The walking man approach to interpreting the receiver operating characteristic curve and area under the receiver operating characteristic curve

An accuracy study of a test that produces a wide range of results will often present a receiver operating characteristic (ROC) curve and report the area under the ROC curve (AUROC). The AUROC is a summary measure of how well the test discriminates between those with the condition or disease in question and those without it. A test that perfectly separates individuals with and without the condition has an AUROC of 1.0, and a test that doesn't separate them at all has an AUROC of 0.5. The AUROC is also the probability that a random individual with the condition will have a more abnormal test result than a random individual without the condition. In this Key Concepts article, we present our "walking man" approach to understanding ROC curves and the AUROC.