Bayesian optimality for Beran’s class of tests of uniformity around the circle

We show that the locally most powerful tests of uniformity on the circle given by Beran have optimality properties not just against the parametric alternatives described by Beran but also against many non-parametric alternatives. We compare these local results to asymptotic versions of this optimali...

Full description

Saved in:
Bibliographic Details
Published in:Journal of statistical planning and inference 2019-01, Vol.198, p.79-90
Main Authors: Sun, Shaun Zheng, Lockhart, Richard A.
Format: Article
Language:English
Subjects:
Bayesian optimal test
Beran’s tests
Directional data
Locally most powerful test
Prior distributions
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We show that the locally most powerful tests of uniformity on the circle given by Beran have optimality properties not just against the parametric alternatives described by Beran but also against many non-parametric alternatives. We compare these local results to asymptotic versions of this optimality. •Local optimality of Beran’s tests is reinterpreted as local Bayesian optimality.•Beran’s tests are locally Bayes optimal against many nonparametric alternatives.•We describe both local and asymptotic versions of this optimality.•We provide details for several well known statistics in Beran’s class.
ISSN:0378-3758
1873-1171
DOI:10.1016/j.jspi.2018.03.006