Most powerful rank tests for perfect rankings

We consider the problem of testing for perfect rankings in ranked set sampling (RSS). By using a new algorithm for computing the probability that specified independent random variables have a particular ordering, we find most powerful rank tests of the null hypothesis of perfect rankings against fu...

Full description

Bibliographic Details
Main Authors: Le, Wang, Frey, Jesse
Format: Villanova Faculty Authorship
Language:English
Online Access:http://ezproxy.villanova.edu/login?url=https://digital.library.villanova.edu/Item/vudl:454708
id vudl:454708
record_format vudl
institution Villanova University
collection Digital Library
modeltype_str_mv vudl-system:CoreModel
vudl-system:ResourceCollection
vudl-system:CollectionModel
datastream_str_mv AUDIT
MEMBER-QUERY
PARENT-LIST
LICENSE
PARENT-QUERY
MEMBER-LIST-RAW
DC
PARENT-LIST-RAW
RELS-EXT
hierarchytype
hierarchy_all_parents_str_mv vudl:454707
vudl:172968
vudl:641262
vudl:3
vudl:1
hierarchy_top_id vudl:641262
hierarchy_top_title Villanova Faculty Publications
fedora_parent_id_str_mv vudl:454707
hierarchy_first_parent_id_str vudl:454708
hierarchy_parent_id vudl:454707
hierarchy_parent_title Wang, Le
hierarchy_sequence_sort_str 0000000000
hierarchy_sequence 0000000000
spelling Most powerful rank tests for perfect rankings
Le, Wang
Frey, Jesse
<div> <table style="width: 2043px;" border="0" cellspacing="0" cellpadding="0"><tbody><tr><td colspan="1" rowspan="1" width="2043" height="21">We consider the problem of testing for perfect rankings in ranked set sampling (RSS). By using a new algorithm for computing the probability that specified independent random variables have a particular ordering, we find most powerful rank tests of the null hypothesis of perfect rankings against fully specified alternatives.Wecompare the power of these most powerful rank tests to that of existing rank tests in the literature, and we find that the existing tests are surprisingly close to optimal over a wide range of alternatives to perfect rankings. This finding holds both for balanced RSS and for unbalanced RSS cases where the different ranks are not equally represented in the sample. We find that the best of the existing tests is the test that rejects when the null probability of the observed ranks is small, and we provide a new, more efficient R function for computing the test statistic.</td></tr></tbody></table> </div>
Villanova Faculty Authorship
vudl:454708
Computational Statistics and Data Analysis
en
dc.title_txt_mv Most powerful rank tests for perfect rankings
dc.creator_txt_mv Le, Wang
Frey, Jesse
dc.description_txt_mv <div> <table style="width: 2043px;" border="0" cellspacing="0" cellpadding="0"><tbody><tr><td colspan="1" rowspan="1" width="2043" height="21">We consider the problem of testing for perfect rankings in ranked set sampling (RSS). By using a new algorithm for computing the probability that specified independent random variables have a particular ordering, we find most powerful rank tests of the null hypothesis of perfect rankings against fully specified alternatives.Wecompare the power of these most powerful rank tests to that of existing rank tests in the literature, and we find that the existing tests are surprisingly close to optimal over a wide range of alternatives to perfect rankings. This finding holds both for balanced RSS and for unbalanced RSS cases where the different ranks are not equally represented in the sample. We find that the best of the existing tests is the test that rejects when the null probability of the observed ranks is small, and we provide a new, more efficient R function for computing the test statistic.</td></tr></tbody></table> </div>
dc.format_txt_mv Villanova Faculty Authorship
dc.identifier_txt_mv vudl:454708
dc.source_txt_mv Computational Statistics and Data Analysis
dc.language_txt_mv en
author Le, Wang
Frey, Jesse
spellingShingle Le, Wang
Frey, Jesse
Most powerful rank tests for perfect rankings
author_facet Le, Wang
Frey, Jesse
dc_source_str_mv Computational Statistics and Data Analysis
format Villanova Faculty Authorship
author_sort Le, Wang
dc_title_str Most powerful rank tests for perfect rankings
description <div> <table style="width: 2043px;" border="0" cellspacing="0" cellpadding="0"><tbody><tr><td colspan="1" rowspan="1" width="2043" height="21">We consider the problem of testing for perfect rankings in ranked set sampling (RSS). By using a new algorithm for computing the probability that specified independent random variables have a particular ordering, we find most powerful rank tests of the null hypothesis of perfect rankings against fully specified alternatives.Wecompare the power of these most powerful rank tests to that of existing rank tests in the literature, and we find that the existing tests are surprisingly close to optimal over a wide range of alternatives to perfect rankings. This finding holds both for balanced RSS and for unbalanced RSS cases where the different ranks are not equally represented in the sample. We find that the best of the existing tests is the test that rejects when the null probability of the observed ranks is small, and we provide a new, more efficient R function for computing the test statistic.</td></tr></tbody></table> </div>
title Most powerful rank tests for perfect rankings
title_full Most powerful rank tests for perfect rankings
title_fullStr Most powerful rank tests for perfect rankings
title_full_unstemmed Most powerful rank tests for perfect rankings
title_short Most powerful rank tests for perfect rankings
title_sort most powerful rank tests for perfect rankings
language English
collection_title_sort_str most powerful rank tests for perfect rankings
relsext.hasModel_txt_mv http://hades.library.villanova.edu:8080/rest/vudl-system:CoreModel
http://hades.library.villanova.edu:8080/rest/vudl-system:ResourceCollection
http://hades.library.villanova.edu:8080/rest/vudl-system:CollectionModel
fgs.createdDate_txt_mv 2016-03-29T01:00:54.350Z
fgs.state_txt_mv Active
relsext.isMemberOf_txt_mv http://hades.library.villanova.edu:8080/rest/vudl:454707
fgs.ownerId_txt_mv diglibEditor
fgs.type_txt_mv http://fedora.info/definitions/v4/repository#Resource
http://www.w3.org/ns/ldp#Container
http://www.w3.org/ns/ldp#RDFSource
http://www.w3.org/ns/ldp#Resource
http://www.w3.org/ns/ldp#BasicContainer
http://fedora.info/definitions/v4/repository#Container
fgs.createdBy_txt_mv fedoraAdmin
fgs.label_txt_mv Most powerful rank tests for perfect rankings
fgs.lastModifiedDate_txt_mv 2021-04-12T19:10:12.497Z
relsext.sortOn_txt_mv title
fgs.lastModifiedBy_txt_mv fedoraAdmin
has_order_str no
license.mdRef_str http://digital.library.villanova.edu/copyright.html
license_str protected
has_thumbnail_str false
first_indexed 2016-03-29T01:00:54Z
last_indexed 2021-04-12T19:39:05Z
_version_ 1785894176297058305
subpages