Compute standard error estimates for estimates of variable importance.
vimp_se(
est,
update,
denom = NULL,
n = length(update),
scale = "log",
na.rm = FALSE
)the estimate of variable importance.
the influence curve-based update.
a list of point estimate and influence curve for the denominator (if any) to make the measure of predictiveness interpretable.
the sample size.
the scale to compute SEs on (either "log", for log-scale, or "identity", for same scale as point estimate).
logical; should NA's be removed in computation? (defaults to FALSE).
The standard error for the estimated variable importance for the given group of left-out covariates.
See the paper by Williamson, Gilbert, Simon, and Carone for more details on the mathematics behind this function and the definition of the parameter of interest.