Selective inference for additive and linear mixed models

After model selection, subsequent inference in statistical models tends to be overconfident if selection is not accounted for. One possible solution address this problem selective inference, which constitutes a post-selection framework and yields valid statements by conditioning on the event. Existing work is, however, directly applicable additive linear mixed models. A novel extension recent class of thus presented. The approach can applied for any type mechanism that expressed as function outcome variable (and potentially covariates conditions). Properties method are validated simulation studies an application data set monetary economics. particularly useful cases non-standard procedures, present motivating application.