Bayesian nonparametric inference for the covariate-adjusted ROC curve
09/01/2018 Tuesday 9th January 2018, 15:00 (Room P3.10, Mathematics Building)
Vanda Inácio De Carvalho, The University of Edinburgh, School of Mathematics
Accurate diagnosis of disease is of fundamental importance in clinical practice and medical research. Before a medical diagnostic test is routinely used in practice, its ability to distinguish between diseased and nondiseased states must be rigorously assessed through statistical analysis. The receiver operating characteristic (ROC) curve is the most popular used tool for evaluating the discriminatory ability of continuous-outcome diagnostic tests. Recently, it has been acknowledged that several factors (e.g., subject-specific characteristics, such as age and/or gender) can affect the test’s accuracy beyond disease status. In this work, we develop Bayesian nonparametric inference, based on a combination of dependent Dirichlet process mixture models and the Bayesian bootstrap, for the covariate-adjusted ROC curve (Janes and Pepe, 2009, Biometrika), a measure of covariate-adjusted diagnostic accuracy. Applications to simulated and real data are provided.