The Youden Index in the Generalized Receiver Operating Characteristic Curve Context

• Published in: The international journal of biostatistics Vol. 15; no. 1
• Main Authors: Martínez-Camblor, Pablo, Pardo-Fernández, Juan Carlos
• Format: Journal Article
• Language: English
• Published: Germany De Gruyter 03.04.2019; Walter de Gruyter GmbH
• Subjects: (Bio)markers; Bias; Biomarkers; Classification; Computer Simulation; Confidence intervals; cutoff point; Data Interpretation, Statistical; Diagnostic tests; Economic models; generalized receiver-operating characteristic (gROC) curve; Medical prognosis; Meningitis; Models, Statistical; Monte Carlo Method; Probability; receiver-operating characteristic (ROC) curve; Research Design; ROC Curve; Youden index; (Bio)markers; Youden index; receiver-operating characteristic (ROC) curve; cutoff point; generalized receiver-operating characteristic (gROC) curve
• ISSN: 2194-573X; 1557-4679; 1557-4679
• DOI: 10.1515/ijb-2018-0060

The receiver operating characteristic (ROC) curve and their associated summary indices, such as the Youden index, are statistical tools commonly used to analyze the discrimination ability of a (bio)marker to distinguish between two populations. This paper presents the concept of Youden index in the context of the generalized ROC (gROC) curve for non-monotone relationships. The interval estimation of the Youden index and the associated cutoff points in a parametric (binormal) and a non-parametric setting is considered. Monte Carlo simulations and a real-world application illustrate the proposed methodology.