Testing Cox proportional hazards assumption with multiple imputed datasets + plotting survival curves

[Eduardo Torre]

Dear Statalist,

I am trying to fit a Cox regression model with my multiple imputed dataset (10 copies). I have one main variable of interest (mvi) and 5 covariates. All the variables are not time-varying. My command should look like this:

mi stset months, failure(outcome)

mi estimate, hr: stcox mvi cov1 cov2 cov3 cov4 cov5

How can I test the Cox assumptions in this case, and how can I plot the survival curve?


Thanks