|
Abstract:
|
We propose a new summary measure of diagnostic test accuracy which can be used as a companion, or possibly as an alternative, to existing diagnostic accuracy measures. Conceptually, our summary measure is most closely related to the Hellinger distance between distributions. Our summary measure is also based on similar construction principles as the standard notions of covariance and Pearson correlation, in the sense that they can be regarded as measures of agreement based on the same geometrical grounds. A covariate-adjusted version of our summary index is devised, which can be used to assess the discrimination performance of a diagnostic test, conditionally on the value of a predictor. Nonparametric Bayes estimators for the proposed index are devised and the performance of our methods is assessed through a simulation study. Data from a prostate cancer diagnosis study are used to demonstrate our methods.
|
