Estimators of Odds Ratio Regression Parameters in Matched Case-Control Studies with Covariate Measurement Error

Abstract

This article studies estimators of the odds ratio and odds ratio regression parameters in finely matched case-control studies containing a binary exposure of primary interest and subject-specific covariates that are subject to measurement error. A retrospective logistic regression model for the binary exposure variable is used. The effect of measurement errors on the conditional maximum likelihood estimator is determined. Three alternatives are considered: bias-corrected, functional, and “transformation” estimators. The asymptotic and small-sample properties of the three competitors are studied. The results are illustrated using data from a case-control study of diet and colon cancer.