Dear R mixed model users, I?d like to announce the release of my new R package cvGEE (https://cran.r-project.org/package=cvGEE) that validates (using repeated cross-validation) predictions from generalized estimating equations using proper scoring rules. It can be used to compare nested and non-nested GEEs, such as to compare GEEs with the same mean structure but different working correlation matrices. You may find more information and examples in the dedicated website: https://drizopoulos.github.io/cvGEE/ and vignette https://drizopoulos.github.io/cvGEE/articles/Scoring_Rules_GEE.html The package currently works with geeglm objects returned by the geepack but there are plans to extend it to other GEE-solvers packages. Additional future plans include functions for calibration plots. As always, any kind of feedback is more than welcome. Best, Dimitris - - - - - - Dimitris Rizopoulos Professor of Biostatistics Erasmus University Medical Center The Netherlands
New cvGEE package for validating predictions from GEEs
1 message · Dimitris Rizopoulos