A Comparison of Correlation Structure Selection Penalties for Generalized Estimating Equations

ABSTRACT

Correlated data are commonly analyzed using models constructed using population-averaged generalized estimating equations (GEEs). The specification of a population-averaged GEE model includes selection of a structure describing the correlation of repeated measures. Accurate specification of this structure can improve efficiency, whereas the finite-sample estimation of nuisance correlation parameters can inflate the variances of regression parameter estimates. Therefore, correlation structure selection criteria should penalize, or account for, correlation parameter estimation. In this article, we compare recently proposed penalties in terms of their impacts on correlation structure selection and regression parameter estimation, and give practical considerations for data analysts. Supplementary materials for this article are available online.

KEYWORDS:

• Bias-correction
• Efficiency
• Empirical covariance matrix
• Longitudinal data

Supplementary Material

• Title: GEE function with penalized correlation selection criteria, simulated dataset, function demonstration.

• GEE Function for Supplementary Material (.txt file): This is an R function for estimating a population-averaged GEE model. Values for the penalized criteria studied in this article are included in the output.

• example_dataset (.txt file): This is an example dataset based on our simulation study model.

• Demonstrating the GEE Function (.txt file): This function utilizes the example dataset to demonstrates the use of our GEE function.

Acknowledgment

We would like to thank the anonymous associate editor and two reviewers for their constructive comments that helped improve this article. We also thank Dr. Abner for providing us with the dataset and relevant information.

Additional information

Funding

The authors gratefully acknowledge the National Center for Research Resources and the National Center for Advancing Translational Sciences, National Institutes of Health, through Grant UL1TR000117. This publication was supported by the National Center for Research Resources and the National Center for Advancing Translational Sciences, National Institutes of Health, through Grant UL1TR000117. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH. We would like to thank Dr. Richard J. Kryscio, Dr. Frederick A. Schmitt, and Dr. Erin Abner for allowing us to use the data from the PREADViSE trial, which was supported through a National Institute on Aging grant (R01 AG019241).