A simple measure of conditional dependence

DOI10.48550/ARXIV.1910.12327MaRDI QIDQ128731zbMATH OpenOpenAlexFDO

Authors Mona Azadkia, Sourav Chatterjee, Mona Azadkia

Publication date 27 October 2019

Published in The Annals of Statistics (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1910.12327

zbMATH Keywords

variable selectionconditional dependencenonparametric measures of association

Mathematics Subject Classification ID

Nonparametric estimation (62G05) Measures of association (correlation, canonical correlation, etc.) (62H20)

Abstract: We propose a coefficient of conditional dependence between two random variables $Y$ and $Z$ given a set of other variables $X_1,ldots,X_p$, based on an i.i.d. sample. The coefficient has a long list of desirable properties, the most important of which is that under absolutely no distributional assumptions, it converges to a limit in $[0,1]$, where the limit is $0$ if and only if $Y$ and $Z$ are conditionally independent given $X_1,ldots,X_p$, and is $1$ if and only if $Y$ is equal to a measurable function of $Z$ given $X_1,ldots,X_p$. Moreover, it has a natural interpretation as a nonlinear generalization of the familiar partial $R^2$ statistic for measuring conditional dependence by regression. Using this statistic, we devise a new variable selection algorithm, called Feature Ordering by Conditional Independence (FOCI), which is model-free, has no tuning parameters, and is provably consistent under sparsity assumptions. A number of applications to synthetic and real datasets are worked out.

Recommendations

• Dependence measuring from conditional variances
• scientific article; zbMATH DE number 3965211
• scientific article; zbMATH DE number 2234837
• A measure of dependence for stable distributions
• Measurable dependence of conditional measures on a parameter
• Dependency measure for sets of random events or random variables
• A note on two measures of dependence
• A measure of mutual complete dependence
• A measure of multivariate mutual complete dependence

Cites work

• scientific article; zbMATH DE number 3860199 (Why is no real title available?)
• scientific article; zbMATH DE number 4170917 (Why is no real title available?)
• scientific article; zbMATH DE number 46873 (Why is no real title available?)
• scientific article; zbMATH DE number 1022658 (Why is no real title available?)
• scientific article; zbMATH DE number 1052006 (Why is no real title available?)
• scientific article; zbMATH DE number 845714 (Why is no real title available?)
• A NONPARAMETRIC HELLINGER METRIC TEST FOR CONDITIONAL INDEPENDENCE
• A consistent characteristic function-based test for conditional independence
• A copula-based non-parametric measure of regression dependence
• A projection-based conditional dependence measure with applications to high-dimensional undirected graphical models
• An Algorithm for Finding Best Matches in Logarithmic Expected Time
• Asymptotic Minimax Character of the Sample Distribution Function and of the Classical Multinomial Estimator
• Bagging predictors
• Better Subset Regression Using the Nonnegative Garrote
• Conditional Distance Correlation
• Conditional association
• Estimation of a conditional copula and association measures
• Fisher lecture: Dimension reduction in regression
• Least angle regression. (With discussion)
• Measuring multivariate association and beyond
• Model Selection and Estimation in Regression with Grouped Variables
• Multivariate adaptive regression splines
• On a nonparametric notion of residual and its applications
• Panning for Gold: ‘Model-X’ Knockoffs for High Dimensional Controlled Variable Selection
• Partial distance correlation with methods for dissimilarities
• Probability theory of classical Euclidean optimization problems
• Probability. Theory and examples.
• Random forests
• Regularization and Variable Selection Via the Elastic Net
• Relative Entropy Measures of Multivariate Dependence
• Sliced Inverse Regression for Dimension Reduction
• Some Methods for Strengthening the Common χ 2 Tests
• Sparse additive models
• Sufficient dimension reduction and prediction in regression
• Testing conditional independence using maximal nonlinear conditional correlation
• Testing conditional independence via Rosenblatt transforms
• Testing conditional independence via empirical likelihood
• The Adaptive Lasso and Its Oracle Properties
• The Dantzig selector: statistical estimation when \(p\) is much larger than \(n\). (With discussions and rejoinder).
• The Hardness of Conditional Independence Testing and the Generalised Covariance Measure
• The conditional permutation test for independence while controlling for confounders
• The elements of statistical learning. Data mining, inference, and prediction
• The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality
• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties

