TY - JOUR

T1 - A bias correction for covariance estimators to improve inference with generalized estimating equations that use an unstructured correlation matrix

AU - Westgate, Philip M.

PY - 2013/7/20

Y1 - 2013/7/20

N2 - Generalized estimating equations (GEEs) are routinely used for the marginal analysis of correlated data. The efficiency of GEE depends on how closely the working covariance structure resembles the true structure, and therefore accurate modeling of the working correlation of the data is important. A popular approach is the use of an unstructured working correlation matrix, as it is not as restrictive as simpler structures such as exchangeable and AR-1 and thus can theoretically improve efficiency. However, because of the potential for having to estimate a large number of correlation parameters, variances of regression parameter estimates can be larger than theoretically expected when utilizing the unstructured working correlation matrix. Therefore, standard error estimates can be negatively biased. To account for this additional finite-sample variability, we derive a bias correction that can be applied to typical estimators of the covariance matrix of parameter estimates. Via simulation and in application to a longitudinal study, we show that our proposed correction improves standard error estimation and statistical inference.

AB - Generalized estimating equations (GEEs) are routinely used for the marginal analysis of correlated data. The efficiency of GEE depends on how closely the working covariance structure resembles the true structure, and therefore accurate modeling of the working correlation of the data is important. A popular approach is the use of an unstructured working correlation matrix, as it is not as restrictive as simpler structures such as exchangeable and AR-1 and thus can theoretically improve efficiency. However, because of the potential for having to estimate a large number of correlation parameters, variances of regression parameter estimates can be larger than theoretically expected when utilizing the unstructured working correlation matrix. Therefore, standard error estimates can be negatively biased. To account for this additional finite-sample variability, we derive a bias correction that can be applied to typical estimators of the covariance matrix of parameter estimates. Via simulation and in application to a longitudinal study, we show that our proposed correction improves standard error estimation and statistical inference.

KW - Correlation structure

KW - Efficiency

KW - Generalized estimating equations

KW - Standard error

KW - Unstructured

UR - http://www.scopus.com/inward/record.url?scp=84879180863&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879180863&partnerID=8YFLogxK

U2 - 10.1002/sim.5709

DO - 10.1002/sim.5709

M3 - Article

C2 - 23255154

AN - SCOPUS:84879180863

SN - 0277-6715

VL - 32

SP - 2850

EP - 2858

JO - Statistics in Medicine

JF - Statistics in Medicine

IS - 16

ER -