Computationally efficient Monte Carlo EM algorithms for generalized linear mixed models

摘要: Maximum likelihood estimation in generalized linear mixed models usually involves intractable integrals that may be of high dimension. To reduce the dimensions involved computation, a reduced form score equation obtained by exploiting conditional independence and random effects structures can used. Two Monte Carlo methods, one based on direct integration other stochastic version Gauss–Hermite quadrature, are proposed for approximating equation. The EM algorithms need to simulate only first iteration; hence, computation burden increasing property original algorithm preserved. A information matrix is standard error estimation. We illustrate methods with an application salamander data examine their performance via simulation studies.