Improving power in small-sample longitudinal studies when using generalized estimating equations

Philip M. Westgate; Woodrow W. Burchett

doi:10.1002/sim.6967

Improving power in small-sample longitudinal studies when using generalized estimating equations

Philip M. Westgate, Woodrow W. Burchett

Biostatistics

Research output: Contribution to journal › Article › peer-review

12 Scopus citations

Abstract

Generalized estimating equations (GEE) are often used for the marginal analysis of longitudinal data. Although much work has been performed to improve the validity of GEE for the analysis of data arising from small-sample studies, little attention has been given to power in such settings. Therefore, we propose a valid GEE approach to improve power in small-sample longitudinal study settings in which the temporal spacing of outcomes is the same for each subject. Specifically, we use a modified empirical sandwich covariance matrix estimator within correlation structure selection criteria and test statistics. Use of this estimator can improve the accuracy of selection criteria and increase the degrees of freedom to be used for inference. The resulting impacts on power are demonstrated via a simulation study and application example.

Original language	English
Pages (from-to)	3733-3744
Number of pages	12
Journal	Statistics in Medicine
Volume	35
Issue number	21
DOIs	https://doi.org/10.1002/sim.6967
State	Published - Sep 20 2016

Bibliographical note

Funding Information:
We thank the anonymous associate editor and two reviewers for their constructive comments that helped improve this paper. We also thank Dr Richard J. Kryscio, Dr Frederick A. Schmitt, and Dr Erin Abner for providing us the application example data from the PREADViSE trial, which was supported by a grant from the National Institute on Aging (R01 AG019241). 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.

Publisher Copyright:
Copyright © 2016 John Wiley & Sons, Ltd.

Keywords

correlation selection
degrees of freedom
efficiency
empirical covariance matrix

ASJC Scopus subject areas

Epidemiology
Statistics and Probability

Access to Document

10.1002/sim.6967

Cite this

@article{4ea441ad74944e708e41bb23cee8d66f,

title = "Improving power in small-sample longitudinal studies when using generalized estimating equations",

abstract = "Generalized estimating equations (GEE) are often used for the marginal analysis of longitudinal data. Although much work has been performed to improve the validity of GEE for the analysis of data arising from small-sample studies, little attention has been given to power in such settings. Therefore, we propose a valid GEE approach to improve power in small-sample longitudinal study settings in which the temporal spacing of outcomes is the same for each subject. Specifically, we use a modified empirical sandwich covariance matrix estimator within correlation structure selection criteria and test statistics. Use of this estimator can improve the accuracy of selection criteria and increase the degrees of freedom to be used for inference. The resulting impacts on power are demonstrated via a simulation study and application example.",

keywords = "correlation selection, degrees of freedom, efficiency, empirical covariance matrix",

author = "Westgate, {Philip M.} and Burchett, {Woodrow W.}",

note = "Funding Information: We thank the anonymous associate editor and two reviewers for their constructive comments that helped improve this paper. We also thank Dr Richard J. Kryscio, Dr Frederick A. Schmitt, and Dr Erin Abner for providing us the application example data from the PREADViSE trial, which was supported by a grant from the National Institute on Aging (R01 AG019241). 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. Publisher Copyright: Copyright {\textcopyright} 2016 John Wiley & Sons, Ltd.",

year = "2016",

month = sep,

day = "20",

doi = "10.1002/sim.6967",

language = "English",

volume = "35",

pages = "3733--3744",

number = "21",

}

TY - JOUR

T1 - Improving power in small-sample longitudinal studies when using generalized estimating equations

AU - Westgate, Philip M.

AU - Burchett, Woodrow W.

N1 - Funding Information: We thank the anonymous associate editor and two reviewers for their constructive comments that helped improve this paper. We also thank Dr Richard J. Kryscio, Dr Frederick A. Schmitt, and Dr Erin Abner for providing us the application example data from the PREADViSE trial, which was supported by a grant from the National Institute on Aging (R01 AG019241). 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. Publisher Copyright: Copyright © 2016 John Wiley & Sons, Ltd.

PY - 2016/9/20

Y1 - 2016/9/20

N2 - Generalized estimating equations (GEE) are often used for the marginal analysis of longitudinal data. Although much work has been performed to improve the validity of GEE for the analysis of data arising from small-sample studies, little attention has been given to power in such settings. Therefore, we propose a valid GEE approach to improve power in small-sample longitudinal study settings in which the temporal spacing of outcomes is the same for each subject. Specifically, we use a modified empirical sandwich covariance matrix estimator within correlation structure selection criteria and test statistics. Use of this estimator can improve the accuracy of selection criteria and increase the degrees of freedom to be used for inference. The resulting impacts on power are demonstrated via a simulation study and application example.

AB - Generalized estimating equations (GEE) are often used for the marginal analysis of longitudinal data. Although much work has been performed to improve the validity of GEE for the analysis of data arising from small-sample studies, little attention has been given to power in such settings. Therefore, we propose a valid GEE approach to improve power in small-sample longitudinal study settings in which the temporal spacing of outcomes is the same for each subject. Specifically, we use a modified empirical sandwich covariance matrix estimator within correlation structure selection criteria and test statistics. Use of this estimator can improve the accuracy of selection criteria and increase the degrees of freedom to be used for inference. The resulting impacts on power are demonstrated via a simulation study and application example.

KW - correlation selection

KW - degrees of freedom

KW - efficiency

KW - empirical covariance matrix

UR - http://www.scopus.com/inward/record.url?scp=84980347592&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84980347592&partnerID=8YFLogxK

U2 - 10.1002/sim.6967

DO - 10.1002/sim.6967

M3 - Article

C2 - 27090375

AN - SCOPUS:84980347592

VL - 35

SP - 3733

EP - 3744

IS - 21

ER -

Improving power in small-sample longitudinal studies when using generalized estimating equations

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this