Quantifying directed dependence via dimension reduction

DOI10.1016/J.JMVA.2023.105266MaRDI QIDQ6200940zbMATH OpenOpenAlexFDO

Authors Sebastian Fuchs

Publication date 25 March 2024

Published in Journal of Multivariate Analysis (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2112.10147

zbMATH Keywords

copulasSpearman's footruleSpearman's rank correlationMarkov productcopula correlationdirected dependence

Mathematics Subject Classification ID

Measures of association (correlation, canonical correlation, etc.) (62H20) Characterization and structure theory of statistical distributions (62E10)

Abstract: Studying the multivariate extension of copula correlation yields a dimension reduction principle, which turns out to be strongly related with the `simple measure of conditional dependence' $T$ recently introduced by Azadkia & Chatterjee (2021). In the present paper, we identify and investigate the dependence structure underlying this dimension-reduction principle, provide a strongly consistent estimator for it, and demonstrate its broad applicability. For that purpose, we define a bivariate copula capturing the scale-invariant extent of dependence of an endogenous random variable $Y$ on a set of $dgeq1$ exogenous random variables $$, and containing the information whether $Y$ is completely dependent on $$, and whether $Y$ and $$ are independent. The dimension reduction principle becomes apparent insofar as the introduced bivariate copula can be viewed as the distribution function of two random variables $Y$ and $Y^{p}rime$ sharing the same conditional distribution and being conditionally independent given $$. Evaluating this copula uniformly along the diagonal, i.e. calculating Spearman's footrule, leads to Azadkia and Chatterjee's `simple measure of conditional dependence' $T$. On the other hand, evaluating this copula uniformly over the unit square, i.e. calculating Spearman's rho, leads to a distribution-free coefficient of determination (a.k.a. copula correlation). Several real data examples illustrate the importance of the introduced methodology.

Cites work

• scientific article; zbMATH DE number 1713116 (Why is no real title available?)
• scientific article; zbMATH DE number 4170917 (Why is no real title available?)
• scientific article; zbMATH DE number 1134711 (Why is no real title available?)
• A Note on Directional Dependence in Regression Setting
• A copula-based non-parametric measure of regression dependence
• A new coefficient of correlation
• A simple measure of conditional dependence
• An introduction to copulas.
• Conditioning-based metrics on the space of multivariate copulas and their interrelation with uniform and levelwise convergence and iterated function systems
• Copula-Based Regression Estimation and Inference
• Copula-induced measures of concordance
• Copulas and Markov processes
• Correlation and Complete Dependence of Random Variables
• Detecting novel associations in large data sets
• Distance multivariance: new dependence measures for random vectors
• Estimating scale-invariant directed dependence of bivariate distributions
• Estimators based on Kendall's tau in multivariate copula models
• Extremes of nonexchangeability
• Global sensitivity analysis: a novel generation of mighty estimators based on rank statistics
• How simplifying and flexible is the simplifying assumption in pair-copula constructions -- analytic answers in dimension three and a glimpse beyond
• Idempotent and multivariate copulas with fractal support
• Linkages: A tool for the construction of multivariate distributions with given nonoverlapping multivariate marginals
• Maximal non-exchangeability in dimension d
• Maximum asymmetry of copulas revisited
• Measuring and testing dependence by correlation of distances
• Multivariate concordance
• Multivariate copulas: transformations, symmetry, order and measures of concordance
• Multivariate extensions of Spearman's rho and related statistics
• Multivariate measures of concordance for copulas and their marginals
• On Conditionally Independent Random Variables, Copula and Order Statistics
• On a multivariate copula-based dependence measure and its estimation
• On a strong metric on the space of copulas and its induced dependence measure
• On distributions with fixed marginals maximizing the joint or the prior default probability, estimation, and related results
• On the asymptotic distribution of a general measure of monotone dependence
• On the copula correlation ratio and its generalization
• On weak conditional convergence of bivariate Archimedean and extreme value copulas, and consequences to nonparametric estimation
• Principles of copula theory
• Reflection invariant copulas
• Some comments on copula-based regression
• Spearman's footrule and Gini's gamma: a review with complements
• The Bertino family of copulas
• Total positivity of copulas from a Markov kernel perspective
• Wahrscheinlichkeitstheorie

Cited in

(11)

• High-dimensional copula-based Wasserstein dependence
• Hierarchical variable clustering based on the predictive strength between random vectors
• On bivariate lower semilinear copulas and the star product
• Azadkia-Chatterjee's correlation coefficient adapts to manifold data
• Quantifying and estimating dependence via sensitivity of conditional distributions
• The exact region and an inequality between Chatterjee's and Spearman's rank correlations
• A dimension reduction for extreme types of directed dependence
• On the exact region between Chatterjee's rank correlation and Spearman's footrule
• Measuring multivariate regression association via spatial sign
• On exact regions between measures of concordance and Chatterjee's rank correlation for lower semilinear copulas
• A Class of Regression Association Measures based on Concordance

This page was built for publication: Quantifying directed dependence via dimension reduction

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6200940)