Minor revision with added functionality.
ordSelect, ordFusion updated/extended to cumulative
logit model models.ordCV added, provides cross-validation for penalized
regression models with ordinal predictors.StabilityCumu added, provides stability selection for
penalized cumulative logit models.Major revision with added functionality.
ordPCA added for nonlinear principal components analysis
for ordinal variables. Also, performance evaluation and selection of
an optimal penalty parameter provided.ordFusion added for fusion and selection of dummy
coefficients of ordinal predictors. Similar syntax as for
ordSmooth() and ordSelect(); generic functions plot and
predict work in the same manner.mgcv::gam()
can be used for fitting generalized linear and additive models with
first- and second-order ordinal smoothing penalty as well as
built-in smoothing parameter selection. A new type of spline basis
for ordered factors s(..., bs = "ordinal")is provided, such that
smooth terms in the GAM formula can be used as an alternative and
extension to ordSmooth(). Additionally, generic functions for
prediction and plotting are provided. Also, mgcv tools for further
statistical inference can be used.Two additional vignettes called ordPens and ordPCA are supplied to
give an overview and describe the usage of the package.
Bug fixes
plot.ordPen(), arguments whichlam and whichx are changed
to whl and whx, respectively.Minor revision with added functionality.
Function ordGene added, which provides testing for differentially
expressed genes.
Changed documentation of function ordAOV: argument null.sample
added, containing values already simulated from the null
distribution.
Fixed some minor bugs / cleaned up code.