Abstract

The EM algorithm is a popular approach to maximum likelihood estimation but has been not much used for high-dimensional regularization problems in linear mixed-effects models. In this paper, we introduce the EMLMLasso algorithm, which combines the EM algorithm and the popular R package glmnet for Lasso variable selection of the fixed effects in linear mixed-effects models. We compare the performance of the proposed EMLMLasso algorithm with the one implemented in the well-known R package glmmLasso, through the analyses of simulated and two real data applications. The simulations and applications when p n demonstrated consistency, good properties, and the effectiveness of the proposed variable selection procedure. Moreover, the EMLMLasso algorithm outperformed glmmLasso for selecting fixed effects in linear mixed-effects models. The proposed method is quite general and can be used for ridge and elastic net penalties in linear mixed-effects models.