horvitz52weights,
year = {1952},
pages = {663-685},
title = {A generalization of sampling without replacement from a finite universe},
author = {D. G. Horvitz and D. J. Thompson},
volume = {47},
journal = {Journal of the American Statistical Association}}
@article{rosenbaum83propensity,
year = {1983},
issue = {1},
pages = {41-55},
title = {The central role of the propensity score in observational studies for causal effects},
author = {Paul R. Rosenbaum and Donald B. Rubin},
volume = {70},
journal = {Biometrika}}
@article{shpitser13cogsci,
year = {2013},
issue = {6},
pages = {1011-1035},
title = {Counterfactual Graphical Models for Longitudinal Mediation Analysis With Unobserved Confounding},
author = {Ilya Shpitser},
volume = {37},
journal = {Cognitive Science ({R}umelhart special issue)}}
@article{tchetgen12semi2,
year = {2012},
title = {Semiparametric theory for causal mediation analysis: efficiency bounds, multiple robustness, and sensitivity analysis},
author = {Eric J. Tchetgen Tchetgen and Ilya Shpitser},
journal = {Annals of Statistics (in Press)}}
@inproceedings{robins99marginal,
year = {1999},
title = {Marginal Structural Models versus Structural Nested Models as Tools for Causal Inference},
author = {J. M. Robins},
editors = {M.E. Halloran and D. Berry},
booktitle = {Statistical Models in Epidemiology: The Environment and Clinical Trials},
publisher = {NY: Springer-Verlag}}
@article{robins00marginal,
year = {2000},
pages = {550-560},
title = {Marginal structural models and causal inference in epidemiology},
author = {James M. Robins and Miguel Hernan and Babette Brumback},
volume = {11(5)},
journal = {Epidemiology},
publisher = {Wolters Kluwer, Alphen aan den Rijn}}
@article{imai13experimental,
year = {2013},
title = {Experimental Designs for Identifying Causal Mechanisms},
author = {Kosuke Imai and Dustin Tingley and Teppei Yamamoto},
volume = {176(1)},
journal = {Journal of the Royal Statistical Society, series (A)}}
@article{word74nonverbal,
year = {1974},
pages = {109-120},
title = {The nonverbal mediation of self-fulfilling prophecies in interracial interaction},
author = {C.O. Word and M.P. Zanna and J. Cooper},
volume = {10},
journal = {Journal of Experimental Social Psychology}}
@article{mackinnon95simulation,
year = {1995},
pages = {41-65},
title = {A simulation study of mediated effect measures},
author = {D. P. MacKinnon and D. P. Warsi and J.H. Dwyer},
volume = {30},
journal = {Multivariate Behavioral Research}}
@article{mackinnon93estimating,
year = {1993},
pages = {144-158},
title = {Estimating mediated effects in prevention studies},
author = {D.P. MacKinnon and J.H. Dwyer},
volume = {17(2)},
journal = {Evaluation Review}}
@article{kaufman04further,
year = {2004},
pages = {1-13},
title = {A further critique of the analytic strategy of adjusting for covariates to identify biologic mediation},
author = {Jay S. Kaufman and Richard F. MacLehose and Sol Kaufman},
volume = {1:4},
journal = {Epidemiologic Perspectives and Innovations}}
@article{tyler09conceptual,
year = {2009},
pages = {457-468},
title = {Conceptual issues concerning mediation, intervention, and composition},
author = {T. J. VanderWeele and S. Vansteelandt},
volume = {2},
journal = {Statistics and Its Interface (Special Issue on Mental Health and Social Behavioral Science)}}
@article{tyler12genetic,
year = {2012},
pages = {1013-1020},
title = {Genetic Variants on 15q25.1, Smoking, and Lung Cancer: An Assessment of Mediation and Interaction},
author = {Tyler J. VanderWeele and Kofi Asomaning and Eric J. Tchetgen Tchetgen and Younghun Han and Margaret R. Spitz and Sanjay Shete and Xifeng Wu and Valerie Gaborieau and Ying Wang and John McLaughlin and Rayjean J. Hung and Paul Brennan and Christopher I. Amos and David C. Christiani and Xihong Lin},
volume = {175(10)},
journal = {American Journal of Epidemiology}}
@article{doll50smoking,
year = {1950},
pages = {739-748},
title = {Smoking and Carcinoma of the Lung},
author = {R. Doll and A. B. Hill},
volume = {2},
journal = {BMJ}}
@article{sobel06what,
year = {2006},
pages = {1398-1407},
title = {What do randomized studies of housing mobility demonstrate? Causal inference in the face of interference},
author = {Michael E. Sobel},
volume = {101.476},
journal = {Journal of the American Statistical Association}}
@article{rucker11mediation,
year = {2011},
pages = {359-371},
title = {Mediation Analysis in Social Psychology: Current Practices and New Recommendations},
author = {Derek D. Rucker and Kristopher J. Preacher and Zakary L. Tormala and Richard E. Petty},
volume = {5/6},
journal = {Social and Personality Psychology Compass}}
@article{richardson03markov,
year = {2003},
pages = {145-157},
title = {Markov properties for acyclic directed mixed graphs},
author = {Thomas S. Richardson},
number = {1},
volume = {30},
journal = {Scandinavial Journal of Statistics}}
@unpublished{richardson11generalized,
note = {Unpublished manuscript},
year = {2011},
title = {Generalized {M}arkov Models Associated with Acyclic Directed Mixed Graphs},
author = {Thomas S. Richardson and James M. Robins and Ilya Shpitser}}
@inproceedings{richardson12nested,
year = {2012},
title = {Nested {M}arkov Properties for Acyclic Directed Mixed Graphs},
author = {Thomas S. Richardson and James M. Robins and Ilya Shpitser},
booktitle = {Twenty Eighth Conference on Uncertainty in Artificial Intelligence (UAI-12)}}
@inproceedings{zhang94simple,
year = {1994},
pages = {171-178},
title = {A Simple approach to {B}ayesian network computations},
author = {N.L. Zhang and D. Poole},
booktitle = {Tenth Canadian Conference on AI}}
@inproceedings{shpitser08dormant,
year = {2008},
title = {Dormant Independence},
author = {Ilya Shpitser and Judea Pearl},
volume = {23},
booktitle = {Conference on Artificial Intelligence},
