Clustering in linear mixed models with Dirichlet process mixtures using EM algorithm

Heinzl, Felix and Tutz, Gerhard (2011): Clustering in linear mixed models with Dirichlet process mixtures using EM algorithm. Department of Statistics: Technical Reports, No.115

Abstract

In linear mixed models the assumption of normally distributed random effects is often inappropriate and unnecessary restrictive. The proposed Dirichlet process mixture assumes a hierarchical Gaussian mixture. In addition to the weakening of distributions assumptions the specification allows to estimate clusters of observations with a similar random effects structure identified. An Expectation-Maximization algorithm is given that solves the estimation problem and that exhibits advantages over in this framework usually used Markov chain Monte Carlo approaches. The method is evaluated in a simulation study and applied to dynamics of unemployment in Germany as well as lung function growth data.

• Item Type: Paper (Technical Report)
• Status: Submitted Version
• Keywords: Dirichlet process mixture, mixed models, likelihood inference, EM algorithm
• Collections: Mathematics, Computer Science and Statistics > Statistics > Technical Reports
• Subjects: 500 Science > 510 Mathematics
• Language: English