https://github.com/cran/CARBayes
Tip revision: 4dcb0c9a35d454fcd280455ae570d6dad367089c authored by Duncan Lee on 08 March 2024, 13:20:02 UTC
version 6.1.1
version 6.1.1
Tip revision: 4dcb0c9
S.CARlocalised.Rd
\name{S.CARlocalised}
\alias{S.CARlocalised}
%- Also NEED an '\alias' for EACH other topic documented here.
\title{
Fit a spatial generalised linear mixed model to data, where a set of spatially
smooth random effects are augmented with a piecewise constant intercept process.
}
\description{
Fit a spatial generalised linear mixed model to areal unit data, where the response
variable can be binomial or Poisson. Note, a Gaussian likelihood is not allowed
because of a lack of identifiability among the parameters. The linear predictor is
modelled by known covariates, a vector of random effects and a piecewise constant
intercept process. The random effects are modelled by an intrinsic CAR prior, while
the piecewise constant intercept process was proposed by Lee and Sarran (2015), and
allow neighbouring areas to have very different values. Further details are given
in the vignette accompanying this package. Inference is conducted in a Bayesian
setting using Markov chain Monte Carlo (MCMC) simulation. Missing (NA) values are
not allowed in this model. For a full model specification see the vignette
accompanying this package.
}
\usage{
S.CARlocalised(formula, family, data=NULL, G, trials=NULL, W, burnin, n.sample,
thin=1, n.chains=1, n.cores=1, prior.mean.beta=NULL, prior.var.beta=NULL,
prior.tau2=NULL,prior.delta=NULL, MALA=TRUE, verbose=TRUE)
}
%- maybe also 'usage' for other objects documented here.
\arguments{
\item{formula}{
A formula for the covariate part of the model using the syntax of the
lm() function. Offsets can be included here using the offset() function. The
response, offset and each covariate is a vector of length K*1.The response
cannot contain missing (NA) values.
}
\item{family}{
One of either "binomial" or "poisson", which respectively specify a
binomial likelihood model with a logistic link function, or a Poisson likelihood
model with a log link function.
}
\item{data}{
An optional data.frame containing the variables in the formula.
}
\item{G}{
The maximum number of distinct intercept terms (groups) to allow in the model.
}
\item{trials}{
A vector the same length as the response containing the total number of trials
for each area. Only used if family="binomial".
}
\item{W}{
A non-negative K by K neighbourhood matrix (where K is the number of spatial units).
Typically a binary specification is used, where the jkth element equals one if areas
(j, k) are spatially close (e.g. share a common border) and is zero otherwise. The
matrix can be non-binary, but each row must contain at least one non-zero entry.
}
\item{burnin}{
The number of MCMC samples to discard as the burn-in period in each chain.
}
\item{n.sample}{
The overall number of MCMC samples to generate in each chain.
}
\item{thin}{
The level of thinning to apply to the MCMC samples in each chain to reduce their
autocorrelation. Defaults to 1 (no thinning).
}
\item{n.chains}{
The number of MCMC chains to run when fitting the model. Defaults to 1.
}
\item{n.cores}{
The number of computer cores to run the MCMC chains on. Must be less than or
equal to n.chains. Defaults to 1.
}
\item{prior.mean.beta}{
A vector of prior means for the regression parameters beta (Gaussian priors are
assumed). Defaults to a vector of zeros.
}
\item{prior.var.beta}{
A vector of prior variances for the regression parameters beta (Gaussian priors
are assumed). Defaults to a vector with values 100,000.
}
\item{prior.tau2}{
The prior shape and scale in the form of c(shape, scale) for an Inverse-Gamma(shape, scale)
prior for tau2. Defaults to c(1, 0.01).
}
\item{prior.delta}{
The prior maximum for the cluster smoothing parameter delta. Defaults to 10.
}
\item{MALA}{
Logical, should the function use Metropolis adjusted Langevin algorithm
(MALA) updates (TRUE, default) or simple random walk updates (FALSE) for
the regression parameters.
}
\item{verbose}{
Logical, should the function update the user on its progress.
}
}
\value{
\item{summary.results }{A summary table of the parameters.}
\item{samples }{A list containing the MCMC samples from the model.}
\item{fitted.values }{The fitted values based on posterior means from the model.}
\item{residuals }{A matrix with 2 columns where each column is a type of
residual and each row relates to an area. The types are "response" (raw),
and "pearson".}
\item{modelfit }{Model fit criteria including the Deviance Information Criterion
(DIC) and its corresponding estimated effective number of parameters (p.d), the Log
Marginal Predictive Likelihood (LMPL), the Watanabe-Akaike Information Criterion
(WAIC) and its corresponding estimated number of effective parameters (p.w), and
the loglikelihood.}
\item{accept }{The acceptance probabilities for the parameters.}
\item{localised.structure }{A vector giving the posterior median of which intercept
group each area is in.}
\item{formula }{The formula (as a text string) for the response, covariate and
offset parts of the model}
\item{model }{A text string describing the model fit.}
\item{mcmc.info }{A vector giving details of the numbers of MCMC samples generated.}
\item{X }{The design matrix of covariates.}
}
\references{
Lee, D and Sarran, C (2015). Controlling for unmeasured confounding and spatial
misalignment in long-term air pollution and health studies, Environmetrics, 26,
477-487.
}
\author{
Duncan Lee
}
\examples{
#################################################
#### Run the model on simulated data on a lattice
#################################################
#### Load other libraries required
library(MASS)
#### Set up a square lattice region
x.easting <- 1:10
x.northing <- 1:10
Grid <- expand.grid(x.easting, x.northing)
K <- nrow(Grid)
#### Split the area into two groups between which there will be a boundary.
groups <-rep(1, K)
groups[Grid$Var1>5] <- 2
#### set up distance and neighbourhood (W, based on sharing a common border) matrices
distance <- as.matrix(dist(Grid))
W <-array(0, c(K,K))
W[distance==1] <-1
#### Generate the response data
phi <- mvrnorm(n=1, mu=groups, Sigma=0.2 * exp(-0.1 * distance))
logit <- phi
prob <- exp(logit) / (1 + exp(logit))
trials <- rep(50,K)
Y <- rbinom(n=K, size=trials, prob=prob)
#### Run the localised smoothing model
formula <- Y ~ 1
\dontrun{model <- S.CARlocalised(formula=formula, family="binomial", trials=trials,
G=2, W=W,burnin=20000, n.sample=100000)}
#### Toy example for checking
model <- S.CARlocalised(formula=formula, family="binomial", trials=trials,
G=2, W=W,burnin=10, n.sample=50)
}