Displaying 1 result from an estimated 1 matches for "timeft".
Did you mean:
time_t
2009 Oct 27
2
cox regression extract strata as numeric
..."straft.ln"
ft.ln <- coxph(Surv(times,deaths)~ages+chemos+chemos:f1+chemos:f2+horms+horms:f1+horms:f2+grades+grades:f1+grades:f2+positives+positives:f1+positives:f2+sizes+sizes:f1+sizes:f2+strata(stra),data=ddd)
basehazzft.ln=basehaz(ft.ln,centered=FALSE)
H0ft.ln=c(basehazzft.ln[,1])
timeft.ln=c(basehazzft.ln[,2])
straft.ln=c(basehazzft.ln[,3])
I notice that basehazzft.ln[,3] is not the same with straft.ln with respect to the values i.e.:
(basehazzft.ln$stra[1])
[1] stra=1
134 Levels: stra=1 stra=10 stra=100 stra=101 stra=102 ... stra=99
> c(basehazzft.ln$stra[1])
[1] 1
so far...