Pearson-Matthews correlation coefficients for binary and multinary classification and hypothesis testing

TL;DR

This paper reviews and extends the Pearson-Matthews correlation coefficient (MCC) for binary and multinary classification, introducing new metrics that improve the indication of poor classification performance.

Contribution

The paper introduces three new metrics for multinary classification that address limitations of existing MCC extensions, enhancing performance evaluation accuracy.

Findings

Existing MCC extensions can fail to indicate poor results.

New metrics provide more decisive assessment of classification quality.

Extensions of MCC improve evaluation for multinary tasks.

Abstract

The Pearson-Matthews correlation coefficient (usually abbreviated MCC) is considered to be one of the most useful metrics for the performance of a binary classification or hypothesis testing method (for the sake of conciseness we will use the classification terminology throughout, but the concepts and methods discussed in the paper apply verbatim to hypothesis testing as well). For multinary classification tasks (with more than two classes) the existing extension of MCC, commonly called the $\text{R}_{\text{K}}$ metric, has also been successfully used in many applications. The present paper begins with an introductory discussion on certain aspects of MCC. Then we go on to discuss the topic of multinary classification that is the main focus of this paper and which, despite its practical and theoretical importance, appears to be less developed than the topic of binary classification. Our discussion of the $\text{R}_{\text{K}}$ is followed by the introduction of two other metrics for multinary classification derived from the multivariate Pearson correlation (MPC) coefficients. We show that both $\text{R}_{\text{K}}$ and the MPC metrics suffer from the problem of not decisively indicating poor classification results when they should, and introduce three new enhanced metrics that do not suffer from this problem. We also present an additional new metric for multinary classification which can be viewed as a direct extension of MCC.