auROC {limma}R Documentation

Area Under Receiver Operating Curve

Description

Compute exact area under the ROC for empirical data.

Usage

auROC(truth, stat)

Arguments

truth numeric vector of 0 and 1 indicating whether the null or alternative respectively is true for each case. If stat is missing then truth is assuming to be already sorted in decreasing test statistic order.
stat numeric vector containing test statistics. Hypotheses are to be rejected if stat exceeds a given threshold.

Details

This function computes the exact area under an empirical ROC curve. The number of true and false discoveries are determined by how well the true states represented by truth match up with the observed statistics given by stat.

Value

Numeric vector giving area under the curve, 1 being perfect and 0 being the minimum, or NULL if truth has zero length.

Author(s)

Gordon Smyth

See Also

See 08.Tests for other functions for testing and processing p-values.

See also AUC in the ROC package.

Examples

auROC(c(1,1,0,0,0))
truth <- rbinom(30,size=1,prob=0.2)
stat <- rchisq(30,df=2)
auROC(truth,stat)

[Package limma version 2.4.7 Index]