This function outputs a calibrated significance level based on coverage of prediction intervals generated using oob collections. Primarily for use in RoyRF().
calibrate(
oob,
alpha = 0.1,
response_data,
tolerance = 0.025,
step_percent = 0.618,
undercoverage = FALSE,
method = "quantile",
max_iter = 10
)collection of oob predictions for training data (in list form).
nominal significance level. Defaults to 0.01.
response data of class data.frame. Must have names() attribute.
tolerance allowed around nominal alpha. Default is 0.25.
ratio absolute difference between empirical oob coverage and nominal coverage to adjust when calibrating. Defaults to 0.618.
Allow undercoverage. Defaults to TRUE. Not currently implemented.
Method to calibrate prediction intervals with. Defaults to "quantile"). Current only "quantile" implemented.
Maximum number of iterations. Defaults to 10.