Inference for spherical location under high concentration

01/02/2019
by   Davy Paindaveine, et al.
0

Motivated by the fact that many circular or spherical data are highly concentrated around a location θ, we consider inference about θ under high concentration asymptotic scenarios for which the probability of any fixed spherical cap centered at θ converges to one as the sample size n diverges to infinity. Rather than restricting to Fisher-von Mises-Langevin distributions, we consider a much broader, semiparametric, class of rotationally symmetric distributions indexed by the location parameter θ, a scalar concentration parameter κ and a functional nuisance f. We determine the class of distributions for which high concentration is obtained as κ diverges to infinity. For such distributions, we then consider inference (point estimation, confidence zone estimation, hypothesis testing) on θ in asymptotic scenarios where κ_n diverges to infinity at an arbitrary rate with the sample size n. Our asymptotic investigation reveals that, interestingly, optimal inference procedures on θ show consistency rates that depend on f. Using asymptotics "à la Le Cam", we show that the spherical mean is, at any f, a parametrically super-efficient estimator of θ and that the Watson and Wald tests for H_0:θ=θ_0 enjoy similar, non-standard, optimality properties. Our results are illustrated by Monte Carlo simulations. On a technical point of view, our asymptotic derivations require challenging expansions of rotationally symmetric functionals for large arguments of the nuisance function f.

READ FULL TEXT
research
11/07/2017

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

We consider one of the most important problems in directional statistics...
research
04/27/2020

Testing for spherical and elliptical symmetry

We construct new testing procedures for spherical and elliptical symmetr...
research
05/24/2019

Likelihood ratio tests for many groups in high dimensions

In this paper we investigate the asymptotic distribution of likelihood r...
research
08/17/2018

Concentration Based Inference for High Dimensional (Generalized) Regression Models: New Phenomena in Hypothesis Testing

We develop simple and non-asymptotically justified methods for hypothesi...
research
06/20/2019

The spherical ensemble and quasi-Monte-Carlo designs

The spherical ensemble is a well-known ensemble of N repulsive points on...
research
11/18/2021

Estimating the concentration parameter of a von Mises distribution: a systematic simulation benchmark

In directional statistics, the von Mises distribution is a key element i...
research
09/19/2020

Tests for circular symmetry of complex-valued random vectors

We propose tests for the null hypothesis that the law of a complex-value...

Please sign up or login with your details

Forgot password? Click here to reset