Generalized Linear Mixed Models for Longitudinal Data Analysis: An Application to Maternal Morbidity Data

Abstract

This article discusses the application of Generalized Linear Mixed Models (GLMM) in which heterogeneity in regression parameters is
explicitly modelled in order to analyze the longitudinal data related to the maternal morbidity. The most commonly used model selection
criterion, Akaike’s Information Criterion (AIC) has been used to select important covariates associated with the pregnancy related
complications of Bangladeshi women. For testing the variance component in generalized linear mixed models, Likelihood Ratio Test (LRT)
has been performed.