Comparison of different computational implementations on fitting generalized linear mixed-effects models for repeated count measures

Lu Huang, Li Tang, Bo Zhang, Zhiwei Zhang, Hui Zhang*

*Corresponding author for this work

Research output: Contribution to journalArticle

5 Scopus citations

Abstract

In modelling repeated count outcomes, generalized linear mixed-effects models are commonly used to account for within-cluster correlations. However, inconsistent results are frequently generated by various statistical R packages and SAS procedures, especially in case of a moderate or strong within-cluster correlation or overdispersion. We investigated the underlying numerical approaches and statistical theories on which these packages and procedures are built. We then compared the performance of these statistical packages and procedures by simulating both Poisson-distributed and overdispersed count data. The SAS NLMIXED procedure outperformed the others procedures in all settings.

Original languageEnglish (US)
Pages (from-to)2392-2404
Number of pages13
JournalJournal of Statistical Computation and Simulation
Volume86
Issue number12
DOIs
StatePublished - Aug 12 2016

Keywords

  • R
  • Repeated count data
  • SAS
  • integral approximation
  • linearization
  • overdispersion

ASJC Scopus subject areas

  • Statistics and Probability
  • Modeling and Simulation
  • Statistics, Probability and Uncertainty
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Comparison of different computational implementations on fitting generalized linear mixed-effects models for repeated count measures'. Together they form a unique fingerprint.

Cite this