Bayesian analysis of pair-matched case-control studies subject to outcome misclassification.

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.

DOI: 10.1002/sim.7427

Cite this paper

@article{Hgg2017BayesianAO, title={Bayesian analysis of pair-matched case-control studies subject to outcome misclassification.}, author={Tanja H{\"{o}gg and John Petkau and Yinshan Zhao and Paul Gustafson and Jos{\'e} M A Wijnands and Helen L Tremlett}, journal={Statistics in medicine}, year={2017}, volume={36 26}, pages={4196-4213} }