rocscore: Compute area under ROC curve

In kuwisdelu/matter: Out-of-core statistical computing and signal processing

Compute area under ROC curve

Description

Calculate the area under the receiver operating characteristic curve (ROC AUC).

Usage

rocscore(x, ref, n = 32L)

Arguments

x	The prediction scores.
ref	The (logical) binary response.
n	The number of points in the curve.

Value

A single number between 0 and 1 giving the ROC AUC, with an attribute called ROC which is a data frame giving the full ROC curve.

Author(s)

Kylie A. Bemis

Examples

set.seed(1)
x <- runif(100)
y <- ifelse(x > 0.5 & runif(100) > 0.2, TRUE, FALSE)
rocscore(x, y)

kuwisdelu/matter documentation built on Oct. 19, 2024, 10:31 a.m.