Theory & Methods: Distance Testing for Selecting the Best Population

Futschik, A. & Pflug, G. ORCID: https://orcid.org/0000-0001-8215-3550 (1998). Theory & Methods: Distance Testing for Selecting the Best Population. Australian & New Zealand Journal of Statistics 40 (4) 443-464. 10.1111/1467-842X.00049.

Full text not available from this repository.

Abstract

Consider testing the null hypothesis that a given population has location parameter greater than or equal to the largest location parameter of k competing populations. This paper generalizes tests proposed by Gupta and Bartholomew by considering tests based on p-distances from the parameter estimate to the null parameter space. It is shown that all tests are equivalent when k[RIGHTWARDS ARROW]∞ for a class of distributions that includes the normal and the uniform. The paper proposes the use of adaptive quantiles. Under suitable assumptions the resulting tests are asymptotically equivalent to the uniformly most powerful test for the case that the location parameters of all but one of the populations are known. The increase in power obtained by using adaptive tests is confirmed by a simulation study.

Item Type: Article
Uncontrolled Keywords: subset selection;simple tree order;distance tests;efficient adaptive testing;order restricted inference;extreme order statistics
Research Programs: Risk, Modeling, Policy (RMP)
Depositing User: IIASA Import
Date Deposited: 15 Jan 2016 02:09
Last Modified: 27 Aug 2021 17:16
URI: https://pure.iiasa.ac.at/5405

Actions (login required)

View Item View Item