0

I am interested in calculating p-values within a Cox PH model based upon the maximal test statistic, to get very robust estimates. Does anyone have experience with this?

I have played around a bit with the R package 'coxphf' that incorporates Firth's penalized likelihood, but it seems to be giving me different coefficients and p-values if I chose firth=FALSE vs. use the standard coxph function in 'survival'.

I do not discount being completely lost on this, so any advice would be useful.

Thanks!

Ryon
  • 1
  • [coxphf uses breslow ties method](https://github.com/cran/coxphf/blob/4c2d8368048653497c4110cbc309ef19864168c5/R/coxphf.R#L65) – rawr Jul 22 '16 at 00:21
  • To extend the comment of @rawr, try adding the argument `ties = "breslow"` when you call the `coxph` object. Default is: `ties = "efron"` – StatMan Jul 25 '16 at 08:04

0 Answers0