publisher = {AAAI Press}}
@inproceedings{shpitser11eid,
year = {2011},
title = {An efficient algorithm for computing interventional distributions in latent variable causal models},
author = {Ilya Shpitser and Thomas S. Richardson and James M. Robins},
volume = {27},
booktitle = {Uncertainty in Artificial Intelligence},
publisher = {AUAI Press}}
@book{r04book,
url = {www.R-project.org},
year = {2004},
title = {R: A language and environment for statistical computing},
author = {{R Development Core Team}},
publisher = {Vienna: R Foundation for Statistical Computing},
Bdsk-Url-1 = {www.R-project.org}}
@book{mackinnon08mediation,
year = {2008},
title = {Statistical Mediation Analysis},
author = {David P. Mackinnon},
publisher = {New York: Tailor and Francisc Group}}
@article{robins10alternative,
year = {2010},
title = {Alternative graphical causal models and the identification of direct effects},
author = {James M. Robins and Thomas S. Richardson},
journal = {Causality and Psychopathology: Finding the Determinants of Disorders and their Cures},
publisher = {P. Shrout, Editor. Oxford University Press}}
@article{baron86mm,
year = {1986},
pages = {1173-1182},
title = {The Moderator-Mediator Variable Distinction in Social Psychology Research: Conceptual, Strategic, and Statistical Considerations},
author = {Reuben M. Baron and David A. Kenny},
volume = {51},
journal = {Journal of Personality and Social Psychology}}
@article{judd81process,
year = {1981},
pages = {602-619},
title = {Process analysis: Estimating mediation in treatment evaluation.},
author = {C. M. Judd and D. A. Kenny},
volume = {5},
journal = {Evaluation Review}}
@article{woodworth28dynamic,
year = {1928},
title = {Dynamic Psychology},
author = {R. S. Woodworth},
journal = {Psychologies of 1925. C. Murchison (ed.)},
publisher = {Worcester, MA: Clark University Press}}
@article{kennes91moebius,
year = {1991},
pages = {201-223},
title = {Computational aspects of the Moebius transform of a graph},
author = {R. Kennes},
volume = {22},
journal = {IEEE Transactions on Systems, Man, and Cybernetics}}
@article{richardson02ancestral,
year = {2002},
pages = {962-1030},
title = {Ancestral graph {M}arkov models},
author = {Thomas Richardson and Peter Spirtes},
volume = {30},
journal = {Annals of Statistics}}
@article{ali09equiv,
year = {2009},
pages = {2808-2837},
title = {Markov equivalence for ancestral graphs},
author = {Ayesha Ali and Thomas S. Richardson and Peter Spirtes},
volume = {37},
journal = {Annals of Statistics}}
@article{drton08binary,
year = {2008},
pages = {287-309},
title = {Binary models for marginal independence},
author = {Drton, M. and T.S. Richardson},
volume = {70(2)},
journal = {J. Roy. Statist. Soc. Ser. B}}
@article{chickering02ges,
year = {2002},
pages = {507-554},
title = {Optimal Structure Identifiation with Greedy Search},
author = {David Maxwell Chickering},
volume = {3},
journal = {Journal of Machine Learning Research}}
@article{schwarz78bic,
year = {1978},
pages = {461-464},
title = {Estimating the dimension of a model},
author = {Gideon E. Schwarz},
volume = {6},
journal = {Annals of Statistics}}
@inproceedings{kelly10flip,
year = {2010},
title = {Causal conclusions that flip repeatedly and their justification},
author = {Kevin T. Kelly and Conor Mayo-Wilson},
booktitle = {26th Conference on Uncertainty in Artificial Intelligence}}
@inproceedings{richardson09factorization,
year = {2009},
title = {A factorization criterion for acyclic directed mixed graphs},
author = {Thomas S. Richardson},
booktitle = {25th Conference on Uncertainty in Artificial Intelligence}}
@inproceedings{geiger90graphoids,
year = {1990},
title = {Separable and Transitive Graphoids},
author = {Dan Geiger and David Heckerman},
booktitle = {Conference on Uncertainty in Artificial Intelligence}}
@inproceedings{tian09parameter,
year = {2009},
pages = {1970-1975},
title = {Parameter identification in a class of linear structural equation models},
author = {Jin Tian},
booktitle = {Proceedings of the Twenty-first International Joint Conference on Artificial Intelligence (IJCAI)},
publisher = {AAAI Press, Palo Alto, CA}}
@inproceedings{tian08dynamic,
year = {2008},
pages = {554--561},
title = {Identifying Dynamic Sequential Plans},
author = {Jin Tian},
address = {Corvallis, Oregon},
booktitle = {Proceedings of the Twenty-Fourth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-08)},
publisher = {AUAI Press}}
@inproceedings{chickering02finding,
year = {2002},
pages = {94--102},
title = {Finding Optimal Bayesian Networks},
author = {David Chickering and Christopher Meek},
address = {San Francisco, CA},
booktitle = {Proceedings of the Eighteenth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-02)},
publisher = {Morgan Kaufmann}}
@inproceedings{friedman97learning,
year = {1997},
pages = {125--133},
title = {Learning Belief Networks in the Presence of Missing Values and Hidden Variables},
author = {Nir Friedman},
booktitle = {Proceedings of the Fourteenth International Conference on Machine Learning {(ICML} 1997), Nashville, Tennessee, USA, July 8-12, 1997}}
@inproceedings{shpitser09edge,
year = {2009},
pages = {1957-1963},
title = {Testing Edges by Truncations},
author = {Ilya Shpitser and Thomas S. Richardson and James M. Robins},
volume = {21},
booktitle = {International Joint Conference on Artificial Intelligence}}
@article{cai08bounds,
year = {2008},
pages = {695 - 701},
title = {Bounds on Direct Effects in the Presence of Confounded Intermediate Variables},
author = {Zhihong Cai and Manabu Kuroki and Judea Pearl and Jin Tian},
volume = {64},
journal = {Biometrics}}
@article{frydenberg90chain,
year = {1990},
pages = {333 - 353},
title = {The Chain Graph Markov Property},
author = {Morten Frydenberg},
volume = {17},
