Post-Model-Selection Prediction Intervals for Generalized Linear Models

We give two prediction intervals for Generalized Linear Models that take model selection uncertainty into account. The first is a straightforward extension of asymptotic normality results and the second includes an extra optimization that improves nominal coverage for small-to-moderate samples. Both PI’s are wider than would be obtained without incorporating model selection uncertainty. We compare these two PI’s with three other PI’s. Two are based on bootstrapping procedures and the third is based on a PI from Bayes model averaging. We argue that for general usage the optimized asymptotic normality PI’s work best unless sample sizes are large in which case the PI’s based only on asymptotic arguments that include model selection will be easier and equivalent. In an Appendix we extend our results to Generalized Linear Mixed Models.