A consistent test of independence based on a sign covariance related to Kendall's tau

Abstract

The most popular ways to test for independence of two ordinal random variables are by means of Kendall's tau and Spearman's rho. However, such tests are not consistent, only having power for alternatives with ``monotonic'' association. In this paper, we introduce a natural extension of Kendall's tau, called ${\tau }^{\ast }$, which is non-negative and zero if and only if independence holds, thus leading to a consistent independence test. Furthermore, normalization gives a rank correlation which can be used as a measure of dependence, taking values between zero and one. A comparison with alternative measures of dependence for ordinal random variables is given, and it is shown that, in a well-defined sense, ${\tau }^{\ast }$ is the simplest, similarly to Kendall's tau being the simplest of ordinal measures of monotone association. Simulation studies show our test compares well with the alternatives in terms of average $p$-values.

Published in at http://dx.doi.org/10.3150/13-BEJ514 the Bernoulli (http://isi.cbs.nl/bernoulli/) by the International Statistical Institute/Bernoulli Society (http://isi.cbs.nl/BS/bshome.htm)

References in corpus (5)

• Measuring and testing dependence by correlation of distances
• 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
• A new correlation coefficient, its orthogonal decomposition and associated tests of independence

Cited by in corpus (18)

• Asymptotic Distributions of High-Dimensional Distance Correlation Inference
• Nonparametric testing of conditional independence by means of the partial copula
• Counting Small Permutation Patterns
• A principle feature analysis
• On the power of Chatterjee rank correlation
• Lower bound on the size of a quasirandom forcing set of permutations
• High dimensional consistent independence testing with maxima of rank correlations
• copent: Estimating Copula Entropy and Transfer Entropy in R
• Generalizing Distance Covariance to Measure and Test Multivariate Mutual Dependence
• Generalized kernel distance covariance in high dimensions: non-null CLTs and power universality
• Patterns in Random Permutations
• Randomized incomplete $U$-statistics in high dimensions
• Distance Metrics for Measuring Joint Dependence with Application to Causal Inference
• independence: Fast Rank Tests
• Efficient Computation of the Bergsma-Dassios Sign Covariance
• A Distribution-Free Test of Independence and Its Application to Variable Selection
• Symmetric Rank Covariances: a Generalised Framework for Nonparametric Measures of Dependence
• An AUK-based index for measuring and testing the joint dependence of a random vector