Robust multivariate nonparametric tests via projection averaging
From MaRDI portal
\(U\)-statisticenergy statistichigh dimension and low sample sizeindependence testingmaximum mean discrepancypermutation tests
Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Nonparametric hypothesis testing (62G10) Nonparametric robustness (62G35) Hypothesis testing in multivariate analysis (62H15) Measures of association (correlation, canonical correlation, etc.) (62H20)
Abstract: In this work, we generalize the Cram'er-von Mises statistic via projection-averaging to obtain a robust test for the multivariate two-sample problem. The proposed test is consistent against all fixed alternatives, robust to heavy-tailed data and minimax rate optimal against a certain class of alternatives. Our test statistic is completely free of tuning parameters and is computationally efficient even in high dimensions. When the dimension tends to infinity, the proposed test is shown to have comparable power to the existing high-dimensional mean tests under certain location models. As a by-product of our approach, we introduce a new metric called the angular distance which can be thought of as a robust alternative to the Euclidean distance. Using the angular distance, we connect the proposed method to the reproducing kernel Hilbert space approach. In addition to the Cram'er-von Mises statistic, we demonstrate that the projection-averaging technique can be used to define robust, multivariate tests in many other problems.
Recommendations
Cites work
- f-Divergence Estimation and Two-Sample Homogeneity Test Under Semiparametric Density-Ratio Models
- A CONSISTENT DIAGNOSTIC TEST FOR REGRESSION MODELS USING PROJECTIONS
- A consistent test of independence based on a sign covariance related to Kendall's tau
- A distribution-free two-sample run test applicable to high-dimensional data
- A General Asymptotic Framework for Distribution-Free Graph-Based Two-Sample Tests
- A high-dimensional nonparametric multivariate test for mean vector
- A kernel two-sample test
- A multivariate two-sample test based on the number of nearest neighbor type coincidences
- A nonparametric two-sample test applicable to high dimensional data
- A review of 20 years of naive tests of significance for high-dimensional mean vectors and covariance matrices
- A smooth test for the equality of distributions
- A triangle test for equality of distribution functions in high dimensions
- A two-sample test for high-dimensional data with applications to gene-set testing
- A weighted edge-count two-sample test for multivariate and object data
- An Exact Distribution-Free Test Comparing Two Multivariate Distributions based on Adjacency
- Average projection type weighted Cramér-von Mises statistics for testing some distributions
- Ball divergence: nonparametric two sample test
- Comparing distributions
- Cramér-von Mises distance: probabilistic interpretation, confidence intervals, and neighbourhood-of-model validation
- Energy statistics: a class of statistics based on distances
- Ensemble subsampling for imbalanced multivariate two-sample tests
- Equivalence of distance-based and RKHS-based statistics in hypothesis testing
- Exact and asymptotically robust permutation tests
- Geometric Representation of High Dimension, Low Sample Size Data
- scientific article; zbMATH DE number 1203738 (Why is no real title available?)
- scientific article; zbMATH DE number 1964693 (Why is no real title available?)
- scientific article; zbMATH DE number 889593 (Why is no real title available?)
- Multivariate generalizations of the Wald-Wolfowitz and Smirnov two-sample tests
- Multivariate nonparametric methods with R. An approach based on spatial signs and ranks.
- Multivariate nonparametric tests
- Multivariate permutation tests
- Multivariate Two-Sample Tests Based on Nearest Neighbors
- On a new multivariate two-sample test.