journal = {Scandinavian Journal of Statistics}}
@article{studeny98chain,
year = {1998},
pages = {1434-1495},
title = {On Chain Graph Models for Description of Conditional Independence Structures},
author = {Milan Studeny and Remco R. Bouckaert},
number = {4},
volume = {26},
journal = {The Annals of Statistics}}
@article{amp97characterization,
year = {1997},
pages = {505--541},
title = {A characterization of {M}arkov equivalence classes for acyclic digraphs},
author = {Steen A. Andersson and David Madigan and Michael D. Perlman},
volume = {25},
journal = {Annals of Statistics}}
@inproceedings{pearl85constraint,
year = {1985},
pages = {31-42},
title = {A Constraint-Propagation Approach to Probabilistic Reasoning},
author = {Judea Pearl},
booktitle = {Uncertainty in Artificial Intelligence (UAI)}}
@inproceedings{pearl94calculus,
year = {1993},
pages = {454-462},
title = {A probabilistic calculus of actions},
author = {Judea Pearl},
volume = {10},
booktitle = {Uncertainty in Artificial Intelligence (UAI)}}
@article{pearl86fusion,
year = {1986},
pages = {241-288},
title = {Fusion, propagation, and structuring in belief networks},
author = {Judea Pearl},
volume = {29},
journal = {Artificial Intelligence}}
@article{lauritzen88local,
year = {1988},
pages = {157-224},
title = {Local computations with probabilities on graphical structures and their application to expert systems},
author = {Steffan L. Lauritzen and David J. Spiegelhalter},
volume = {Ser. B 50},
journal = {Journal of the Royal Statistical Society}}
@article{pearl93comment,
year = {1993},
pages = {266-269},
title = {Comment: Graphical Models, Causality, and Intervention},
author = {Judea Pearl},
number = {3},
volume = {8},
journal = {Statistical Science}}
@article{pearl93belief,
year = {1993},
pages = {49-56},
title = {Belief Networks Revisited},
author = {Judea Pearl},
volume = {59},
journal = {Artificial Intelligence}}
@techreport{tchetgen12semi,
year = {2012},
title = {Semiparametric estimation of models for natural direct and indirect effects},
author = {Eric J. Tchetgen Tchetgen and Ilya Shpitser},
number = {129},
institution = {Department of Biostatistics, Harvard School of Public Health}}
@techreport{pearl11cmf,
year = {2011},
title = {The causal mediation formula -- a guide to the assessment of pathways and mechanisms},
author = {Judea Pearl},
number = {R-379},
institution = {Cognitive Systems Laboratory, University of California, Los Angeles}}
@techreport{verma88influence,
year = {1988},
title = {Influence Diagrams and d-Separation},
author = {T. Verma and Judea Pearl},
number = {R-101},
institution = {Cognitive Systems Laboratory, University of California, Los Angeles}}
@techreport{shpitser07appendum,
year = {2007},
title = {Appendum to Identification of Conditional Interventional Distributions},
author = {Ilya Shpitser},
number = {R-329-APPENDUM},
institution = {Cognitive Systems Laboratory, University of California, Los Angeles}}
@techreport{verma86causal,
year = {1986},
title = {Causal networks: semantics and expressiveness},
author = {Thomas S. Verma},
number = {R-65},
institution = {Cognitive Systems Laboratory, University of California, Los Angeles}}
@techreport{verma90equiv,
year = {1990},
title = {Equivalence and Synthesis of Causal Models},
author = {Thomas S. Verma and Judea Pearl},
number = {R-150},
institution = {Department of Computer Science, University of California, Los Angeles}}
@inproceedings{suzuki93mdl,
year = {1993},
pages = {266-273},
title = {A construction of Bayesian networks from databases based on an MDL scheme},
author = {J. Suzuki},
booktitle = {UAI 93}}
@inproceedings{shpitser06id,
year = {2006},
title = {Identification of Joint Interventional Distributions in Recursive Semi-{M}arkovian Causal Models},
author = {Ilya Shpitser and Judea Pearl},
booktitle = {Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI-06)},
publisher = {AAAI Press, Palo Alto},
institution = {Department of Computer Science, University of California, Los Angeles}}
@inproceedings{shpitser06idc,
year = {2006},
pages = {437-444},
title = {Identification of Conditional Interventional Distributions},
author = {Ilya Shpitser and Judea Pearl},
booktitle = {Proceedings of the Twenty Second Conference on Uncertainty in Artificial Intelligence (UAI-06)},
publisher = {AUAI Press, Corvallis, Oregon},
institution = {Department of Computer Science, University of California, Los Angeles}}
@inproceedings{huang06do,
year = {2006},
title = {Pearl's Calculus of Interventions is Complete},
author = {Yimin Huang and Marco Valtorta},
booktitle = {Twenty Second Conference On Uncertainty in Artificial Intelligence},
institution = {Computer Science and Engineering Department, University of South Carolina}}
@inproceedings{jordan02graphical,
year = {2002},
title = {Graphical Models: Probabilistic Inference},
author = {M. I. Jordan and Y. Weiss},
editor = {M. Arbib},
booktitle = {The Handbook of Brain Theory and Neural Networks, 2nd edition},
publisher = {Cambridge, MA: MIT Press}}
@inproceedings{huang06ident,
year = {2006},
title = {Identifiability in Causal Bayesian Networks: A Sound and Complete Algorithm},
author = {Yimin Huang and Marco Valtorta},
booktitle = {Twenty-First National Conference on Artificial Intelligence},
institution = {Computer Science and Engineering Department, University of South Carolina}}
@inproceedings{pearl01direct,
year = {2001},
pages = {411-420},
title = {Direct and Indirect Effects},
author = {Judea Pearl},
booktitle = {Proceedings of the Seventeenth Conference on Uncertainty in Artificial Intelligence (UAI-01)},
publisher = {Morgan Kaufmann, San Francisco}}
@inproceedings{verma91theory,
year = {1991},
pages = {441-452},
title = {A Theory of Inferred Causation},
author = {Judea Pearl and Thomas S. Verma},
