A Comparison of Estimation Methods for Multivariate Generalized Linear Mixed Models

• In Event: 26.081 - Poster Session 3
  In Poster Session: 26.081-4 - Division D Section 2 Poster Session: Statistical Methods

Abstract

As part of a longitudinal study, researchers often collect data on a large number of variables at each measurement occasion. Although many research questions can be answered using separate models for each outcome variable, there are benefits to using models that can handle several outcomes simultaneously. This study demonstrates how multivariate generalized linear mixed models can be used to simultaneously analyze several repeated-measures variables which are not necessarily of the same scale type. A simulation study was conducted to investigate how well the parameters for this model can be recovered using a variety of estimation methods.

Author

• Casey Codd, Ascend Learning