B1605
Title: Post-selection inference for linear mixed model parameters using the conditional Akaike information criterion
Authors: Gerda Claeskens - KU Leuven (Belgium)
Katarzyna Reluga - University of Toronto (Canada) [presenting]
Stefan Sperlich - University of Geneva (Switzerland)
Abstract: The issue of post-selection inference for a fixed and a mixed parameter in a linear mixed model is investigated using a conditional Akaike information criterion as a model selection procedure. Within the framework of linear mixed models, we develop a complete theory to construct confidence intervals for regression and mixed parameters under three frameworks: nested and general model sets as well as misspecified models. The theoretical analysis is accompanied by a simulation experiment and a post-selection examination on mean income across Galicia's counties. The numerical studies confirm a good performance of our new procedure. Moreover, they reveal startling robustness to the model misspecification of a naive method to construct the confidence intervals for a mixed parameter which is in contrast to our findings for the fixed parameters.
