The receiver operating characteristic (ROC) curve is frequently used to evaluate and compare diagnostic tests. As one of the ROC summary indices, the Youden index measures the effectiveness of a diagnostic marker and enables the selection of an optimal threshold value (cut‐off point) for the marker. Recently, the overlap coefficient, which captures the similarity between two distributions directly, has been considered as an alternative index for determining the diagnostic performance of markers. In this case, a larger overlap indicates worse diagnostic accuracy, and vice versa.
A new paper out of Georgia Southern University Jiann-Ping Hsu College of Public Health provides a graphical demonstration and mathematical derivation of the relationship between the Youden index and the overlap coefficient and states their advantages over the most popular diagnostic measure, the area under the ROC curve. It also outlines the differences between the Youden index and overlap coefficient and identifies situations in which the overlap coefficient outperforms the Youden index. Numerical examples and real data analysis are provided.
“Notes on the overlap measure as an alternative to the Youden index: How are they related?,” was recently published in Statistics in Medicine.
Dr. Hani Samawi, professor of biostatistics at Georgia Southern was the lead author. Georgia Southern’s Dr. Jingjing Yin, assistant professor of biostatistics, Dr. Haresh Rochani, assistant professor of biostatistics, and Mr. Viral Panchal, alumni, were co-authors.