Bayesian Inference of Odds Ratios in Misclassified Binary Data with a Validation Substudy and an Application to Cervical Cancer Data

• Activity Number: 479
• Type: Contributed
• Date/Time: Wednesday, August 3, 2011 : 8:30 AM to 10:20 AM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Dewi Gabriela Rahardja*+ and Yan Daniel Zhao and Hao "Helen" Zhang
• Companies: The University of Texas Southwestern Medical Center and The University of Texas Southwestern Medical Center and North Carolina State University
• Keywords: Bayesian inference ; Binary data ; Credible interval ; Case-control study ; Misclassification ; Odds ratio

Abstract

We propose a fully Bayesian model with a non-informative prior for analyzing misclassified binary data with a validation substudy. In addition, we derive a closed-form algorithm for sampling all parameters from the posterior distribution and making statistical inference on odds ratios. Our algorithm draws each parameter from a beta distribution, avoids the specification of initial values, and does not have convergence issues. For illustration, we consider a case-control study which explores the association between herpes simplex virus and invasive cervical cancer. We then apply our algorithm to this case-control and compare the results with those obtained by other existing methods. Finally, we assess the performance of our algorithm using simulation studies.