American Statistical Association
Concordance Probability Estimate (CPE) is a consistent estimate of the concordance probability in a Cox model. It is a function of the model coefficients and the empirical distribution of the covariates. This formulation allows for mediating censoring via partial likelihood and ensures consistency but it does not easily lend itself to the usual methods of validation. In this talk, I will give examples of how one can use CPE with standard validation techniques such as split-sample and bootstrap with an application to a predictive model developed at MSK for patients with gastrointestinal stromal tumors.
|Date:||Wednesday, October 22, 2008|
|Time:||4:00 P.M. - 5:00 P.M.|
Memorial Sloan-Kettering Cancer Center
Department of Epidemiology and Biostatistics
307 East 63rd Street
(between First and Second Avenues)
3rd Floor Conference Room
New York, New York
Note: To gain access to the building, please follow the directions by the telephone in the foyer.