You are here:
ANALYSIS OF CASE-CONTROL DATA WITH COVARIATE MEASUREMENT ERROR: APPLICATION TO DIET AND COLON CANCER
Citation:
Armstrong, B., A. Whittemore, AND G. Howe. ANALYSIS OF CASE-CONTROL DATA WITH COVARIATE MEASUREMENT ERROR: APPLICATION TO DIET AND COLON CANCER. U.S. Environmental Protection Agency, Washington, D.C., EPA/600/J-89/391.
Description:
We propose a method for estimating odds ratios from case-control data in which ovariates are subject to mesurement error. he mesurement error may contain both a random component and a systematic difference between cases and controls (recall bias). ultivariate normal discriminant analysis model is assumed. f the distribution of measurement error is known, then a simple correction to naive (biased) estimates of odds ratios from logistic regression of disease on fallible measurements of covariates removes bias. he same correction yields confidence intervals and significance tests. e apply the proposed methods to data from case-control study of colon cancer and diet.