approxAUC: Approximate AUC

In nfultz/stackoverflow: Stack Overflow's Greatest Hits

Description

AUC can be computed exactly by sorting the fitted values, which is often computationally slow. Instead, we can approximate the AUC numerically using monte carlo.

Usage

approxAUC(y, yhat, n = 1000)

Arguments

y	the actual class labels [0-1]
yhat	the predicted probabilities
n	number of samples to draw

Author(s)

erik, Neal Fultz

References

http://stackoverflow.com/questions/4903092/calculate-auc-in-r

Examples

g <- glm(y~x,data=data.frame(x=1:10,y=1:10))
classMethods(g)

nfultz/stackoverflow documentation built on Aug. 4, 2020, 5:31 a.m.