An Approximate EM Algorithm for Maximum Likelihood Estimation in Generalized Linear Mixed Models

摘要

This article considers the maximum likelihood estimation in generalized linear mixed models (GLMMs). Using results from number theory, we propose a numerical EM algorithm to find the maximum likelihood estimates in GLMMs. Details of the steps required by applying the proposed numerical method to the E-step of the EM algorithm are outlined. The performance and efficiency of the proposed method are compared to some commonly used methods discussed in the literature.