Cited in

(57)

• General tests of conditional independence based on empirical processes indexed by functions
• Measures of conditional dependence for nonlinearity, asymmetry and beyond
• High-dimensional copula-based Wasserstein dependence
• Feature selection from local lift dependence-based partitions
• Four simple axioms of dependence measures
• On a multivariate copula-based dependence measure and its estimation
• On propensity score matching with a diverging number of matches
• On the asymptotic null distribution of the symmetrized Chatterjee's correlation coefficient
• Local permutation tests for conditional independence
• Test and Measure for Partial Mean Dependence Based on Machine Learning Methods
• Anytime-Valid Tests of Conditional Independence Under Model-X
• The improved correlation coefficient of Chatterjee
• Testing for selectivity in the dependence of random variables on external factors
• Hierarchical variable clustering based on the predictive strength between random vectors
• Nonlinear directed acyclic graph estimation based on the kernel partial correlation coefficient
• Azadkia-Chatterjee's correlation coefficient adapts to manifold data
• Global sensitivity analysis: a novel generation of mighty estimators based on rank statistics
• Dependence properties of bivariate copula families
• Large-scale multiple inference of collective dependence with applications to protein function
• On a general theoretical framework of reliability
• Adapted Chatterjee correlation coefficient
• High-dimensional missing data imputation via undirected graphical model
• On relationships between Chatterjee’s and Spearman’s correlation coefficients
• Quantifying and estimating dependence via sensitivity of conditional distributions
• Conditional association
• The exact region and an inequality between Chatterjee's and Spearman's rank correlations
• Azadkia-Chatterjee's dependence coefficient for infinite dimensional data
• Test of conditional independence in factor models via Hilbert-Schmidt independence criterion
• Asymptotic expected sensitivity function and its applications to measures of monotone association
• FOCI
• A dimension reduction for extreme types of directed dependence
• The Binary Expansion Randomized Ensemble Test
• Doubly robust conditional independence testing with generative neural networks
• Compositional data graphical model learning based on conditional independence measurement
• Distribution-free tests of multivariate independence based on center-outward quadrant, Spearman, Kendall, and van der Waerden statistics
• A projection-based conditional dependence measure with applications to high-dimensional undirected graphical models
• Factor Importance Ranking and Selection Using Total Indices
• Nonparametric Bayes inference on conditional independence
• A probabilistic classification method based on conditional independences
• Comparison results for positive supermodular dependent Markov tree distributions
• Copula modeling from Abe Sklar to the present day
• Quantifying directed dependence via dimension reduction
• On Azadkia-Chatterjee's conditional dependence coefficient
• Exact detection thresholds and minimax optimality of Chatterjee's correlation coefficient
• Conditional expectation estimation through attributable components
• Maximal asymmetry of bivariate copulas and consequences to measures of dependence
• A survey of some recent developments in measures of association
• A fishing route optimization decision support system: the case of the tuna purse seiner
• A new algorithm for variable selection in general linear models
• A Class of Regression Association Measures based on Concordance
• A Kernel Measure of Dissimilarity between M Distributions
• A simple bias reduction for Chatterjee's correlation
• A simple bootstrap for Chatterjee's rank correlation
• A robust-equitable measure for feature ranking and selection
• On universally consistent and fully distribution-free rank tests of vector independence
• Quantile generalized measures of correlation
• Model-free variable selection in high dimension via constrained kernel regression

This page was built for publication: A simple measure of conditional dependence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q128731)