AUC: AUC

Description

Compute the Area Under the ROC Curve (AUC) of a predictor and possibly its 95% confidence interval.

Usage

AUC(pred, target, digits = NULL)
AUCBoot(pred, target, nboot = 10000, seed = NA, digits = NULL)

Value

The AUC, a probability, and possibly its 2.5% and 97.5% quantiles (95% CI).

Arguments

pred: Vector of predictions.
target: Vector of true labels (must have exactly two levels, no missing values).
digits: See round. Default doesn't use rounding.
nboot: Number of bootstrap samples used to evaluate the 95% CI. Default is 1e4.
seed: See set.seed. Use it for reproducibility. Default doesn't set any seed.

Details

Other packages provide ways to compute the AUC (see this answer). I chose to compute the AUC through its statistical definition as a probability: $$P(score(x_{case}) > score(x_{control})).$$ Note that I consider equality between scores as a 50%-probability of one being greater than the other.

Examples

Run this code

set.seed(1)

AUC(c(0, 0), 0:1) # Equality of scores
AUC(c(0.2, 0.1, 1), c(0, 0, 1)) # Perfect AUC
x <- rnorm(100)
z <- rnorm(length(x), x, abs(x))
y <- as.numeric(z > 0)
print(AUC(x, y))
print(AUCBoot(x, y))

# Partial AUC
pAUC <- function(pred, target, p = 0.1) {
  val.min <- min(target)
  q <- quantile(pred[target == val.min], probs = 1 - p)
  ind <- (target != val.min) | (pred > q)
  bigstatsr::AUC(pred[ind], target[ind]) * p
}
pAUC(x, y)
pAUC(x, y, 0.2)