I am conducting a Weibull Survival analysis (recurrent event) with the time-frame between 1970 and 2010. One question is the difference in survival time between gender. However in the earlier years for 1970-1973 there are no women observed. Since calendar year is not my time scale this shouldn't be a problem right? Everyone in my sample starts at zero (onset of risk).

I did inlcude possible period effects as dummy variables (for example new hollywood era and blockbuster era).

  • $\begingroup$ It may depend on whether 1970-1973 was different from later periods (at least for men). If it was, then you may be biasing your analysis $\endgroup$
    – Henry
    Apr 29, 2021 at 10:27
  • $\begingroup$ @Henry And what if those periods do differ? Is there a way to incorporate that? $\endgroup$
    – MaiMai
    Apr 29, 2021 at 10:38


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.