Joint Modeling of Stochastic and Variability Orders in ROC Curves Using a Bayesian Semiparametric Approach

• Activity Number: 294
• Type: Contributed
• Date/Time: Tuesday, August 5, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Beomseuk Hwang*+ and Zhen Chen
• Companies: NIH/NICHD and NIH/NICHD
• Keywords: Dirichlet process ; Joint modeling ; Nonparametric Bayes ; ROC curve ; Stochastic order ; Variability order

Abstract

In estimating ROC curves of multiple tests, it's often the case that some a priori constraints exist, either between the healthy and diseased populations within each test or between tests within a diseased population. In this talk, we propose an integrated modeling approach for ROC curves that can jointly account for stochastic and variability orders. Within a Bayesian semi-parametric framework, we use features of Dirichlet process mixtures to incorporate these constraints in a natural way. We demonstrate the performance of the proposed approach using data from the Physician Reliability Study that investigated the accuracy of diagnosing endometriosis using different clinical information. To address the issue of no gold standard in the real data, we use a sensitivity analysis approach that exploits diagnosis from some international experts.