-
-
Notifications
You must be signed in to change notification settings - Fork 136
Description
Summary:
Questions about stan_surv function.
Description:
I want to utilize stan_surv to explore various variables' (including time-fixed covariate and time-varying covariate) impact on survival time. And the manual suggests give us examples of time-fixed covariate and time-varying covariate situations like this:
mod1 <- stan_surv(formula = Surv(recyrs, status) ~ group, data = bcancer, chains = CHAINS, cores = CORES, seed = SEED, iter = ITER)
and
mod_tvc <- stan_surv( formula = Surv(tstart, tstop, death) ~ log(bili) + log(protime), data = dat, chains = CHAINS, cores = CORES, seed = SEED, iter = ITER)
Time-fixed covariate and time-varying covariate are analyzed separately, and the model for time-varying covariates has a "start-stop" time structure.
Here I would like to ask that if I have time-fixed covariate and time-varying covariate at the same time, should I separate them? Moreover, the model for time-fixed covariate only contains one covariate, if I have a few covariates, should I separate them or put them together?
Looking forward to your answer and appreciate it!