[R] using newdata in survfit with categorical variable

Zhixin Liu zliu at efs.mq.edu.au
Tue Nov 11 01:58:01 CET 2008


Hi R-helpers,

I was trying to put gender='Male'  in newdata to create a expected survival curve for a pseudo cohort by using survfit based on Cox regression. My codes are shown below: 

fit<- coxph(Surv(end, status2)~gender, data=wlwsn1)
Summary(fit) 
                     coef exp(coef) se(coef)    z     p
genderMale 0.204      1.23   0.0912 2.23 0.025

temp<-data.frame(gender='Male)
wlwsn1curve<-survfit(fit, newdata=temp)
Then I got error message: 
Error in `contrasts<-`(`*tmp*`, value = "contr.treatment") : 
  contrasts can be applied only to factors with 2 or more levels

I do not know what this error message indicates, do I have to recode gender to 0,1 to get it through?

Many thanks

Zhixin



More information about the R-help mailing list