A Measure of Explained Variation for Event History Data
Article first published online: 14 DEC 2010
© 2010, The International Biometric Society
Volume 67, Issue 3, pages 750–759, September 2011
How to Cite
Stare, J., Perme, M. P. and Henderson, R. (2011), A Measure of Explained Variation for Event History Data. Biometrics, 67: 750–759. doi: 10.1111/j.1541-0420.2010.01526.x
- Issue published online: 14 SEP 2011
- Article first published online: 14 DEC 2010
- Received April 2010. Revised August 2010. Accepted September 2010.
- Dynamic models;
- Explained variation;
- Rank correlation;
- Recurrent events
Summary There is no shortage of proposed measures of prognostic value of survival models in the statistical literature. They come under different names, including explained variation, correlation, explained randomness, and information gain, but their goal is common: to define something analogous to the coefficient of determination R2 in linear regression. None however have been uniformly accepted, none have been extended to general event history data, including recurrent events, and many cannot incorporate time-varying effects or covariates. We present here a measure specifically tailored for use with general dynamic event history regression models. The measure is applicable and interpretable in discrete or continuous time; with tied data or otherwise; with time-varying, time-fixed, or dynamic covariates; with time-varying or time-constant effects; with single or multiple event times; with parametric or semiparametric models; and under general independent censoring/observation. For single-event survival data with neither censoring nor time dependency it reduces to the concordance index. We give expressions for its population value and the variance of the estimator and explore its use in simulations and applications. A web link to R software is provided.