On asymptotic efficiency of multivariate version of Spearman's rho

2009/06/05 by Alexander I. Nazarov, Alexander Nazarov, Nazarov, Alexander +2
Computer Science · Mathematics · #Advanced Statistical Methods and Models #Bayesian Methods and Mixture Models #Statistical Methods and Inference #math.PR #math.ST #msc:62G10 #msc:62G20 #stat.TH

paper · pdf · doi:10.48550/arxiv.0906.1059

18 pages

arxiv created 2009/06/05 · arxiv updated 2009/12/01

Abstract

A multivariate version of Spearman's rho for testing independence is considered. Its asymptotic efficiency is calculated under a general distribution model specified by the dependence function. The efficiency comparison study that involves other multivariate Spearman-type test statistics is made. Conditions for Pitman optimality of the test are established. Examples that illustrate the quality of the multivariate Spearman's test are included.

Citations

• The Proof and Measurement of Association between Two Things

Related

• Asymptotic relative efficiency of the Kendall and Spearman correlation statistics
• Distribution-free tests of multivariate independence based on center-outward quadrant, Spearman, Kendall, and van der Waerden statistics
• Nonparametric estimation of the multivariate Spearman's footrule: a further discussion
• The Spearman-Brown Formula and Reliabilities of Random Test Forms
• Bahadur efficiency of nonparametric test for independence based on L₁-error