Detecting the direction of a signal on high-dimensional spheres: non-null and Le Cam optimality results

DOI10.1007/S00440-019-00937-XMaRDI QIDQ2174669zbMATH OpenOpenAlexFDO

Authors Davy Paindaveine, Thomas Verdebout

Publication date 21 April 2020

Published in Zeitschrift für Wahrscheinlichkeitstheorie und Verwandte Gebiete (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1711.02504

zbMATH Keywords

high-dimensional statisticsinvariancelocal asymptotic normalityrotationally symmetric distributionsLe Cam's asymptotic theory of statistical experiments

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Directional data; spatial statistics (62H11)

Abstract: We consider one of the most important problems in directional statistics, namely the problem of testing the null hypothesis that the spike direction $heta$ of a Fisher-von Mises-Langevin distribution on the $p$-dimensional unit hypersphere is equal to a given direction $het{a}_0$. After a reduction through invariance arguments, we derive local asymptotic normality (LAN) results in a general high-dimensional framework where the dimension $p_n$ goes to infinity at an arbitrary rate with the sample size $n$, and where the concentration $kapp{a}_n$ behaves in a completely free way with $n$, which offers a spectrum of problems ranging from arbitrarily easy to arbitrarily challenging ones. We identify various asymptotic regimes, depending on the convergence/divergence properties of $(kapp{a}_n)$, that yield different contiguity rates and different limiting experiments. In each regime, we derive Le Cam optimal tests under specified $kapp{a}_n$ and we compute, from the Le Cam third lemma, asymptotic powers of the classical Watson test under contiguous alternatives. We further establish LAN results with respect to both spike direction and concentration, which allows us to discuss optimality also under unspecified $kapp{a}_n$. To investigate the non-null behavior of the Watson test outside the parametric framework above, we derive its local asymptotic powers through martingale CLTs in the broader, semiparametric, model of rotationally symmetric distributions. A Monte Carlo study shows that the finite-sample behaviors of the various tests remarkably agree with our asymptotic results.

Recommendations

• High-dimensional tests for spherical location and spiked covariance
• Inference on the mode of weak directional signals: a Le Cam perspective on hypothesis testing near singularities
• Testing uniformity on high-dimensional spheres against monotone rotationally symmetric alternatives
• Local Powers of Optimal One‐sample and Multi‐sample Tests for the Concentration of Fisher‐von Mises‐Langevin Distributions
• Tests for the mean direction of the Langevin distribution with large concentration parameter

Cites work

• scientific article; zbMATH DE number 4210538 (Why is no real title available?)
• scientific article; zbMATH DE number 5430929 (Why is no real title available?)
• scientific article; zbMATH DE number 4054823 (Why is no real title available?)
• scientific article; zbMATH DE number 1375577 (Why is no real title available?)
• scientific article; zbMATH DE number 600061 (Why is no real title available?)
• scientific article; zbMATH DE number 1181283 (Why is no real title available?)
• scientific article; zbMATH DE number 765034 (Why is no real title available?)
• A distribution-free M-estimator of multivariate scatter
• Asymptotic Statistics
• Asymptotics in statistics. Some basic concepts.
• Computation of Modified Bessel Functions and Their Ratios
• Distributions of angles in random packing on spheres
• Estimation of the concentration parameter in von Mises-Fisher distributions
• Group Invariance in Statistical Inference
• High dimensional limit theorems and matrix decompositions on the Stiefel manifold
• High-dimensional tests for spherical location and spiked covariance
• Improved likelihood ratio tests on the von Mises-Fisher distribution
• Inference for spherical location under high concentration
• Inference on the mode of weak directional signals: a Le Cam perspective on hypothesis testing near singularities
• Modern directional statistics
• Optimal R-estimation of a spherical location
• Robust direction estimation
• Skew-symmetric distributions and Fisher information: the double sin of the skew-normal
• Spherical regression
• Spherical regression for concentrated Fisher-von Mises distributions
• Statistical analysis on high-dimensional spheres and shape spaces
• Statistics of orthogonal axial frames
• Testing Statistical Hypotheses
• Testing for principal component directions under weak identifiability
• Testing uniformity on high-dimensional spheres against monotone rotationally symmetric alternatives
• \(M\)-estimation for location and regression parameters in group models: A case study using Stiefel manifolds

Cited in

(5)

• Testing uniformity on high-dimensional spheres against monotone rotationally symmetric alternatives
• Inference for spherical location under high concentration
• On the power of axial tests of uniformity on spheres
• Testing uniformity on high-dimensional spheres: the non-null behaviour of the Bingham test
• Inference on the mode of weak directional signals: a Le Cam perspective on hypothesis testing near singularities

Describes a project that uses

Uses Software

• movMF

This page was built for publication: Detecting the direction of a signal on high-dimensional spheres: non-null and Le Cam optimality results

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2174669)