determineCut: determine best Accuracy cuttoff

Description Usage Arguments Examples

View source: R/roc.R

Description

determine best Accuracy cuttoff

Usage

1
determineCut(cases, controls, plot = FALSE, scanstep = 0.01)

Arguments

cases

a factor of predicted classes

controls

a factor of classes to be used as the true results

plot

create plot of threasholds versus Accuracy

scanstep

step size for threshold estimation

Examples

1
2
3
4
5
library(pROC)
cases <- rnorm(100,-1,1.1)
controls <- rnorm(500,1,1.1)
cut <- determineCut(cases,controls)
makeROCplot(cases,controls,abline=cut)

quantable documentation built on May 2, 2019, 4:05 p.m.