I have a global dataset (with over 170 countries) and most of the countries in the data experienced the event multiple times. I use extended Cox models to analyze the data (so called "PWP"/conditional model) model. However, I am not sure how to calculate median survival time in R?

Also, I wonder if it is possible to calculate median survival time to the first, second,.. x event? I have no idea how to do it and the standard books on survival/event history analysis are not talking about these issues. Grateful for any suggestions.

  • $\begingroup$ What would you like to illustrate with a quantity such as the median survival time in this case? Do you think it would be meaningful? Also, what are your time scales? $\endgroup$ – Theodor Oct 23 '15 at 9:51
  • $\begingroup$ @Theodor Thank you for your question. Time scales are in years(1989 to 2014). Actually, given the imprecision of how I measure the time and the emphasize of the article in understanding how covariates affects the hazard rate, it is of less interest. However, reviewers would like to know how long does it take for states too experience the event (theoretically if it takes to short time = it was too easy; too long = we can't be really sure if it was X that affected..) Therefore, I would like to calculate median survival time (ideally, plot it). Or average (but that seems to be even more tricky.) $\endgroup$ – FKG Oct 23 '15 at 15:43

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.