Generalized R-squared for detecting dependence

DOI10.1093/BIOMET/ASW071MaRDI QIDQ5384448zbMATH OpenOpenAlexWikidataFDO

Authors Xufei Wang, Bo Jiang, Jun S. Liu

Publication date 24 June 2019

Published in Biometrika (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1604.02736

zbMATH Keywords

Bayes factorcoefficient of determinationhypothesis testlikelihood ratio

Mathematics Subject Classification ID

Bayesian inference (62F15) Nonparametric hypothesis testing (62G10) Measures of association (correlation, canonical correlation, etc.) (62H20)

Abstract: Detecting dependence between two random variables is a fundamental problem. Although the Pearson correlation is effective for capturing linear dependency, it can be entirely powerless for detecting nonlinear and/or heteroscedastic patterns. We introduce a new measure, G-squared, to test whether two univariate random variables are independent and to measure the strength of their relationship. The G-squared is almost identical to the square of the Pearson correlation coefficient, R-squared, for linear relationships with constant error variance, and has the intuitive meaning of the piecewise R-squared between the variables. It is particularly effective in handling nonlinearity and heteroscedastic errors. We propose two estimators of G-squared and show their consistency. Simulations demonstrate that G-squared estimates are among the most powerful test statistics compared with several state-of-the-art methods.

Recommendations

• A measure of general functional dependence between two continuous variables
• Recognizing and visualizing departures from independence in bivariate data using local Gaussian correlation
• Measuring and testing dependence by correlation of distances
• Measuring dependence powerfully and equitably
• scientific article; zbMATH DE number 472957

Cited in

(17)

• A new coefficient of correlation
• An empirical study of the maximal and total information coefficients and leading measures of dependence
• Equitability, interval estimation, and statistical power
• Validation of association
• Expected conditional characteristic function-based measures for testing independence
• Fisher Exact Scanning for Dependency
• The Hellinger Correlation
• Generalizing R² for deming regressions
• The Binary Expansion Randomized Ensemble Test
• Exact detection thresholds and minimax optimality of Chatterjee's correlation coefficient
• Measures of conditional dependence for nonlinearity, asymmetry and beyond
• A survey of some recent developments in measures of association
• Dissecting Gene Expression Heterogeneity: Generalized Pearson Correlation Squares and the K -Lines Clustering Algorithm
• Varying Coefficient Model via Adaptive Spline Fitting
• Kernel copula density estimation of Hellinger correlation
• Lancaster correlation: a new dependence measure linked to maximum correlation
• Detecting dependence structure: visualization and inference

This page was built for publication: Generalized R-squared for detecting dependence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5384448)