Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
From | Molla Huq <molla.huq@gmail.com> |
To | statalist@hsphsun2.harvard.edu |
Subject | st: Validation with estat concordance |
Date | Thu, 29 Jul 2010 12:54:05 +1000 |
Hi, I am trying to validate a proposed cox proportional hazard model. I have a split data (60% on which I have constructed the model and 40% on which I am trying to validate it). As for CPH model we dont use lroc, we can use Harrell's C (as far as I know). But Harrell's C (estat concordance) only runs on the data on which the model was constructed (60%) not on the data (40%) I am trying to validate as it is a post-estimation command. Is there anything I can do to do a validation or n-fold validation? Any help will be appreciated. Thanks -- Molla Huq Bio-Statistician, Department of Epidemiology and Preventive Medicine, Monash University, Australia * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/