Quantifying the Predictive Performance of Prognostic Models for Censored Survival Data with Time-Dependent Covariates
Article first published online: 28 JUN 2008
© 2008, The International Biometric Society
Volume 64, Issue 2, pages 603–610, June 2008
How to Cite
Schoop, R., Graf, E. and Schumacher, M. (2008), Quantifying the Predictive Performance of Prognostic Models for Censored Survival Data with Time-Dependent Covariates. Biometrics, 64: 603–610. doi: 10.1111/j.1541-0420.2007.00889.x
- Issue published online: 28 JUN 2008
- Article first published online: 28 JUN 2008
- Received July 2006. Revised May 2007. Accepted June 2007.
- Failure time data;
- Prognostic accuracy
Summary Prognostic models in survival analysis typically aim to describe the association between patient covariates and future outcomes. More recently, efforts have been made to include covariate information that is updated over time. However, there exists as yet no standard approach to assess the predictive accuracy of such updated predictions. In this article, proposals from the literature are discussed and a conditional loss function approach is suggested, illustrated by a publicly available data set.