Working-correlation-structure identification in generalized estimating equations

Hin, Lin-Yee and Wang, You-Gan (2009) Working-correlation-structure identification in generalized estimating equations. Statistics in Medicine, 28 4: 642-658. doi:10.1002/sim.3489


Author Hin, Lin-Yee
Wang, You-Gan
Title Working-correlation-structure identification in generalized estimating equations
Journal name Statistics in Medicine   Check publisher's open access policy
ISSN 0277-6715
1097-0258
Publication date 2009-02-20
Year available 2008
Sub-type Article (original research)
DOI 10.1002/sim.3489
Volume 28
Issue 4
Start page 642
End page 658
Total pages 17
Place of publication Bognor Regis, West Sussex, United Kingdom
Publisher John Wiley & Sons
Language eng
Abstract Selecting an appropriate working correlation structure is pertinent to clustered data analysis using generalized estimating equations (GEE) because an inappropriate choice will lead to inefficient parameter estimation. We investigate the well-known criterion of QIC for selecting a working correlation structure, and have found that performance of the QIC is deteriorated by a term that is theoretically independent of the correlation structures but has to be estimated with an error. This leads us to propose a correlation information criterion (CIC) that substantially improves the QIC performance. Extensive simulation studies indicate that the CIC has remarkable improvement in selecting the correct correlation structures. We also illustrate our findings using a data set from the Madras Longitudinal Schizophrenia Study.
Keyword Clustered data
Correlation modelling
Correlation information criterion
Covariance
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Non-UQ
Additional Notes Article first published online: 8 DEC 2008

Document type: Journal Article
Sub-type: Article (original research)
Collection: School of Mathematics and Physics
 
Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 43 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 47 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Wed, 17 Nov 2010, 23:50:22 EST