- On estimated projection pursuit-type Crámer-von Mises statistics
- On high dimensional two-sample tests based on nearest neighbors
- On the Distribution of the Two-Sample Cramer-von Mises Criterion
- On the shortest spanning subtree of a graph and the traveling salesman problem
- Projection correlation between two random vectors
- Testing Statistical Hypotheses
- Tests for high-dimensional data based on means, spatial signs and spatial ranks
- The Large-Sample Power of Tests Based on Permutations of Observations
- Two sample tests for high-dimensional covariance matrices
- Two-sample smooth tests for the equality of distributions
- Two-sample test statistics for measuring discrepancies between two multivariate probability density functions using kernel-based density estimates
Cited in
(63)- The exact equivalence of distance and kernel methods in hypothesis testing
- An overview of tests on high-dimensional means
- Stable correlation and robust feature screening
- Projection quantile correlation and its use in high-dimensional grouped variable screening
- A new framework for distance and kernel-based metrics in high dimensions
- Spatial rank-based high-dimensional change point detection via random integration
- On universally consistent and fully distribution-free rank tests of vector independence
- Consistency of invariance-based randomization tests
- Poisson limit theorems for the Cressie-Read statistics
- Sharp local minimax rates for goodness-of-fit testing in multivariate binomial and Poisson families and in multinomials
- Minimax optimality of permutation tests
- Projection-based high-dimensional sign test
- Local minimax rates for closeness testing of discrete distributions
- Minimax confidence intervals for the sliced Wasserstein distance
- A comparison of likelihood-free methods with and without summary statistics
- Projection-averaging-based cumulative covariance and its use in goodness-of-fit testing for single-index models
- Consistent Screening Procedures in High-dimensional Binary Classification
- A new nonparametric extension of ANOVA via projection mean variance measure
- Distribution-Free Consistent Independence Tests via Center-Outward Ranks and Signs
- Distributed inference for two‐sample U‐statistics in massive data analysis
- Use of Random Integration to Test Equality of High Dimensional Covariance Matrices
- Measuring, Testing, and Identifying Heterogeneity of Large Parallel Datasets
- Poisson and Gaussian approximations of the power divergence family of statistics
- Measuring and testing homogeneity of distributions by characteristic distance
- Weighted bootstrap for two-sample U-statistics
- Projection divergence in the reproducing kernel Hilbert space: asymptotic normality, block-wise and slicing estimation, and computational efficiency
- Dimension-agnostic inference using cross U-statistics
- A hyperbolic divergence based nonparametric test for two‐sample multivariate distributions
- Testing homogeneity in high dimensional data through random projections
- Testing distributional equality for functional random variables
- Non-parametric two-sample tests: recent developments and prospects
- Distribution-free tests of multivariate independence based on center-outward quadrant, Spearman, Kendall, and van der Waerden statistics
- A survey of some recent developments in measures of association
- Nonparametric Statistical Inference via Metric Distribution Function in Metric Spaces
- A Gaussian process approach to model checks
- A conditional distribution function-based measure for independence and K-sample tests in multivariate data
- Regionalization of China's PM₂.5: a robust functional spatial clustering with angular depth
- Specification tests for generalised propensity scores using double projections
- Testing for independence in high dimensions based on characteristic covariance
- Semi-supervised U-statistics
- Functional sufficient dimension reduction with multivariate responses: a projection averaging method and beyond
- Asymptotic distribution-free tests related to maximum mean discrepancy
- Two-sample distribution tests in high dimensions via max-sliced Wasserstein distance and bootstrapping
- Boosting the power of kernel two-sample tests
- Enhanced HSIC for independence test via projection integration
- High-dimensional behaviour of some two-sample tests based on ball divergence
- Robust feature screening via Grothendieck's correlation with FDR control
- Kernel Angle Dependence Measures in Metric Spaces
- Studentized tests of independence: random-lifter approach
- A kernel independence test using projection-based measure in high-dimension
- High-dimensional projection-based ANOVA test
- A robust and powerful metric for distributional homogeneity
- Two-sample smooth test for the equality of distributions for dependent data and its bootstrap consistency
- Methods for quantifying dataset similarity: a review, taxonomy and comparison
- Testing the equality of distributions using integrated maximum mean discrepancy
- Frequent-voting independence screening for data of different types or different dimensions
- A Minimax Two-Sample Test for Functional Data via Grothendieck’s Divergence
- Testing independence between high-dimensional random vectors using rank-based max-sum tests
- Finding distributions that differ, with false discovery rate control
- A composite kernel two-sample test
- Pitman efficiency lower bounds for multivariate distribution-free tests based on optimal transport
- Sufficient dimension reduction via inverse conditional mean or variance independence
- Testing for the equality of distributions in high dimension
This page was built for publication: Robust multivariate nonparametric tests via projection averaging
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1996775)
