Entering edit mode
4.2 years ago
huynguyen96.dnu
▴
50
Hi there, I have just constructed my own nomogram using cph function. Next, I compute C-index through D_xy value using the function validate of the package rms . It looks like:
survival rate
mod.cox <- cph(formula = Surv(time, status) ~ age + weight,
data=train, x= TRUE, y= TRUE, surv = TRUE)
Get the D_xy
v <- validate(mod.cox, dxy=TRUE, B=1000)
v
Compute C-index
Dxy = v[rownames(v)=="Dxy", colnames(v)=="index.corrected"]
The c-statistic according to the Dxy=2(c-0.5)
round(Dxy/2+0.5,3) #~0.5938927
So, I had C-index = 0.594. I wonder how can I get 95%CI from this?
