Using generalized estimating equation (gee) to analyse the influence of some factors on the state of health of diabetes patients

Abstract

In longitudinal studies, observations measured repeatedly from the same subject over time are serially correlated. One objective of statistical analysis is to describe the marginal expectation of the outcome variable as a function of the covariates while accounting for the correlation among the repeated observations for a given subject. Generalized Estimating Equation (GEE) is a general statistical approach to fit a marginal model for longitudinal/clustered data analysis, and it has been popularly applied into clinical trials and biomedical studies. Generalized linear Model (GLM)on the other hand has been widely used in fitting a regression to a set of data of dependent variables depending solely on a/some set of covariates with the different set of distributions and their link function and its use has been extended to longitudinal data. This paper examines the effects of some factors; age, sex, Body Mass Index (BMI), blood pressure, exercise and glucose tolerance on the health status of 840 diabetes patients attending clinic over a period of five years using the generalized linear model and the generalized estimating equations methods. The GEE performs better than the GLM. The result reveals that glucose tolerance, blood pressure and BMI are the important factors that affect the state of health of these patients