|
Abstract:
|
In analyzing longitudinal or clustered data with a mixed effects model, violations of normality can potentially impact subset selection, inferences on the heterogeneity structure, and the accuracy of predictions. Although there is often interest in identifying the subset of predictors having random effects, random effects selection can be challenging, particularly when outcome distributions are non-normal. This article focuses on Bayesian methods for subset selection in nonparametric random effects models in which one is uncertain about the predictors to be included and the distribution of their random effects. By using carefully-chosen mixture priors for coefficients in the base distributions of the component Dirichlet Process, we allow fixed and random effects to be effectively dropped out of the model. An approximation is used for intractable integrals for non-normal outcomes.
|
