Frailty models (Survival package) mismatch SE

[csthiago]

Hi all,
I really enjoy the easystats suite, really great work!

I noticed the model_parameters is extracting the wrong SE value from cox models with frailty terms.
Please see below:

library(survival)
library(parameters)

rfit2a <- coxph(Surv(time, status) ~ rx +
                  frailty.gaussian(litter, df=13, sparse=FALSE), rats,
                subset= (sex=='f'))
summary(rfit2a)$coef

model_parameters(rfit2a,
                 exponentiate = F,
                 digits=4)

It seems to be extracting the se2 value instead se(coef).

Similar problems with coxph(...robust=T). This one I don't know if it is the intended behaviour or not- always extract the se(coef)

rfit_f <- coxph(Surv(time, status) ~ rx, rats,
                subset= (sex=='f'),
                robust = T)
summary(rfit_f)$coef

model_parameters(rfit_f,
exponentiate = F,
digits=4)

Best wishes,
Thiago

[strengejacke]

Thanks for reporting. The 2nd issue seems to be fixed with #1189.
Will look into the first one.