Time-Dependent Predictive Accuracy in the Presence of Competing Risks

• Published in: Biometrics Vol. 66; no. 4; pp. 999 - 1011
• Main Authors: Saha, P., Heagerty, P. J.
• Format: Journal Article
• Language: English
• Published: Malden, USA Blackwell Publishing Inc 01.12.2010; Wiley-Blackwell; Blackwell Publishing Ltd
• Subjects: Accuracy; BIOMETRIC METHODOLOGY; Biometrics; biometry; Breast cancer; Censorship; Competing risks; Consistent estimators; Cox regression; Discrimination; Estimate reliability; Estimation bias; Estimation methods; Estimators; Kaplan-Meier estimator; Kernel smoothing; Kinetics; Methods; Modeling; Models, Statistical; Prediction; Predictive Value of Tests; Research methodology; Risk; Risk factors; Sensitivity; Specificity; Statistical analysis; Time; Time dependence; Time Factors

Summary Competing risks arise naturally in time-to-event studies. In this article, we propose time-dependent accuracy measures for a marker when we have censored survival times and competing risks. Time-dependent versions of sensitivity or true positive (TP) fraction naturally correspond to consider...