Nonparametric multivariate rank tests and their unbiasedness

DOI10.3150/10-BEJ326zbMATH Open1291.62095arXiv1203.0450OpenAlexW2109530652MaRDI QIDQ408099FDOQ408099

Authors: Jan Kalina, Jana Jurečková 

Publication date: 29 March 2012

Published in: Bernoulli (Search for Journal in Brave)

Abstract: Although unbiasedness is a basic property of a good test, many tests on vector parameters or scalar parameters against two-sided alternatives are not finite-sample unbiased. This was already noticed by Sugiura [Ann. Inst. Statist. Math. 17 (1965) 261--263]; he found an alternative against which the Wilcoxon test is not unbiased. The problem is even more serious in multivariate models. When testing the hypothesis against an alternative which fits well with the experiment, it should be verified whether the power of the test under this alternative cannot be smaller than the significance level. Surprisingly, this serious problem is not frequently considered in the literature. The present paper considers the two-sample multivariate testing problem. We construct several rank tests which are finite-sample unbiased against a broad class of location/scale alternatives and are finite-sample distribution-free under the hypothesis and alternatives. Each of them is locally most powerful against a specific alternative of the Lehmann type. Their powers against some alternatives are numerically compared with each other and with other rank and classical tests. The question of affine invariance of two-sample multivariate tests is also discussed.

Full work available at URL: https://arxiv.org/abs/1203.0450

Recommendations

• Multivariate Rank-Based Distribution-Free Nonparametric Testing Using Measure Transportation
• scientific article; zbMATH DE number 1406070
• A nonparametric procedure for testing partially ranked data
• Nonparametric Hypotheses and Rank Statistics for Unbalanced Factorial Designs
• A nonparametric test for a multi-sample scale problem using ranked-set data
• A note on consistency of non-parametric rank tests and related rank transformations
• Multivariate nonparametric tests
• Nonparametric rank tests for non-stationary panels
• Testing nonparametric statistical functionals with applications to rank tests

zbMATH Keywords

Wilcoxon testaffine invarianceunbiasednesscontiguityKolmogorov-Smirnov testLehmann alternativesLiu-Singh testpsi testSavage testtwo-sample multivariate model

Mathematics Subject Classification ID

Nonparametric hypothesis testing (62G10)

Cites Work

• Title not available (Why is that?)
• On a new multivariate two-sample test.
• Title not available (Why is that?)
• Multivariate generalizations of the Wald-Wolfowitz and Smirnov two-sample tests
• On the multivariate runs test
• Multivariate Two-Sample Tests Based on Nearest Neighbors
• Permutation tests for equality of distributions in high-dimensional settings
• An Exact Distribution-Free Test Comparing Two Multivariate Distributions based on Adjacency
• A Distribution Free Version of the Smirnov Two Sample Test in the $p$-Variate Case
• On a notion of data depth based on random simplices
• On the limiting distributions of multivariate depth-based rank sum statistics and related tests
• Title not available (Why is that?)
• A Quality Index Based on Data Depth and Multivariate Rank Tests
• On a notion of simplicial depth
• Title not available (Why is that?)
• Reducing multidimensional two-sample data to one-dimensional interpoint comparisons
• Optimal tests for multivariate location based on interdirections and pseudo-Mahalanobis ranks.
• Multivariate nonparametric tests
• Sign Tests in Multidimension: Inference Based on the Geometry of the Data Cloud
• Multivariate nonparametric methods with R. An approach based on spatial signs and ranks.
• On the efficiency of multivariate spatial sign and rank tests
• Title not available (Why is that?)
• Permutation tests for directional data
• A multivariate two-sample test based on the number of nearest neighbor type coincidences
• Title not available (Why is that?)
• An Approach to Multivariate Rank Tests in Multivariate Analysis of Variance
• Permutation tests for multivariate location problems
• An example of a two-sided Wilcoxon signed rank test which is not unbiased
• An example of the two-sided Wilcoxon test which is not unbiased
• Biased and unbiased two-sided Wilcoxon tests for equal sample sizes
• The locally unbiased two-sided Durbin-Watson test
• Contributions to the Theory of Rank Order Statistics-the Two-Sample Case
• Title not available (Why is that?)
• Inference based on the affine invariant multivariate Mann–Whitney–Wilcoxon statistic
• Test of multivariate linear models using spatial concordances
• On Permutation Tests in Multiple Regression and Analysis of Covariance Problems
• Title not available (Why is that?)
• Title not available (Why is that?)
• Multivariate Procedures Invariant Under Linear Transformations
• The Power of Rank Tests

Cited In (41)

• A randomized Baumgartner statistic for multivariate two-sample testing hypothesis
• Graphical Comparison of High‐Dimensional Distributions
• Interpoint Distance Test of Homogeneity for Multivariate Mixture Models
• Unified multivariate hypergeometric interpoint distances
• Testing for central symmetry and inference of the unknown center
• A nonparametric procedure for testing partially ranked data
• Power Comparison of Multivariate Wilcoxon-type Tests Based on the Jurečková–Kalina’s Ranks of Distances
• Interpoint distances: applications, properties, and visualization
• A New Scale-Invariant Nonparametric Test for Two-Sample Bivariate Location Problem with Application
• Testing equality of functions under monotonicity constraints
• Detecting a structural change in functional time series using local Wilcoxon statistic
• The minimum weighted covariance determinant estimator revisited
• Nonparametric rank-based tests of bivariate extreme-value dependence
• Multinomial interpoint distances
• Symmetrisation of a class of two-sample tests by mutually considering depth ranks including functional spaces
• Use of multivariate distance measures for high‐dimensional data in tests for difference, superiority, equivalence and non‐inferiority
• An exact projection pursuit-based algorithm for multivariate two-sample nonparametric testing applicable to retrospective and group sequential studies
• Interpoint distance tests for high-dimensional comparison studies
• An example of a two-sided Wilcoxon signed rank test which is not unbiased
• Multivariate power series interpoint distances
• Rationality and Unbiasedness in Hypothesis Testing
• Title not available (Why is that?)
• Some nonparametric tests of perfect judgment ranking for judgment post stratification
• Multivariate Kruskal_Wallis tests based on principal component score and latent source of independent component analysis
• A distribution-free procedure for testing versatile alternative in medical multisample comparison studies
• Biased and unbiased two-sided Wilcoxon tests for equal sample sizes
• Title not available (Why is that?)
• On the interpoint distances of Bernoulli vectors
• Tests for comparison of multiple endpoints with application to omics data
• Hotelling \(T^2\) test in high dimensions with application to Wilks outlier method
• Analysis of distance matrices
• Unbiasedness and biasedness of the Jonckheere-Terpstra and the Kruskal-Wallis tests
• A hypothesis test for the domain of attraction of a random variable
• Two-sample test in high dimensions through random selection
• Title not available (Why is that?)
• A Normality Test for High-dimensional Data Based on the Nearest Neighbor Approach
• On sensitivity analysis for Fisher-Behrens comparisons of soil contaminants in Arica, Chile
• Testing exchangeability of multivariate distributions
• Power comparisons of the unbiased Berk-Jones test and the unbiased reversed Berk-Jones test
• Multivariate ranks and quantiles using optimal transport: consistency, rates and nonparametric testing
• Unbiased goodness-of-fit tests

Uses Software

• MNM

This page was built for publication: Nonparametric multivariate rank tests and their unbiasedness

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q408099)