Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wu, Shengjun, Wu, Jeffery
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.18653
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914496125075456
author Wu, Shengjun
Wu, Jeffery
author_facet Wu, Shengjun
Wu, Jeffery
contents Analyzing correlation between variables is often both the tool and the goal of modern science. A crucial question is whether the correlation between two variables is a direct correlation or only an indirect correlation through a confounder. We review the existing measures of direct correlation and organize them into two families, each corresponding to a systematic construction: (i) removing the direct correlation from the original joint distribution and quantifying the resulting distributional shift, and (ii) intervening on one variable via do-calculus and quantifying how the distribution of the other variable responds. For every Kullback--Leibler-based measure in either family, we propose a Jensen--Shannon-based regularized analogue. Since the square root of the Jensen--Shannon divergence is a bounded metric, the regularized measures take values in $[0,1]$ and are free of the singularity of the Kullback--Leibler divergence. We further analyze the achievable upper bound of each regularized measure under the observed marginal $p(x,z)$, which depends on the alphabet size and is in general strictly below $1$; this sets the correct scale against which observed values should be read. The properties and the differences of the proposed measures are illustrated on a decision-making toy model and on three public real datasets: Titanic survival, UCI Adult (Census Income), and the UC~Berkeley 1973 graduate admissions. Bootstrap $95\%$ confidence intervals are reported for every numerical value.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18653
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle How to quantify direct correlations between variables
Wu, Shengjun
Wu, Jeffery
Methodology
Physics and Society
Analyzing correlation between variables is often both the tool and the goal of modern science. A crucial question is whether the correlation between two variables is a direct correlation or only an indirect correlation through a confounder. We review the existing measures of direct correlation and organize them into two families, each corresponding to a systematic construction: (i) removing the direct correlation from the original joint distribution and quantifying the resulting distributional shift, and (ii) intervening on one variable via do-calculus and quantifying how the distribution of the other variable responds. For every Kullback--Leibler-based measure in either family, we propose a Jensen--Shannon-based regularized analogue. Since the square root of the Jensen--Shannon divergence is a bounded metric, the regularized measures take values in $[0,1]$ and are free of the singularity of the Kullback--Leibler divergence. We further analyze the achievable upper bound of each regularized measure under the observed marginal $p(x,z)$, which depends on the alphabet size and is in general strictly below $1$; this sets the correct scale against which observed values should be read. The properties and the differences of the proposed measures are illustrated on a decision-making toy model and on three public real datasets: Titanic survival, UCI Adult (Census Income), and the UC~Berkeley 1973 graduate admissions. Bootstrap $95\%$ confidence intervals are reported for every numerical value.
title How to quantify direct correlations between variables
topic Methodology
Physics and Society
url https://arxiv.org/abs/2604.18653