Bayesian analysis of pair‐matched case‐control studies subject to outcome misclassification. (7th August 2017)

• Record Type: Journal Article
• Authors: Högg, Tanja; Petkau, John; Zhao, Yinshan; Gustafson, Paul; Wijnands, José MA; Tremlett, Helen
• Is Part Of: Statistics in medicine. Volume 36:Number 26(2017)
• Page Start: 4196
• Page End: 4213
• Publication Date: 2017-08-07
• Subjects: Bayesian method -- health administrative databases -- matched case‐control study -- odds ratio -- outcome misclassification; Medical statistics -- Periodicals; Statistique médicale -- Périodiques; Statistiques médicales -- Périodiques; 610.727
• DOI: 10.1002/sim.7427
• Languages: English
• ISSNs: 0277-6715

Abstract

Abstract : We examine the impact of nondifferential outcome misclassification on odds ratios estimated from pair‐matched case‐control studies and propose a Bayesian model to adjust these estimates for misclassification bias. The model relies on access to a validation subgroup with confirmed outcome status for all case‐control pairs as well as prior knowledge about the positive and negative predictive value of the classification mechanism. We illustrate the model's performance on simulated data and apply it to a database study examining the presence of ten morbidities in the prodromal phase of multiple sclerosis.