{"id":"https://openalex.org/W2161417756","doi":"https://doi.org/10.1145/2484028.2484163","title":"A comparison of the optimality of statistical significance tests for information retrieval evaluation","display_name":"A comparison of the optimality of statistical significance tests for information retrieval evaluation","publication_year":2013,"publication_date":"2013-07-28","ids":{"openalex":"https://openalex.org/W2161417756","doi":"https://doi.org/10.1145/2484028.2484163","mag":"2161417756"},"language":"en","primary_location":{"id":"doi:10.1145/2484028.2484163","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048779508","display_name":"Juli\u00e1n Urbano","orcid":"https://orcid.org/0000-0003-2933-1949"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Juli\u00e1n Urbano","raw_affiliation_strings":["University Carlos III of Madrid, Legan\u00e9s, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Carlos III of Madrid, Legan\u00e9s, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047898572","display_name":"M\u00f3nica Marrero","orcid":"https://orcid.org/0000-0002-2359-6340"},"institutions":[{"id":"https://openalex.org/I50357001","display_name":"Universidad Carlos III de Madrid","ror":"https://ror.org/03ths8210","country_code":"ES","type":"education","lineage":["https://openalex.org/I50357001"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"M\u00f3nica Marrero","raw_affiliation_strings":["University Carlos III of Madrid, Legan\u00e9s, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University Carlos III of Madrid, Legan\u00e9s, Spain","institution_ids":["https://openalex.org/I50357001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016938805","display_name":"Diego R. Mart\u00edn","orcid":"https://orcid.org/0000-0001-8810-0695"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Diego Mart\u00edn","raw_affiliation_strings":["Technical University of Madrid, Madrid, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048779508"],"corresponding_institution_ids":["https://openalex.org/I50357001"],"apc_list":null,"apc_paid":null,"fwci":9.1957,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.97534619,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"925","last_page":"928"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.982200026512146,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9772999882698059,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.9577000141143799,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/wilcoxon-signed-rank-test","display_name":"Wilcoxon signed-rank test","score":0.9017331600189209},{"id":"https://openalex.org/keywords/sign-test","display_name":"Sign test","score":0.7102380394935608},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.6636770367622375},{"id":"https://openalex.org/keywords/statistical-significance","display_name":"Statistical significance","score":0.6342915892601013},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.6034985780715942},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.5954992175102234},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.5657296776771545},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.5467761754989624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45890918374061584},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4244471788406372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3358384370803833},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.32169991731643677},{"id":"https://openalex.org/keywords/mann\u2013whitney-u-test","display_name":"Mann\u2013Whitney U test","score":0.27644211053848267}],"concepts":[{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.9017331600189209},{"id":"https://openalex.org/C165793278","wikidata":"https://www.wikidata.org/wiki/Q2301904","display_name":"Sign test","level":4,"score":0.7102380394935608},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.6636770367622375},{"id":"https://openalex.org/C65409693","wikidata":"https://www.wikidata.org/wiki/Q425265","display_name":"Statistical significance","level":2,"score":0.6342915892601013},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.6034985780715942},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.5954992175102234},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.5657296776771545},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.5467761754989624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45890918374061584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4244471788406372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3358384370803833},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.32169991731643677},{"id":"https://openalex.org/C12868164","wikidata":"https://www.wikidata.org/wiki/Q1424533","display_name":"Mann\u2013Whitney U test","level":2,"score":0.27644211053848267},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2484028.2484163","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484163","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1990190154","https://openalex.org/W1998328714","https://openalex.org/W2015338694","https://openalex.org/W2017826930","https://openalex.org/W2058896506","https://openalex.org/W2075893676","https://openalex.org/W2163004772"],"related_works":["https://openalex.org/W1946812442","https://openalex.org/W584167426","https://openalex.org/W2014452851","https://openalex.org/W1981089293","https://openalex.org/W1599875686","https://openalex.org/W4205615042","https://openalex.org/W4281954079","https://openalex.org/W4386333995","https://openalex.org/W1990190154","https://openalex.org/W2890914849"],"abstract_inverted_index":{"Previous":[0],"research":[1],"has":[2],"suggested":[3],"the":[4,8,20,23,43,50,69],"permutation":[5,51],"test":[6,13,48,52],"as":[7],"theoretically":[9,70],"optimal":[10],"statistical":[11],"significance":[12],"for":[14,19],"IR":[15],"evaluation,":[16],"and":[17,25,46],"advocated":[18],"discontinuation":[21],"of":[22],"Wilcoxon":[24,47],"sign":[26],"tests.":[27],"We":[28,57],"present":[29],"a":[30],"large-scale":[31],"study":[32],"comprising":[33],"nearly":[34],"60":[35],"million":[36],"system":[37],"comparisons":[38],"showing":[39],"that":[40,60,75],"in":[41],"practice":[42],"bootstrap,":[44],"t-test":[45],"outperform":[49],"under":[53],"different":[54],"optimality":[55],"criteria.":[56],"also":[58],"show":[59],"actual":[61],"error":[62],"rates":[63],"seem":[64],"to":[65],"be":[66,79],"lower":[67],"than":[68],"expected":[71],"5%,":[72],"further":[73],"confirming":[74],"we":[76],"may":[77],"actually":[78],"underestimating":[80],"significance.":[81]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}
