Asymptotics and practical aspects of testing normality with kernel methods

DOI10.1016/J.JMVA.2020.104665zbMATH Open1459.62087arXiv1902.03241OpenAlexW3047519670MaRDI QIDQ2201553FDOQ2201553

Authors: Natsumi Makigusa, Kanta Naito 

Publication date: 29 September 2020

Published in: Journal of Multivariate Analysis (Search for Journal in Brave)

Abstract: This paper is concerned with testing normality in a Hilbert space based on the maximum mean discrepancy. Specifically, we discuss the behavior of the test from two standpoints: asymptotics and practical aspects. Asymptotic normality of the test under a fixed alternative hypothesis is developed, which implies that the test has consistency. Asymptotic distribution of the test under a sequence of local alternatives is also derived, from which asymptotic null distribution of the test is obtained. A concrete expression for the integral kernel associated with the null distribution is derived under the use of the Gaussian kernel, allowing the implementation of a reliable approximation of the null distribution. Simulations and applications to real data sets are reported with emphasis on high-dimension low-sample size cases.

Full work available at URL: https://arxiv.org/abs/1902.03241

Recommendations

• A one-sample test for normality with kernel methods
• Asymptotic normality of a generalized maximum mean discrepancy estimator
• Asymptotic normality of a consistent estimator of maximum mean discrepancy in Hilbert space
• Testing normality using kernel methods
• A kernel two-sample test

zbMATH Keywords

asymptoticsHilbert spacekernel methodtesting normality

Mathematics Subject Classification ID

Density estimation (62G07) Asymptotic distribution theory in statistics (62E20) Hypothesis testing in multivariate analysis (62H15) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22)

Cites Work

• A goodness-of-fit test for elliptical distributions with diagnostic capabilities
• An introduction to recent advances in high/infinite dimensional statistics
• Approximation Theorems of Mathematical Statistics
• A partial overview of the theory of statistics with functional data
• Title not available (Why is that?)
• Title not available (Why is that?)
• Theory of Reproducing Kernels
• Linear processes in function spaces. Theory and applications
• A kernel two-sample test
• Tests of multinormality based on location vectors and scatter matrices
• An F approximation and its application
• Recent advances in functional data analysis and high-dimensional statistics
• A class of invariant consistent tests for multivariate normality
• Measures of multivariate skewness and kurtosis with applications
• Testing for normality in arbitrary dimension
• A one-sample test for normality with kernel methods
• Adaptive Smoothing and Density-Based Tests of Multivariate Normality
• Title not available (Why is that?)
• A test for normality based on the empirical characteristic function
• An analysis of variance test for normality (complete samples)
• Goodness-of-fit testing based on a weighted bootstrap: a fast large-sample alternative to the parametric bootstrap
• The law of large numbers and the central limit theorem in Banach spaces
• Title not available (Why is that?)
• Estimations for some functions of covariance matrix in high dimension under non-normality and its applications
• Cumulative chi-squared statistic as a tool for testing goodness of fit
• Large sample theory for U-statistics and tests of fit
• Chebyshev's inequality for Hilbert-space-valued random elements
• Scattered Data Approximation
• Title not available (Why is that?)
• Mercer’s Theorem, Feature Maps, and Smoothing
• A comparative study of goodness-of-fit tests for multivariate normality
• Data driven smooth tests for bivariate normality

Cited In (3)

• On Asymptotic Minimaxity of Kernel-based Tests
• Asymptotically Optimal One- and Two-Sample Testing With Kernels
• Title not available (Why is that?)

This page was built for publication: Asymptotics and practical aspects of testing normality with kernel methods

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2201553)