A Paradox: Can Efficiency Be Gained by Correcting for Misclassification?

• Activity Number: 79
• Type: Contributed
• Date/Time: Sunday, July 29, 2012 : 4:00 PM to 5:50 PM
• Sponsor: ENAR
• Author(s): Molin Wang*+ and Xiaomei Liao and Donna Spiegelman
• Companies: Harvard School of Public Health and Harvard School of Public Health and Harvard School of Public Health
• Keywords: Misclassification ; Odds ratio ; 2 by 2 table ; Case control study ; Validation study design

Abstract

This presentation considers 2 by 2 tables arising from case-control studies in which the binary exposure may be misclassified. We found circumstances under which the inverse matrix method can provide a more efficient log-odds ratio estimator than the naive estimator. We provide some intuition for the findings, and also provide a formula for obtaining the minimum size of the validation study such that the variance of the log-odds ratio estimator from the inverse matrix method is smaller than that of the naive estimator. As a corollary of this result, we show that correcting for misclassification does not necessarily lead to a widening of the confidence intervals, but, rather, in addition to producing a consistent estimate, may also produce one that is more efficient.