Health & Environmental Research Online (HERO)


Print Feedback Export to File
1330108 
Journal Article 
Selection of Working Correlation Structure and Best Model in GEE Analyses of Longitudinal Data 
Cui, J; Qian, G 
2007 
Yes 
Communications in Statistics: Simulation and Computation
ISSN: 0361-0918
EISSN: 1532-4141 
36 
5 
987-996 
WOS:000251715000005 
The Generalized Estimating Equations ( GEE) method is one of
the most commonly used statistical methods for the analysis of longitudinal data in
epidemiological studies. A working correlation structure for the repeated measures of the outcome
variable of a subject needs to be specified by this method. However, statistical criteria for
selecting the best correlation structure and the best subset of explanatory variables in GEE are
only available recently because the GEE method is developed on the basis of quasi-likelihood
theory. Maximum likelihood based model selection methods, such as the widely used Akaike
Information Criterion (AIC), are not applicable to GEE directly. Pan (2001) proposed a selection
method called QIC which can be used to select the best correlation structure and the best subset
of explanatory variables. Based on the QIC method, we developed a computing program to calculate
the QIC value for a range of different distributions, link functions and correlation structures.
This program was written in Stata software. In this article, we introduce this program and
demonstrate how to use it to select the most parsimonious model in GEE analyses of longitudinal
data through several representative examples. 
AIC; GEE; longitudinal study; QIC