No Detail Found!

Effect of Correlation Structure in Generalized Estimating Equations and Quasi Least Squares: An Application in Type 2 Diabetes Patients

Author(s)
Dilip C. Nath Department of Statistics Gauhati University Guwahati-781014 India
Atanu Bhattacharjee Department of Statistics Gauhati University Guwahati-781014 India
Abstract
The Quasi-Least Squares (QLS) is useful for various correlation structures when using Generalized Estimating Equations (GEE). The purpose of this work is to compare the regression parameters in the presence of different correlation structures when using GEE and QLS method. The comparison of estimated regression parameters has been performed in clinical trial data set; studying the effect of drug treatment (metformin with pioglitazone) vs (gliclazide with pioglitazone) in type 2 diabetes patients. In the case of QLS, the correlation coefficient for post-parandinal blood glucose (PPBG) under a tridiagonal correlation structure is 0.008 using GEE. It has been found that the combination of metformin with pioglitazone is more effective when compared to the combination of gliclazide with pioglitazone. 
Publication Details
Page(s) 401-412
DOI DOI not available
Published Journal: Pakistan Journal of Statistics and Operation Research, Volume: 7, Issue: 2, Year: 2011

Request the full text from PASTIC

Keywords
MCMC, Unstructured Correlation, Exchangeable, AR(1)
0

Citations

0

Downloads

98

Views