No. 904

Title:

Extended Information Criterion (EIC) approach for linear mixed effects
models under restricted maximum likelihood (REML) estimation

Author(s):

Yafune, Akifumi (Clinic Sendagaya, The Institute of Statistical Mathematics);
Funatogawa, Takashi (Clinical Data Analysis Dept., Chugai Pharmaceutical Co., Ltd.);
Ishiguro, Makio (The Institute of Statistical Mathematics, The Graduate University for Advanced Studies)

Key words:

bootstrap method; covariance structure; Extended Information Criterion (EIC); mean structure; model selection; restricted maximum likelihood (REML) method.

Abstract:

    In clinical data analysis, the restricted maximum likelihood method has been commonly used for estimating variance components in the linear mixed effects model. Under the REML estimation, however, it is not straightforward to compare several linear mixed effects models with different mean and covariance structures. In particular, few approaches have been proposed for the comparison of linear mixed effects models with different mean structures under the REML estimation. We propose an approach using Extended Information Criterion (EIC), which is a bootstrap-based extension of AIC, for comparing linear mixed effects models with different mean and covariance structures under the REML estimation. We present a simulation study and applications to two actual clinical data sets.