booktitle = {Principles of Knowledge Representation and Reasoning: Proceedings of the Second International Conference}}
@inproceedings{chen05ijcai,
year = {2005},
pages = {357-363},
title = {Identifiability of Path-Specific Effects},
author = {Chen Avin and Ilya Shpitser and Judea Pearl},
volume = {19},
booktitle = {Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence (IJCAI-05)},
publisher = {Morgan Kaufmann, San Francisco}}
@inproceedings{pearl95seq,
year = {1995},
pages = {444-453},
title = {Probabilistic Evaluation of Sequential Plans from Causal Models with Hidden Variables},
author = {Judea Pearl and J. M. Robins},
volume = {11},
booktitle = {Uncertainty in Artificial Intelligence}}
@article{lam94mdl,
year = {1994},
title = {Learning Bayesian Belief Networks: An Approach Based on the {MDL} Principle},
author = {Lam, Wai and Bacchus, Fahiem},
number = {4},
volume = {10},
journal = {Computational Intelligence}}
@article{bickel75discrimination,
year = {1975},
pages = {398-404},
title = {Sex bias in graduate admissions: Data from Berkeley},
author = {P.J. Bickel, E.A Hammel, J.W. O'Connell},
volume = {187},
journal = {Science}}
@article{dejong02review,
year = {2002},
pages = {67-103},
title = {Modeling and Simulation of Genetic Regulatory Systems: A Literature Review},
author = {Hidde de Jong},
volume = {9},
journal = {Journal of Computational Biology}}
@article{kalman60filter,
year = {1960},
pages = {35-45},
title = {A New Approach to Linear Filter and Prediction Problems},
author = {R. E. Kalman},
volume = {82},
journal = {Transactions of the ASME - Journal of Basic Engineering}}
@article{besag74spatial,
year = {1974},
pages = {192-236},
title = {Spatial Interaction and the Statistical Analysis of Lattice Systems},
author = {J. Besag},
volume = {36},
journal = {Journal of the Royal Statistical Society}}
@article{robins86new,
year = {1986},
pages = {1393-1512},
title = {A new approach to causal inference in mortality studies with sustained exposure periods -- Application to control of the healthy worker survivor effect},
author = {J. M. Robins},
volume = {7},
journal = {Mathematical Modeling}}
@article{robins87g,
year = {1987},
pages = {139-161},
title = {A Graphical Approach to the Identification and Estimation of Causal Parameters in Mortality Studies with Sustained Exposure Periods},
author = {J. M. Robins},
volume = {2},
journal = {Journal of Chronic Disease}}
@article{dawid79cond,
year = {1979},
pages = {1-31},
title = {Conditional Independence in Statistical Theory},
author = {A. Philip Dawid},
volume = {41},
journal = {Journal of the Royal Statistical Society}}
@article{kuroki99jjsc,
year = {1999},
pages = {105-117},
title = {Identifiability Criteria for Causal Effects of Joint Interventions},
author = {Manabu Kuroki and Masami Miyakawa},
volume = {29},
journal = {Journal of Japan Statistical Society}}
@article{goldberger72sem,
year = {1972},
pages = {979-1001},
title = {Structural Equation Models in the Social Sciences},
author = {Goldberger, A. S.},
volume = {40},
journal = {Econometrika}}
@article{pearl95causal,
url = {citeseer.ist.psu.edu/55450.html},
year = {1995},
pages = {669--709},
title = {Causal Diagrams for Empirical Research},
author = {Judea Pearl},
number = {4},
volume = {82},
journal = {Biometrika},
Bdsk-Url-1 = {citeseer.ist.psu.edu/55450.html}}
@article{neyman23app,
year = {1923},
pages = {463-472},
title = {Sur les applications de la thar des probabilities aux experiences Agaricales: Essay des principle. Excerpts reprinted (1990) in {E}nglish},
author = {Jerzy Neyman},
volume = {5},
journal = {Statistical Science}}
@article{rubin04direct,
year = {2004},
pages = {161-170},
title = {Direct and indirect causal effects via potential outcomes},
author = {Donald B. Rubin},
volume = {31},
journal = {Scandinavian Journal of Statistics}}
@article{rubin05causal,
year = {2005},
pages = {322-331},
title = {Causal inference using potential outcomes: design, modeling, decisions},
author = {Donald B. Rubin},
volume = {100},
journal = {Journal of the American Statistical Association}}
@article{rubin74potential,
year = {1974},
pages = {688-701},
title = {Estimating causal effects of treatments in randomized and non-randomized studies},
author = {Donald B. Rubin},
volume = {66},
journal = {Journal of Educational Psychology}}
@article{hernan2006estimating,
year = {2006},
pages = {578--586},
title = {Estimating causal effects from epidemiological data},
author = {Hern{\'a}n, Miguel A and Robins, James M},
number = {7},
volume = {60},
journal = {Journal of Epidemiology \& Community Health},
publisher = {BMJ Publishing Group Ltd}}
@article{dawid00criticism,
year = {2000},
pages = {407-448},
title = {Causal Inference without Counterfactuals},
author = {A Philip Dawid},
volume = {95},
journal = {Journal of the American Statistical Association}}
@inproceedings{robins97estimation,
year = {1997},
pages = {309-420},
title = {Estimation of Effects of Sequential Treatments by Reparameterizing Directed Acyclic Graphs},
author = {James M. Robins and Larry Wasserman},
booktitle = {Proceedings of the 13th Conference on Uncertainty in Artificial Intelligence},
publisher = {Morgan Kaufmann}}
@inproceedings{robins97longitudinal,
year = {1997},
pages = {69-117},
title = {Causal Inference from Complex Longitudinal Data},
author = {James M. Robins},
volume = {120},
booktitle = {Latent Variable Modeling and Applications to Causality}}
@article{robins92effects,
year = {1992},
pages = {143-155},
title = {Identifiability and Exchangeability of Direct and Indirect Effects},
author = {James M. Robins and Sander Greenland},
volume = {3},
journal = {Epidemiology}}
@article{roweis99generative,
year = {1999},
pages = {305-345},
title = {A Unifying Review of Linear Gaussian Models},
