Alternatives to Pearson's and Spearman's Correlation Coefficients

TL;DR

This paper explores alternative correlation measures to Pearson's and Spearman's coefficients, demonstrating that combined approaches can yield better results especially when rank information is more significant than actual values.

Contribution

It introduces new mixture-based correlation methods that outperform traditional coefficients in specific scenarios involving rank importance.

Findings

Mixture correlations outperform traditional coefficients in rank-sensitive samples.

Proposed methods provide more accurate correlation estimates in discrete variable contexts.

Examples illustrate the effectiveness of the alternatives over classical measures.

Abstract

This article presents several alternatives to Pearson's correlation coefficient and many examples. In the samples where the rank in a discrete variable counts more than the variable values, the mixtures that we propose of Pearson's and Spearman's correlation coefficients give better results.