#### Major (to fix before next release) ######################################## (*) bug fixes for estimation methods! #### Intermediate ##################################################################### (MM) R/special-func.R & man/Bernoulli.Rd: Research for better algorithms <--> Rmpfr (MM) please take a look at gtrafouni() in ./R/gof.R: Can "Remillard" (and "Genest") be made faster? Especially "Remillard" is slow (although B Remillard told me that his method is faster than C. Genest's.) #### Minor ##################################################################### (*) write nice little function that provides confidence intervals for tau and lambda's (*) fix: cop <- onacopulaL("Frank", list(200, 1:2)); rnacopula(100, cop) maybe use limit copulas also for other families (upper frechet bound) (*) add an ASCII-plot for the hierarchical structure; Actually, define setAs("nacopula", "dendrogram", ....) and then use dendrogram print()ing. (*) design a function that gets an outer nacopula and returns a matrix of numbers which correspond to the different sectors; this can be used, e.g., for building a [default] color-matrix for splom2 or for estimation purposes etc. (*) it would be good to have tryCatch.W.E in the package [call it tryCatchWE -- easier to type] Maybe one can also directly return a list with "value", "error", and "warning"? [So far, "value" can also contain the errors => a bit unhandy, but maybe the only "elegant" general solution] (*) From time to time (well, whenever Marius has.. ;-)) check the .Rd files for overlong lines, i.e. apply for f in *Rd; do printf '%20s: ' \$f ; printf '%4d\n' `maxcol \$f` ; done #### Long-term maybe ########################################################### (*) implement Khoudraji or Liebscher trafo incl. density etc. (*) allow families to have outer power parameters (outer power families) (*) be compatible with package copula (*) include pairwise estimators for nACs (*) FIXME in enacopula (in estimation.R): return an object? (*) can we create a function for the GIG generator similar to opower()?