author = {Sam Roweis and Zoubin Ghahramani},
volume = {11},
journal = {Neural Computation}}
@article{halpern90probability,
doi = {http://dx.doi.org/10.1016/0004-3702(90)90019-V},
issn = {0004-3702},
year = {1990},
pages = {311--350},
title = {An analysis of first-order logics of probability},
author = {Joseph Y. Halpern},
number = {3},
volume = {46},
journal = {Artificial Intelligence},
Bdsk-Url-1 = {http://dx.doi.org/10.1016/0004-3702(90)90019-V}}
@book{tinbergen37econometric,
year = {1937},
title = {An Econometric Approach to Business Cycle Problems},
author = {J. Tinbergen},
publisher = {Hermann, Paris}}
@book{lauritzen96graphical,
year = {1996},
title = {Graphical Models},
author = {Steffan L. Lauritzen},
publisher = {Oxford, U.K.: Clarendon}}
@book{lewis73cntfcts,
year = {1973},
title = {Counterfactuals},
author = {D. Lewis},
publisher = {Cambridge, MA: Harvard University Press}}
@book{fisher51design,
year = {1926},
title = {The Design of Experiments},
author = {R. A. Fisher},
publisher = {6th edition. Edinburgh, U.K.: Oliver and Boyd}}
@book{kline05sem,
year = {2005},
title = {Principles and Practice of Structural Equation Modeling},
author = {R. B. Kline},
publisher = {The Guilford Press}}
@book{baxter92exact,
year = {1992},
title = {Exactly Solved Models in Statistical Mechanics},
author = {R. J. Baxter},
publisher = {Academic Press, London}}
@book{kunen80set,
year = {1980},
title = {Set Theory: an Introduction to Independence Proofs},
author = {Kenneth Kunen},
publisher = {North Holland}}
@book{fraenkel58set,
year = {1958},
title = {Foundations of Set Theory},
author = {Abraham Fraenkel, Yehoshua Bar-Hillel, Azriel Levy},
publisher = {North Holland}}
@book{goedel40ch,
year = {1940},
title = {The Consistency of the Continuum Hypothesis},
author = {Kurt Goedel},
publisher = {Princeton}}
@book{cohen66set,
year = {1966},
title = {Set Theory and the Continuum Hypothesis},
author = {Paul J. Cohen},
publisher = {WA Benjamin}}
@book{pearl88probabilistic,
year = {1988},
title = {Probabilistic Reasoning in Intelligent Systems},
author = {Judea Pearl},
publisher = {Morgan and Kaufmann, San Mateo}}
@book{cartwright83physics,
year = {1983},
title = {How the Laws of Physics Lie},
author = {Nancy Cartwright},
publisher = {Oxford, U.K.: Clarendon}}
@article{evans13marginal,
year = {2013},
pages = {743-768},
title = {Marginal log-linear parameters for graphical {M}arkov models},
author = {Robin J. Evans and Thomas S. Richardson},
number = {4},
volume = {75},
journal = {Journal of the Royal Statistical Society: Series B}}
@phdthesis{evans11parameterizations,
year = {2011},
title = {Parameterizations of Discrete Graphical Models},
author = {Robin J. Evans},
school = {Department of statistics, University of Washington}}
@phdthesis{tian02studies,
year = {2002},
title = {Studies in Causal Reasoning and Learning},
author = {Jin Tian},
school = {Department of Computer Science, University of California, Los Angeles}}
@book{pearl09causality,
isbn = {978-0521895606},
year = {2009},
title = {Causality: Models, Reasoning, and Inference},
author = {Judea Pearl},
publisher = {Cambridge University Press}}
@book{pearl00causality,
isbn = {0-521-77362-8},
year = {2000},
title = {Causality: Models, Reasoning, and Inference},
author = {Judea Pearl},
publisher = {Cambridge University Press}}
@book{spirtes01causation,
isbn = {978-0262194402},
year = {2001},
title = {Causation, Prediction, and Search},
author = {Peter Spirtes and Clark Glymour and Richard Scheines},
edition = {2},
publisher = {Springer Verlag, New York}}
@book{spirtes93causation,
year = {1993},
title = {Causation, Prediction, and Search},
author = {Spirtes, P. and Glymour, C. and Scheines, R.},
publisher = {Springer Verlag, New York}}
@article{pearl98graphs,
year = {1998},
pages = {226--284},
title = {Graphs, causality, and structural equation models},
author = {Judea Pearl},
number = {2},
volume = {27},
journal = {Sociological Methods and Research}}
@article{balke97bounds,
year = {1997},
pages = {1171-1176},
title = {Bounds on treatment effects from studies with imperfect compliance},
author = {Alexander Balke and Judea Pearl},
number = {439},
volume = {92},
journal = {Journal of the American Statistical Association}}
@article{shpitser07hierarchy,
year = {2008},
pages = {1941-1979},
title = {Complete Identification Methods for the Causal Hierarchy},
author = {Ilya Shpitser and Judea Pearl},
volume = {9(Sep)},
journal = {Journal of Machine Learning Research}}
@techreport{halpern00causes,
year = {2000},
title = {Causes and Explanations: A Structural-Model Approach},
author = {Joseph Halpern and Judea Pearl},
number = {R--266},
institution = {UCLA Cognitive Systems Laboratory}}
@article{halpern00axiom,
year = {2000},
pages = {317-337},
title = {Axiomatizing Causal Reasoning},
author = {Joseph Halpern},
volume = {12},
journal = {Journal of A.I. Research}}
@article{halpern01causes,
year = {2001},
pages = {411-420},
title = {Causes and Explanations: A Structural-Model Approach -- Part I: Causes},
author = {Joseph Halpern and Judea Pearl},
journal = {Proceedings of UAI-01}}
@inproceedings{russell95local,
year = {1995},
pages = {1146-1152},
title = {Local learning in probabilistic networks with hidden variables},
author = {Stuart Russell and John Binder and Daphne Koller and Keiji Kanazawa},
booktitle = {Proceedings of the Fourteenth international joint conference on Artificial intelligence (IJCAI-95)},
publisher = {Morgan Kaufmann Publishers Inc. San Francisco, CA, USA}}
@article{peters14causal,
year = {2014},
pages = {2009--2053},
title = {Causal Discovery with Continuous Additive Noise Models},
author = {Jonas Peters and Joris M. Mooij and Dominik Janzing and Bernhard Scholkopf},
journal = {Journal of Machine Learning Research}}
@article{eiter01complexity,
