A unified approach to constructing correlation coefficients between random variables

Characterization and structure theory for multivariate probability distributions; copulas (62H05) Measures of association (correlation, canonical correlation, etc.) (62H20) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: Measuring the correlation (association) between two random variables is one of the important goals in statistical applications. In the literature, the covariance between two random variables is a widely used criterion in measuring the linear association between two random variables. In this paper, first we propose a covariance based unified measure of variability for a continuous random variable X and we show that several measures of variability and uncertainty, such as variance, Gini mean difference, cumulative residual entropy, etc., can be considered as special cases. Then, we propose a unified measure of correlation between two continuous random variables X and Y, with distribution functions (DFs) F and G, based on the covariance between X and H^{-1}G(Y) (known as the Q-transformation of H on G) where H is a continuous DF. We show that our proposed measure of association subsumes some of the existing measures of correlation. Under some mild condition on H, it is shown the suggested index ranges between [-1,1] where the extremes of the range, i.e., -1 and 1, are attainable by the Frechet bivariate minimal and maximal DFs, respectively. A special case of the proposed correlation measure leads to a variant of Pearson correlation coefficient which, as a measure of strength and direction of the linear relationship between X and Y, has absolute values greater than or equal to the Pearson correlation. The results are examined numerically for some well known bivariate DFs.

Review text

Measuring the strength of correlation between two variables or two sets of variables is of vital importance in machine learning. This paper proposes the unified index of correlation between two continuous random variables \(X\) and \(Y\) which leads to new measures of correlations and subsumes some of the existing measures such as the Pearson correlation coefficient and Gini correlation coefficient and its extensions widely employed in random forest theory. The proposed measure is validated on three examples.

Recommendations

Cites work

Cited in

(10)

This page was built for publication: A unified approach to constructing correlation coefficients between random variables

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2189757)