Measure to compare true observed labels with predicted
labels
in binary classification tasks.
Usage
mcc(truth, response, positive, ...)
Value
Performance value as numeric(1).
Arguments
truth
(factor())
True (observed) labels.
Must have the exactly same two levels and the same length as response.
response
(factor())
Predicted response labels.
Must have the exactly same two levels and the same length as truth.
positive
(character(1))
Name of the positive class.
...
(any)
Additional arguments. Currently ignored.
Meta Information
Type: "binary"
Range: \([-1, 1]\)
Minimize: FALSE
Required prediction: response
Details
The Matthews Correlation Coefficient is defined as $$
\frac{\mathrm{TP} \cdot \mathrm{TN} - \mathrm{FP} \cdot \mathrm{FN}}{\sqrt{(\mathrm{TP} + \mathrm{FP}) (\mathrm{TP} + \mathrm{FN}) (\mathrm{TN} + \mathrm{FP}) (\mathrm{TN} + \mathrm{FN})}}.
$$
This above formula is undefined if any of the four sums in the denominator is 0.
The denominator is then set to 1.
References
Matthews BW (1975).
“Comparison of the predicted and observed secondary structure of T4 phage lysozyme.”
Biochimica et Biophysica Acta (BBA) - Protein Structure, 405(2), 442--451.
tools:::Rd_expr_doi("10.1016/0005-2795(75)90109-9").