year = {2001},
pages = {35-40},
title = {Complexity Results for Structure-Based Causality},
author = {Thomas Eiter and Thomas Lukasiewicz},
journal = {Proceedings of IJCAI-01}}
@inproceedings{eiter02causes,
year = {2002},
pages = {146-153},
title = {Causes and Explanations in the Structural-Model Approach: Tractable Cases},
author = {Thomas Eiter and Thomas Lukasiewicz},
booktitle = {Proceedings of UAI-02}}
@article{hall98two,
year = {1998},
title = {Two Concepts of Causation},
author = {Ned Hall}}
@article{lin95embracing,
year = {1995},
pages = {1985-1991},
title = {Embracing Causality in Specifying the Indirect Effect of Actions},
author = {F. Lin},
journal = {Proceedings of IJCAI-95}}
@article{mackie65causes,
year = {1965},
pages = {245-255, 261-264},
title = {Causes and Conditions},
author = {John L. Mackie},
number = {4},
volume = {2},
journal = {American Philosophical Quarterly}}
@techreport{mccarthy63situations,
year = {1963},
title = {Situations, Actions, and Causal Laws},
author = {John McCarthy},
institution = {Stanford University}}
@article{pearl99reasoning,
year = {1999},
pages = {1437-1449},
title = {Reasoning with Cause and Effect},
author = {Judea Pearl},
journal = {Proceedings of IJCAI-99}}
@article{haavelmo43simultaneous,
year = {1943},
pages = {1-12},
title = {The statistical implications of a system of simultaneous equations},
author = {Trygve Haavelmo},
volume = {11},
journal = {Econometrica}}
@article{wright21correlation,
year = {1921},
pages = {557-585},
title = {Correlation and Causation},
author = {Sewall Wright},
volume = {20},
journal = {Journal of Agricultural Research}}
@inproceedings{tian04cond,
year = {2004},
title = {Identifying Conditional Causal Effects},
author = {Jin Tian},
booktitle = {Conference on Uncertainty in Artificial Intelligence (UAI)}}
@inproceedings{tian02general,
isbn = {0-262-51129-0},
year = {2002},
pages = {567--573},
title = {A General Identification Condition for Causal Effects},
author = {Jin Tian and Judea Pearl},
booktitle = {Eighteenth National Conference on Artificial Intelligence}}
@inproceedings{brito06graphical,
year = {2006},
pages = {47-54},
title = {Graphical condition for identification in recursive SEM},
author = {Brito, C. and Pearl, J.},
editors = {Dechter, R. and Richardson, T.S., eds.},
booktitle = {Proceedings of the Twenty-Second Conference on Uncertainty in Artificial Intelligence},
publisher = {AUAI Press, Arlington, VA}}
@inproceedings{brito02graphical,
isbn = {0-262-51129-0},
year = {2002},
pages = {533--538},
title = {A graphical criterion for the identification of causal effects in linear models},
author = {Carlos Brito and Judea Pearl},
location = {Edmonton, Alberta, Canada},
booktitle = {Eighteenth national conference on Artificial intelligence},
publisher = {American Association for Artificial Intelligence}}
@inproceedings{shpitser07cnt,
year = {2007},
title = {What Counterfactuals Can Be Tested},
author = {Ilya Shpitser and Judea Pearl},
booktitle = {Twenty Third Conference on Uncertainty in Artificial Intelligence, forthcoming},
publisher = {Morgan Kaufmann},
institution = {Department of Computer Science, Univesity of California, Los Angeles}}
@techreport{tian02onid,
year = {2002},
title = {On the Identification of Causal Effects},
author = {Jin Tian and Judea Pearl},
number = {R-290-L},
institution = {Department of Computer Science, University of California, Los Angeles}}
@techreport{verma93aspects,
year = {1993},
title = {Graphical Aspects of Causal Models},
author = {Thomas S. Verma},
number = {R-101},
institution = {Department of Computer Science, University of California, Los Angeles}}
@inproceedings{evans10maximum,
year = {2010},
title = {Maximum likelihood fitting of acyclic directed mixed graphs to binary data},
author = {Robin J. Evans and Thomas S. Richardson},
volume = {26},
booktitle = {Proceedings of the Twenty Sixth Conference on Uncertainty in Artificial Intelligence}}
@inproceedings{chen14on,
year = {2014},
pages = {2424--2430},
title = {Testable Implications of Linear Structural Equation Models},
author = {Bryant Chen and Jin Tian and Judea Pearl},
booktitle = {Proceedings of the Twenty-Eighth {AAAI} Conference on Artificial Intelligence}}
@inproceedings{chen16identification,
year = {2016},
pages = {1579--1587},
title = {Identification and Overidentification of Linear Structural Equation Models},
author = {Bryant Chen},
volume = {29},
booktitle = {Advances in Neural Information Processing Systems},
publisher = {Curran Associates, Inc.}}
@inproceedings{tian02on,
year = {2002},
pages = {519-527},
title = {On the Testable Implications of Causal Models with Hidden Variables},
author = {Jin Tian and Judea Pearl},
volume = {18},
booktitle = {Proceedings of the Eighteenth Conference on Uncertainty in Artificial Intelligence (UAI-02)},
publisher = {AUAI Press, Corvallis, Oregon}}
@inproceedings{tian00probab,
year = {2000},
pages = {589--598},
title = {Probabilities of Causation: Bounds and Identification},
author = {Jin Tian and Judea Pearl},
booktitle = {Proceedings of UAI-00}}
@inproceedings{Pearl94probab,
year = {1994},
pages = {454-462},
title = {A Probabilistic Calculus of Actions},
author = {Pearl Judea},
booktitle = {Proceedings of UAI-94}}
@inproceedings{balke94countereval,
year = {1994},
pages = {230-237},
title = {Probabilistic Evaluation of Counterfactual Queries},
author = {Alexander Balke and Judea Pearl},
booktitle = {Procedings of the Twelfth Conference on Artificial Intelligence (AAAI-94)},
publisher = {Morgan Kaufmann, San Francisco}}
@inproceedings{balke94counter,
year = {1994},
pages = {46-54},
title = {Counterfactual Probabilities: Computational Methods, Bounds and Applications},
author = {Alexander Balke and Judea Pearl},
booktitle = {Proceedings of UAI-94}}
@article{galles98axiomatic,
