Modified robust variance estimator for generalized estimating equations with improved small-sample performance

Ming Wang, Qi Long

Research output: Contribution to journalArticle

27 Citations (Scopus)

Abstract

Generalized estimating equations (GEE (Biometrika 1986; 73(1):13-22) is a general statistical method to fit marginal models for correlated or clustered responses, and it uses a robust sandwich estimator to estimate the variance-covariance matrix of the regression coefficient estimates. While this sandwich estimator is robust to the misspecification of the correlation structure of the responses, its finite sample performance deteriorates as the number of clusters or observations per cluster decreases. To address this limitation, Pan (Biometrika 2001; 88(3):901-906) and Mancl and DeRouen (Biometrics 2001; 57(1):126-134) investigated two modifications to the original sandwich variance estimator. Motivated by the ideas underlying these two modifications, we propose a novel robust variance estimator that combines the strengths of these estimators. Our theoretical and numerical results show that the proposed estimator attains better efficiency and achieves better finite sample performance compared with existing estimators. In particular, when the sample size or cluster size is small, our proposed estimator exhibits lower bias and the resulting confidence intervals for GEE estimates achieve better coverage rates performance. We illustrate the proposed method using data from a dental study.

Original languageEnglish (US)
Pages (from-to)1278-1291
Number of pages14
JournalStatistics in Medicine
Volume30
Issue number11
DOIs
StatePublished - May 20 2011

Fingerprint

Generalized Estimating Equations
Robust Estimators
Variance Estimator
Sandwich Estimator
Small Sample
Estimator
Sample Size
Tooth
Confidence Intervals
Marginal Model
Coefficient Estimates
Regression Estimate
Variance-covariance Matrix
Misspecification
Correlation Structure
Number of Clusters
Regression Coefficient
Biometrics
Estimate
Statistical method

All Science Journal Classification (ASJC) codes

  • Epidemiology
  • Statistics and Probability

Cite this

@article{f3779d8a61eb455796f50e83052e9050,
title = "Modified robust variance estimator for generalized estimating equations with improved small-sample performance",
abstract = "Generalized estimating equations (GEE (Biometrika 1986; 73(1):13-22) is a general statistical method to fit marginal models for correlated or clustered responses, and it uses a robust sandwich estimator to estimate the variance-covariance matrix of the regression coefficient estimates. While this sandwich estimator is robust to the misspecification of the correlation structure of the responses, its finite sample performance deteriorates as the number of clusters or observations per cluster decreases. To address this limitation, Pan (Biometrika 2001; 88(3):901-906) and Mancl and DeRouen (Biometrics 2001; 57(1):126-134) investigated two modifications to the original sandwich variance estimator. Motivated by the ideas underlying these two modifications, we propose a novel robust variance estimator that combines the strengths of these estimators. Our theoretical and numerical results show that the proposed estimator attains better efficiency and achieves better finite sample performance compared with existing estimators. In particular, when the sample size or cluster size is small, our proposed estimator exhibits lower bias and the resulting confidence intervals for GEE estimates achieve better coverage rates performance. We illustrate the proposed method using data from a dental study.",
author = "Ming Wang and Qi Long",
year = "2011",
month = "5",
day = "20",
doi = "10.1002/sim.4150",
language = "English (US)",
volume = "30",
pages = "1278--1291",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "11",

}

Modified robust variance estimator for generalized estimating equations with improved small-sample performance. / Wang, Ming; Long, Qi.

In: Statistics in Medicine, Vol. 30, No. 11, 20.05.2011, p. 1278-1291.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Modified robust variance estimator for generalized estimating equations with improved small-sample performance

AU - Wang, Ming

AU - Long, Qi

PY - 2011/5/20

Y1 - 2011/5/20

N2 - Generalized estimating equations (GEE (Biometrika 1986; 73(1):13-22) is a general statistical method to fit marginal models for correlated or clustered responses, and it uses a robust sandwich estimator to estimate the variance-covariance matrix of the regression coefficient estimates. While this sandwich estimator is robust to the misspecification of the correlation structure of the responses, its finite sample performance deteriorates as the number of clusters or observations per cluster decreases. To address this limitation, Pan (Biometrika 2001; 88(3):901-906) and Mancl and DeRouen (Biometrics 2001; 57(1):126-134) investigated two modifications to the original sandwich variance estimator. Motivated by the ideas underlying these two modifications, we propose a novel robust variance estimator that combines the strengths of these estimators. Our theoretical and numerical results show that the proposed estimator attains better efficiency and achieves better finite sample performance compared with existing estimators. In particular, when the sample size or cluster size is small, our proposed estimator exhibits lower bias and the resulting confidence intervals for GEE estimates achieve better coverage rates performance. We illustrate the proposed method using data from a dental study.

AB - Generalized estimating equations (GEE (Biometrika 1986; 73(1):13-22) is a general statistical method to fit marginal models for correlated or clustered responses, and it uses a robust sandwich estimator to estimate the variance-covariance matrix of the regression coefficient estimates. While this sandwich estimator is robust to the misspecification of the correlation structure of the responses, its finite sample performance deteriorates as the number of clusters or observations per cluster decreases. To address this limitation, Pan (Biometrika 2001; 88(3):901-906) and Mancl and DeRouen (Biometrics 2001; 57(1):126-134) investigated two modifications to the original sandwich variance estimator. Motivated by the ideas underlying these two modifications, we propose a novel robust variance estimator that combines the strengths of these estimators. Our theoretical and numerical results show that the proposed estimator attains better efficiency and achieves better finite sample performance compared with existing estimators. In particular, when the sample size or cluster size is small, our proposed estimator exhibits lower bias and the resulting confidence intervals for GEE estimates achieve better coverage rates performance. We illustrate the proposed method using data from a dental study.

UR - http://www.scopus.com/inward/record.url?scp=79955625527&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955625527&partnerID=8YFLogxK

U2 - 10.1002/sim.4150

DO - 10.1002/sim.4150

M3 - Article

C2 - 21538453

AN - SCOPUS:79955625527

VL - 30

SP - 1278

EP - 1291

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 11

ER -