Comparing Two Diagnostic Processes: Operating Characteristics of Nonparametric Methods

Abstract

The area under ROC curve (AUC) is frequently used as a measure for the effectiveness of diagnostic processes. The aim of this paper is to explore and evaluate several nonparametric test methods of comparing the effectiveness and performance of two competing diagnostic processes producing quantitative ratings. These nonparametric methods make use of ROC curves when comparing the diagnostics processes. An extensive simulation study is performed to investigate the operating characteristics of the test methods in a wide range of settings.