year = {1998},
pages = {151-182},
title = {An axiomatic characterization of causal counterfactuals},
author = {David Galles and Judea Pearl},
volume = {3},
journal = {Foundation of Science}}
@inproceedings{galles95testing,
year = {1995},
pages = {185-195},
title = {Testing Identifiability of Causal Effects},
author = {David Galles and Judea Pearl},
booktitle = {Proceedings of UAI-95}}
@inproceedings{rabiner89hmm,
year = {1989},
pages = {257-286},
title = {A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition},
author = {Lawrence R. Rabiner},
volume = {77},
booktitle = {Proceedings of the IEEE}}
@unpublished{evans:complete,
note = {{W}orking paper, \url{https://arxiv.org/abs/1501.02103}},
year = {2015},
title = {Margins of discrete {B}ayesian networks},
author = {Robin J. Evans}}
@inproceedings{balke95counter,
year = {1995},
pages = {11-18},
title = {Counterfactuals and Policy Analysis in Structural Models},
author = {Alexander Balke and Judea Pearl},
booktitle = {Proceedings of UAI-95}}
@incollection{robins2008higher,
year = {2008},
pages = {335--421},
title = {Higher order influence functions and minimax estimation of nonlinear functionals},
author = {Robins, James and Li, Lingling and Tchetgen, Eric and van der Vaart, Aad and others},
booktitle = {Probability and Statistics: Essays in Honor of David A. Freedman},
publisher = {Institute of Mathematical Statistics}}
@article{mukherjee2017semiparametric,
year = {2017},
title = {Semiparametric efficient empirical higher order influence function estimators},
author = {Mukherjee, Rajarshi and Newey, Whitney K and Robins, James M},
journal = {arXiv preprint arXiv:1705.07577}}
@article{robins2009quadratic,
year = {2009},
pages = {227--247},
title = {Quadratic semiparametric von mises calculus},
author = {Robins, James and Li, Lingling and Tchetgen, Eric and van der Vaart, Aad W},
number = {2},
volume = {69},
journal = {Metrika},
publisher = {Springer}}
@article{robins2017minimax,
year = {2017},
pages = {1951--1987},
title = {Minimax estimation of a functional on a structured high-dimensional model},
author = {Robins, James M and Li, Lingling and Mukherjee, Rajarshi and Tchetgen, Eric Tchetgen and van der Vaart, Aad and others},
number = {5},
volume = {45},
journal = {Annals of Statistics},
publisher = {Institute of Mathematical Statistics}}
@article{dorn2021sharp,
year = {2021},
title = {Sharp Sensitivity Analysis for Inverse Propensity Weighting via Quantile Balancing},
author = {Dorn, Jacob and Guo, Kevin},
journal = {arXiv preprint arXiv:2102.04543}}
@article{dorn2021doubly,
year = {2021},
title = {Doubly-Valid/Doubly-Sharp Sensitivity Analysis for Causal Inference with Unmeasured Confounding},
author = {Dorn, Jacob and Guo, Kevin and Kallus, Nathan},
journal = {arXiv preprint arXiv:2112.11449}}
@article{tan2006distributional,
year = {2006},
pages = {1619--1637},
title = {A distributional approach for causal inference using propensity scores},
author = {Tan, Zhiqiang},
number = {476},
volume = {101},
journal = {Journal of the American Statistical Association},
publisher = {Taylor \& Francis}}
@book{hastie2017generalized,
year = {2017},
title = {Generalized Additive Models},
author = {Hastie, Trevor J and Tibshirani, Robert J},
publisher = {Routledge}}
@article{kennedy2022semiparametric,
year = {2022},
title = {Semiparametric doubly robust targeted double machine learning: a review},
author = {Kennedy, Edward H},
journal = {arXiv preprint arXiv:2203.06469}}
@article{yang2018asymptotic,
year = {2018},
pages = {487--493},
title = {Asymptotic inference of causal effects with observational studies trimmed by the estimated propensity scores},
author = {Yang, S and Ding, P},
number = {2},
volume = {105},
journal = {Biometrika},
publisher = {Oxford University Press}}
@article{ZhuZF2010Dimension,
DOI = {10.1198/jasa.2010.tm09666},
ISSN = {0162-1459,1537-274X},
YEAR = {2010},
PAGES = {1455--1466},
TITLE = {Dimension reduction in regressions through cumulative slicing
estimation},
AUTHOR = {Zhu, Li-Ping and Zhu, Li-Xing and Feng, Zheng-Hui},
NUMBER = {492},
VOLUME = {105},
JOURNAL = {Journal of the American Statistical Association},
MRCLASS = {62G08 (62H12 62H25)},
MRNUMBER = {2796563},
MRREVIEWER = {Tianfa\ Xie}}
@article{Masten24,
doi = {10.1080/07350015.2023.2183212},
url = {https://doi.org/10.1080/07350015.2023.2183212},
issn = {0735-0015},
year = {2024},
month = {Jan},
pages = {1-13},
title = {Assessing Sensitivity to Unconfoundedness: Estimation and Inference},
author = {Matthew A. Masten, Alexandre Poirier, Linqi Zhang},
number = {1},
volume = {42},
journal = {Journal of Business & Economic Statistics},
publisher = {Informa UK Limited}}
@article{Ding2016,
doi = {10.1097/ede.0000000000000457},
url = {https://doi.org/10.1097/ede.0000000000000457},
issn = {1044-3983},
year = {2016},
month = {May},
pages = {368-377},
title = {Sensitivity Analysis Without Assumptions},
author = {Peng Ding, Tyler J. VanderWeele},
number = {3},
volume = {27},
journal = {Epidemiology},
publisher = {Ovid Technologies (Wolters Kluwer Health)}}
@article{Hammond1958,
doi = {10.1001/jama.1958.02990110030007},
url = {https://doi.org/10.1001/jama.1958.02990110030007},
issn = {0002-9955},
year = {1958},
month = {Mar},
pages = {1294},
title = {SMOKING AND DEATH RATES—REPORT ON FORTY-FOUR MONTHS OF FOLLOW-UP OF 187,783 MEN},
author = {E. Cuyler Hammond},
number = {11},
volume = {166},
journal = {Journal of the American Medical Association},
publisher = {American Medical Association (AMA)}}
@article{Mathur2018,
doi = {10.1097/ede.0000000000000864},
url = {https://doi.org/10.1097/ede.0000000000000864},
issn = {1044-3983},
year = {2018},
month = {Sep},
pages = {e45-e47},
title = {Web Site and R Package for Computing E-values},
