Online Program Home
My Program

Abstract Details

Activity Number: 167 - Statistical Computing and Statistical Graphics: Student Paper Award and Chambers Statistical Software Award
Type: Contributed
Date/Time: Monday, July 30, 2018 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistical Computing
Abstract #328341
Title: MM Algorithms for Variance Components Models
Author(s): Liuyi Hu* and Hua Zhou and Jin Zhou and Kenneth Lange
Companies: North Carolina State University and UCLA and University of Arizona and UCLA
Keywords: generalized linear mixed model; maximum likelihood estimation; minorization-maximization; variance components model; matrix convexity; linear mixed model

Variance components estimation and mixed model analysis are central themes in statistics with applications in numerous scientific disciplines. Building on the minorization-maximization (MM) principle, this paper presents a novel iterative algorithm for variance components estimation. MM algorithm is trivial to implement and competitive on large data problems. The algorithm readily extends to more complicated problems such as multivariate response models and generalized linear mixed models (GLMM). We establish the global convergence of the MM algorithm to a KKT point and demonstrate, both numerically and theoretically, that it converges faster than the classical EM algorithm when the number of variance components is greater than two and all covariance matrices are positive definite.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program