You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
For some reason on this specific dataset the CI of precision with a threshold of 1 is NA.
When calculating the ci.coords with several thresholds, the following error occurs:
> load("roc_error.RData")
> ci.coords(pROC_obj_with_ci, x=c(.5, 1), ret="precision", transpose=TRUE)
|======================================================================| 100%
Error in apply(sapply(perfs, c), 1, quantile, probs = c(0 + (1 - conf.level)/2, :
dim(X) must have a positive length
In addition: Warning message:
In ci.coords.roc(pROC_obj_with_ci, x = c(0.5, 1), ret = "precision", :
NA value(s) produced during bootstrap were ignored.