Don't worry about the sign. When predicting relative log hazard, high hazard means short survival time so Dxy is negative. When predicting survival probability (u specified), high prob. means long survival time so Dxy is positive. You can just reverse the sign when u is not specified.
I did not see Dxy of -.54 or .6 anywhere on the output you sent. Specify time.inc of 30 to cph in the 2nd case. As you did not provide code to simulate test data, please run the second model yourself without strat but with surv=TRUE time.inc=30 (and u=30 to validate) to see if you get the same Dxy as for the first model, before bringing strat into the picture. rms and Design prefer for you to store the predictors as factor()s in the dataset instead of specifying this in the model formula. Frank ----- Frank Harrell Department of Biostatistics, Vanderbilt University -- View this message in context: http://r.789695.n4.nabble.com/Interpreting-the-example-given-by-Prof-Frank-Harrell-in-Design-validate-cph-tp3316820p3318189.html Sent from the R help mailing list archive at Nabble.com. ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.