Dear list,
I ran a conditional frailty model with an interaction term (see below). To
interpret the interaction term, I would like to produce plots that reflect
how does a moderator variable (ecogr) shape the effect of the other
interacted variable (elderly).
condfrailty.gamma.em <-coxph(Surv(evst,evdur,pere) ~ ecogr+ elderly+
elderly_ecogr+strata(strata)+
frailty(country,distribution="gamma",method="em"),
method=c("efron"),data=ret)
summary(condfrailty.gamma.em)
plot(condfrailty.gamma.em,fun=cumhaz, lty=1, ylab=,xlab=,ylim=c(0,4))
However, the plot command after this function only produces the hazard rate
for each event strata. Is there a syntax to produce a single hazard rate for
all the strata?
Moreover, is it possible to obtain hazard rates for specific ranges in the
independent variables? I would like to produce two plots. Plot #1 would
provide the rates when ecogr is below its mean and elderly is,
respectively, one standard deviation above and one below its mean.Plot #2
would provide the rates when ecogr is above its mean and elderly is,
respectively, one standard deviation above and below its mean.
Thanks,
Juan
[[alternative HTML version deleted]]
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
