Scientific article

Variable Selection for Marginal Longitudinal Generalized Linear Models

Published inBiometrics, vol. 61, no. 2, p. 507-514
Publication date2005

Variable selection is an essential part of any statistical analysis and yet has been somewhat neglected in the context of longitudinal data analysis. In this paper we propose a generalized version of Mallows's Cp (GCp ) suitable for use with both parametric and nonparametric models. GCp provides an estimate of a measure of model's adequacy for prediction. We examine its performance with popular marginal longitudinal models (fitted using GEE) and contrast results with what is typically done in practice: variable selection based on Wald-type or score-type tests. An application to real data further demonstrates the merits of our approach while at the same time emphasizing some important robust features inherent to GCp.

  • Cp
  • Generalized estimating equations (GEE)
  • Prediction er- ror
  • Robustness
  • Variable selection
Citation (ISO format)
CANTONI, Eva, FLEMMING, Joanna Mills, RONCHETTI, Elvezio. Variable Selection for Marginal Longitudinal Generalized Linear Models. In: Biometrics, 2005, vol. 61, n° 2, p. 507–514. doi: 10.1111/j.1541-0420.2005.00331.x
Main files (1)
Article (Accepted version)
ISSN of the journal0006-341X

Technical informations

Creation09/12/2012 10:46:00 AM
First validation09/12/2012 10:46:00 AM
Update time03/14/2023 5:41:03 PM
Status update03/14/2023 5:41:03 PM
Last indexation05/02/2024 12:39:39 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack