Mixture of linear mixed models Application to repeated data clustering
The problem of finite mixture analysis from repeated data is considered. Data variability is taken into account through linear mixed models leading to a mixture of mixed models. The maximum likelihood estimation of this family of models through the EM algorithm is presented. The problem of selecting a particular mixture of mixed models is considered. Illustrative Monte Carlo experiments are presented and an application to the clustering of gene expression profiles is detailed. All those experiments highlight the interest of linear mixed model mixtur es for taking account of data variability in a proper way.