Testing multivariate normality by zeros of the harmonic oscillator in characteristic function spaces

DOI10.1111/SJOS.12477MaRDI QIDQ5001012zbMATH OpenOpenAlexFDO

Authors Philip Dörr, Bruno Ebner, Norbert Henze

Publication date 16 July 2021

Published in Scandinavian Journal of Statistics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/1909.12624

zbMATH Keywords

consistencyaffine invariancetest for multivariate normalityharmonic oscillatorempirical characteristic functionneighborhood-of-model validation

Mathematics Subject Classification ID

Hypothesis testing in multivariate analysis (62H15) Functional data analysis (62R10)

Abstract: We study a novel class of affine invariant and consistent tests for normality in any dimension. The tests are based on a characterization of the standard $d$-variate normal distribution as the unique solution of an initial value problem of a partial differential equation motivated by the harmonic oscillator, which is a special case of a Schr"odinger operator. We derive the asymptotic distribution of the test statistics under the hypothesis of normality as well as under fixed and contiguous alternatives. The tests are consistent against general alternatives, exhibit strong power performance for finite samples, and they are applied to a classical data set due to R.A. Fisher. The results can also be used for a neighborhood-of-model validation procedure.

Recommendations

• A new test of multivariate normality by a double estimation in a characterizing PDE
• scientific article; zbMATH DE number 5019864
• Testing for normality in any dimension based on a partial differential equation involving the moment generating function
• Two tests for multivariate normality based on the characteristic function
• A class of invariant consistent tests for multivariate normality

Cited in

(6)

• On combining the zero bias transform and the empirical characteristic function to test normality
• Testing for normality in any dimension based on a partial differential equation involving the moment generating function
• A general Monte Carlo method for multivariate goodness-of-fit testing applied to elliptical families
• Testing normality in any dimension by Fourier methods in a multivariate Stein equation
• Tests for multivariate normality -- a critical review with emphasis on weighted L^2-statistics
• Logistic or not Logistic?

This page was built for publication: Testing multivariate normality by zeros of the harmonic oscillator in characteristic function spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5001012)