American Statistical Association
Model-based concordance (MBC) measures provide consistent estimates of apparent discrimination under random censoring. Their use in external validation settings is problematic since they assume the model is correctly specified. In this talk, I will describe how this can be improved by incorporating the calibration slope in the estimation of MBC using external validation data. Performance of MBC and its competitors are examined by simulation and applied to a data set with very high (~90%) censoring.
|Date:||Wednesday, November 19, 2014|
|Time:||4:00 - 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.