The Chi-Square Test of Distance Correlation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Cencheng, Panda, Sambit, Vogelstein, Joshua T.
Format: Preprint
Published: 2019
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916300262998016
author Shen, Cencheng
Panda, Sambit
Vogelstein, Joshua T.
author_facet Shen, Cencheng
Panda, Sambit
Vogelstein, Joshua T.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_1912_12150
institution arXiv
publishDate 2019
record_format arxiv
spellingShingle The Chi-Square Test of Distance Correlation
Shen, Cencheng
Panda, Sambit
Vogelstein, Joshua T.
Machine Learning
Statistics Theory
Methodology
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.
title The Chi-Square Test of Distance Correlation
topic Machine Learning
Statistics Theory
Methodology
url https://arxiv.org/abs/1912.12150