mcc: Matthew's correlation coefficient

In EU-ECDC/HerpesZosterModel: ZM

Description

Matthew's correlation coefficient (MCC) is given by

MCC = (TP \cdot TN - FP \cdot FN) / (√((TP + FP)(TP + FN)(TN + FP)(TN + FN)))

where TP denotes true positives, TN denotes true negatives, FP denotes false positives, and FN denotes false negatives.

Usage

mcc(tp, tn, fp, fn, ...)

Arguments

tp	True positives
tn	True negatives
fp	False positives
fn	False negatives

Details

It is considered to be better than F1 and Rand index (accuracy) for binary classification \insertCite@see @Chicco2017 for detailszostmod.

References

\insertRef

Chicco2017zostmod

See Also

f1() rand()

Other classification scores: auc, bcr, brier, dor, dp, err, et, f1, fai, fm, gain, gl, gm, ignr, jacc, kappa, lr, op, rand, rt, rus, sm, ss, tss

Examples

mcc(tp = 45, fp = 15, fn = 25, tn = 15)

EU-ECDC/HerpesZosterModel documentation built on July 7, 2019, 2:58 a.m.