STATISTICS IN MEDICINE Statist. Med. 2008; 27:2756–2783 Published online 18 September 2007 in Wiley InterScience (www.interscience.wiley.com) DOI: 10.1002/sim.3044 Accounting for error due to misclassification of exposures in case–control studies of gene–environment interaction Li Zhang 1 , Bhramar Mukherjee 2, ∗, † , Malay Ghosh 3 , Stephen Gruber 4 and Victor Moreno 5, 6 1 Department of Quantitative Health Sciences, The Cleveland Clinic Foundation, Cleveland, OH-44195, U.S.A. 2 Department of Biostatistics, University of Michigan, Ann Arbor, MI-48109, U.S.A. 3 Department of Statistics, University of Florida, Gainesville, FL-32611, U.S.A. 4 Department of Internal Medicine, Epidemiology and Human Genetics, University of Michigan, Ann Arbor, MI-48109, U.S.A. 5 Department of Internal Medicine and Epidemiology, University of Michigan, Ann Arbor, MI-48109, U.S.A. 6 IDIBELL, Catalan Institute of Oncology, L’Hospitalet Barcelona, Spain SUMMARY We consider analysis of data from an unmatched case–control study design with a binary genetic factor and a binary environmental exposure when both genetic and environmental exposures could be potentially misclassified. We devise an estimation strategy that corrects for misclassification errors and also exploits the gene–environment independence assumption. The proposed corrected point estimates and confidence intervals for misclassified data reduce back to standard analytical forms as the misclassification error rates go to zero. We illustrate the methods by simulating unmatched case–control data sets under varying levels of disease–exposure association and with different degrees of misclassification. A real data set on a case–control study of colorectal cancer where a validation subsample is available for assessing genotyping error is used to illustrate our methods. Copyright 2007 John Wiley & Sons, Ltd. KEY WORDS: case-only method; gene–environment independence; sensitivity; specificity 1. INTRODUCTION Measurement error in exposure assessment is one of the major sources of bias in epidemiological studies. When ignored, even small errors in exposure assessment can result in biased point and ∗ Correspondence to: Bhramar Mukherjee, Department of Biostatistics, University of Michigan, Ann Arbor, MI-48109, U.S.A. † E-mail: bhramar@umich.edu Contract/grant sponsor: NSA; contract/grant number: H98230-06-1-0033 Contract/grant sponsor: Spanish Secretara de Estado de Universidades e Investigacin, Ministerio de Educacin y Ciencia Received 6 March 2007 Copyright 2007 John Wiley & Sons, Ltd. Accepted 10 July 2007