The Chi-Square Test of Distance Correlation

Abstract

Distance correlation has gained much recent attention in the data science community: the sample statistic is straightforward to compute and asymptotically equals zero if and only if independence, making it an ideal choice to discover any type of dependency structure given sufficient sample size. One major bottleneck is the testing process: because the null distribution of distance correlation depends on the underlying random variables and metric choice, it typically requires a permutation test to estimate the null and compute the p-value, which is very costly for large amount of data. To overcome the difficulty, in this paper we propose a chi-square test for distance correlation. Method-wise, the chi-square test is non-parametric, extremely fast, and applicable to bias-corrected distance correlation using any strong negative type metric or characteristic kernel. The test exhibits a similar testing power as the standard permutation test, and can be utilized for K-sample and partial testing. Theory-wise, we show that the underlying chi-square distribution well approximates and dominates the limiting null distribution in upper tail, prove the chi-square test can be valid and universally consistent for testing independence, and establish a testing power inequality with respect to the permutation test.

arXiv comment21 pages, 4 figures, 1 table

References in corpus (11)

• Measuring and testing dependence by correlation of distances
• Brownian distance covariance
• Equivalence of distance-based and RKHS-based statistics in hypothesis testing
• A consistent multivariate test of association based on ranks of distances
• Distance covariance in metric spaces
• DISCO analysis: A nonparametric extension of analysis of variance
• Large-Scale Kernel Methods for Independence Testing
• A fast algorithm for computing distance correlation
• From Distance Correlation to Multiscale Graph Correlation
• Discovering and Deciphering Relationships Across Disparate Data Modalities
• The Exact Equivalence of Distance and Kernel Methods for Hypothesis Testing

Cited by in corpus (9)

• The Exact Equivalence of Distance and Kernel Methods for Hypothesis Testing
• hyppo: A Multivariate Hypothesis Testing Python Package
• Synergistic Graph Fusion via Encoder Embedding
• Universally Consistent K-Sample Tests via Dependence Measures
• The FEDHC Bayesian network learning algorithm
• Discovering the Signal Subgraph: An Iterative Screening Approach on Graphs
• Multiscale Comparative Connectomics
• Adaptation of the Phase Distance Correlation Periodogram to Account for Measurement Uncertainties
• Model Independent Periodogram for Scanning Astrometry