I am new at using survival analyses. I am writing an article on differences in recidivism for an experimental and control group of offenders. Due to differences between the groups in gender, I have added gender as covariate to my Cox Regression analysis. In Kaplan Meier, I get the mean survival time (no median, I think because in one of the groups the hazard ratio does not reach $0.50$), but this analysis does not take the covariate into consideration. Is it possible to request the mean survival time in Cox Regression using SPSS, for the analysis including the covariate?

  • 3
    $\begingroup$ One solution is to run Kaplan Meier on men and women separately. $\endgroup$ – Peter Flom Sep 26 '12 at 17:20
  • $\begingroup$ If you can't estimate the 50th percentile of the survival time, then estimate the 25th for example. Or more than one single percentile. I strongly suggest you to take a look at the Laplace Regression, which can model percentiles of the survival times while adjusting for covariates. onlinelibrary.wiley.com/doi/10.1002/bimj.200900310/abstract $\endgroup$ – boscovich Sep 27 '12 at 7:41

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.