author = {Maya B. Mathur, Peng Ding, Corinne A. Riddell, Tyler J. VanderWeele},
number = {5},
volume = {29},
journal = {Epidemiology},
publisher = {Ovid Technologies (Wolters Kluwer Health)}}
@article{Linden2020,
doi = {10.1177/1536867x20909696},
url = {https://doi.org/10.1177/1536867x20909696},
issn = {1536-867X},
year = {2020},
month = {Mar},
pages = {162-175},
title = {Conducting sensitivity analysis for unmeasured confounding in observational studies using E-values: The evalue package},
author = {Ariel Linden, Maya B. Mathur, Tyler J. VanderWeele},
number = {1},
volume = {20},
journal = {The Stata Journal: Promoting communications on statistics and Stata},
publisher = {SAGE Publications}}
@article{Masten18,
doi = {10.3982/ecta14481},
url = {https://doi.org/10.3982/ecta14481},
issn = {0012-9682},
year = {2018},
pages = {317-351},
title = {Identification of Treatment Effects Under Conditional Partial Independence},
author = {Matthew A. Masten, Alexandre Poirier},
number = {1},
volume = {86},
journal = {Econometrica},
publisher = {The Econometric Society}}
@article{Cattaneo10,
doi = {10.1016/j.jeconom.2009.09.023},
url = {https://doi.org/10.1016/j.jeconom.2009.09.023},
issn = {0304-4076},
year = {2010},
month = {Apr},
pages = {138--154},
title = {Efficient semiparametric estimation of multi-valued treatment effects under
ignorability},
author = {Matias D. Cattaneo},
number = {2},
volume = {155},
journal = {Journal of Econometrics},
publisher = {Elsevier BV}}
@article{Almond5,
doi = {10.1093/qje/120.3.1031},
url = {https://doi.org/10.1093/qje/120.3.1031},
issn = {0033-5533},
year = {2005},
month = {Aug},
pages = {1031-1083},
title = {The Costs of Low Birth Weight},
author = {D. Almond, K. Y. Chay, D. S. Lee},
number = {3},
volume = {120},
journal = {The Quarterly Journal of Economics},
publisher = {Oxford University Press (OUP)}}
@article{LuqueParadox2016,
doi = {10.1007/s10654-016-0139-5},
url = {https://doi.org/10.1007/s10654-016-0139-5},
issn = {0393-2990},
year = {2016},
month = {Jun},
pages = {613-623},
title = {Deconstructing the smoking-preeclampsia paradox through a counterfactual framework},
author = {Miguel Angel Luque-Fernandez, Helga Zoega, Unnur Valdimarsdottir, Michelle A. Williams},
number = {6},
volume = {31},
journal = {European Journal of Epidemiology},
publisher = {Springer Science and Business Media LLC}}
@article{Hernandez-Diaz_2006,
doi = {10.1093/aje/kwj275},
url = {https://doi.org/10.1093/aje/kwj275},
issn = {0002-9262},
year = {2006},
month = {Sep},
pages = {1115-1120},
title = {The Birth Weight "Paradox" Uncovered?},
author = {S. Hernandez-Diaz, E. F. Schisterman, M. A. Hernan},
number = {11},
volume = {164},
journal = {American Journal of Epidemiology},
publisher = {Oxford University Press (OUP)}}
@article{Banack2013,
doi = {10.1097/ede.0b013e31828c776c},
url = {https://doi.org/10.1097/ede.0b013e31828c776c},
issn = {1044-3983},
year = {2013},
month = {May},
pages = {461-462},
title = {The “Obesity Paradox” Explained},
author = {Hailey R. Banack, Jay S. Kaufman},
number = {3},
volume = {24},
journal = {Epidemiology},
publisher = {Ovid Technologies (Wolters Kluwer Health)}}
@article{Witccomb2009,
doi = {10.1111/j.1365-3016.2009.01053.x},
url = {https://doi.org/10.1111/j.1365-3016.2009.01053.x},
issn = {0269-5022},
year = {2009},
month = {Sep},
pages = {394-402},
title = {Quantification of collider‐stratification bias and the birthweight paradox},
author = {Brian W. Whitcomb, Enrique F. Schisterman, Neil J. Perkins, Robert W. Platt},
number = {5},
volume = {23},
journal = {Paediatric and Perinatal Epidemiology},
publisher = {Wiley}}
@article{Keil2014_7676,
doi = {10.1097/ede.0000000000000160},
url = {https://doi.org/10.1097/ede.0000000000000160},
issn = {1044-3983},
year = {2014},
month = {Nov},
pages = {889-897},
title = {The Parametric g-Formula for Time-to-event Data},
author = {Alexander P. Keil, Jessie K. Edwards, David B. Richardson, Ashley I. Naimi, Stephen R. Cole},
number = {6},
volume = {25},
journal = {Epidemiology},
publisher = {Ovid Technologies (Wolters Kluwer Health)}}
@article{Maldonado2009,
doi = {10.1186/1742-5573-6-3},
url = {https://doi.org/10.1186/1742-5573-6-3},
issn = {1742-5573},
year = {2009},
month = {Dec},
title = {Update: Greenland and Robins (1986). Identifiability, exchangeability and epidemiological confounding},
author = {George Maldonado},
number = {1},
volume = {6},
journal = {Epidemiologic Perspectives & Innovations},
publisher = {Springer Science and Business Media LLC}}
@article{Pearce2014,
doi = {10.1093/ije/dyu025},
url = {https://doi.org/10.1093/ije/dyu025},
issn = {0300-5771},
year = {2014},
month = {Apr},
pages = {521-524},
title = {Commentary: Three worlds collide: Berkson's bias, selection bias and collider bias},
author = {N. Pearce, L. Richiardi},
number = {2},
volume = {43},
journal = {International Journal of Epidemiology},
publisher = {Oxford University Press (OUP)}}
@article{Schomaker_2019,
doi = {10.1002/sim.8340},
url = {https://doi.org/10.1002/sim.8340},
issn = {0277-6715},
year = {2019},
month = {Oct},
pages = {4888-4911},
title = {Using longitudinal targeted maximum likelihood estimation in complex settings with dynamic interventions},
author = {M. Schomaker, M.A. Luque‐Fernandez, V. Leroy, M.A. Davies},
number = {24},
volume = {38},
journal = {Statistics in Medicine},
publisher = {Wiley}}
@article{Withcomb2021,
doi = {10.1093/aje/kwaa267},
url = {https://doi.org/10.1093/aje/kwaa267},
issn = {0002-9262},
year = {2021},
month = {May},
pages = {697-700},
title = {Defining, Quantifying, and Interpreting “Noncollapsibility” in Epidemiologic Studies of Measures of “Effect”},
author = {Brian W Whitcomb, Ashley I Naimi},
number = {5},
volume = {190},
journal = {American Journal of Epidemiology},
publisher = {Oxford University Press (OUP)}}
