cox regression with non binary covariates

General
1

Hi,
I'm running a cox model regression with a covariate that has three categories (3 time periods: 0,1 or 2). I'm running it in a univariate model first like this:
model <- coxph(Surv(time1, time2, treatment) ~ period, data = two, ties="efron")

The results I get (see below) do not seem to take into account that there are 3 categories? Is there a way I can specify this?

     coef exp(coef) se(coef)     z Pr(>|z|)

period 0.2225 1.2491 0.1764 1.261 0.207

   exp(coef) exp(-coef) lower .95 upper .95

period 1.249 0.8005 0.884 1.765

Thank you!

2

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.