COMPSTAT 2018: Start Registration
View Submission - COMPSTAT2018
Title: Computational tools for count data regression Authors:  Christian Kleiber - Universitaet Basel (Switzerland) [presenting]
Abstract: An overview of a variety of computational tools for count data regressions that are available via the R package \textbf{countreg} is provided. The package provides a number of fitting functions and new tools for model diagnostics: it incorporates enhanced versions of fitting functions for hurdle and zero-inflation models that have been available via the \textbf{pscl} package for some 10 years, now also permitting binomial responses. In addition, it provides zero-truncation models for data without zeros, along with \textbf{mboost} family generators that enable boosting of zero-truncated and untruncated count data regressions, thereby supplementing and extending family generators available with the \textbf{mboost} package. For visualizing model fits, \textbf{countreg} offers rootograms and probability integral transform (PIT) histograms. A (generic) function for computing (randomized) quantile residuals is also available. Development versions of \textbf{countreg} can be obtained from R-Forge. Some well-known data sets from the count data literature will be revisited.