{"id":"https://openalex.org/W4288280764","doi":"https://doi.org/10.1145/3331184.3331259","title":"Statistical Significance Testing in Information Retrieval","display_name":"Statistical Significance Testing in Information Retrieval","publication_year":2019,"publication_date":"2019-07-18","ids":{"openalex":"https://openalex.org/W4288280764","doi":"https://doi.org/10.1145/3331184.3331259"},"language":"en","primary_location":{"id":"doi:10.1145/3331184.3331259","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3331184.3331259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.11096","any_repository_has_fulltext":true},"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/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Juli\u00e1n Urbano","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033817022","display_name":"Harlley Lima","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Harlley Lima","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037486611","display_name":"Alan Hanjali\u0107","orcid":"https://orcid.org/0000-0002-5771-2549"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alan Hanjalic","raw_affiliation_strings":["Delft University of Technology, Delft, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98358874"],"apc_list":null,"apc_paid":null,"fwci":3.9719,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.94925538,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"505","last_page":"514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9915000200271606,"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":0.9915000200271606,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9847999811172485,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9763000011444092,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7972460389137268},{"id":"https://openalex.org/keywords/null-hypothesis","display_name":"Null hypothesis","score":0.674828827381134},{"id":"https://openalex.org/keywords/type-i-and-type-ii-errors","display_name":"Type I and type II errors","score":0.6421543955802917},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.6001585721969604},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.5513238906860352},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5190618634223938},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.515782356262207},{"id":"https://openalex.org/keywords/wilcoxon-signed-rank-test","display_name":"Wilcoxon signed-rank test","score":0.5037829279899597},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49990034103393555},{"id":"https://openalex.org/keywords/multiple-comparisons-problem","display_name":"Multiple comparisons problem","score":0.4968872368335724},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4896848499774933},{"id":"https://openalex.org/keywords/null","display_name":"Null (SQL)","score":0.46327921748161316},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.4541161060333252},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.44930484890937805},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3682861030101776},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3641451299190521},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34792715311050415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32314789295196533},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.2864387631416321},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2713974714279175},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15165123343467712},{"id":"https://openalex.org/keywords/mann\u2013whitney-u-test","display_name":"Mann\u2013Whitney U test","score":0.09333416819572449}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7972460389137268},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.674828827381134},{"id":"https://openalex.org/C40696583","wikidata":"https://www.wikidata.org/wiki/Q989120","display_name":"Type I and type II errors","level":2,"score":0.6421543955802917},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.6001585721969604},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.5513238906860352},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5190618634223938},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.515782356262207},{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.5037829279899597},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49990034103393555},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.4968872368335724},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4896848499774933},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.46327921748161316},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.4541161060333252},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.44930484890937805},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3682861030101776},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3641451299190521},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34792715311050415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32314789295196533},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.2864387631416321},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2713974714279175},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15165123343467712},{"id":"https://openalex.org/C12868164","wikidata":"https://www.wikidata.org/wiki/Q1424533","display_name":"Mann\u2013Whitney U test","level":2,"score":0.09333416819572449},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3331184.3331259","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3331184.3331259","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1905.11096","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.11096","pdf_url":"https://arxiv.org/pdf/1905.11096","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.11096","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.11096","pdf_url":"https://arxiv.org/pdf/1905.11096","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4593709364","display_name":"Towards Richer Online Music Public-domain Archives","funder_award_id":"770376","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4668232341","display_name":null,"funder_award_id":"770376","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5654083137","display_name":null,"funder_award_id":"770376-2","funder_id":"https://openalex.org/F4320335254","funder_display_name":"Horizon 2020"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320335254","display_name":"Horizon 2020","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W103650626","https://openalex.org/W125003123","https://openalex.org/W390686421","https://openalex.org/W1824124613","https://openalex.org/W1964801579","https://openalex.org/W1974475152","https://openalex.org/W1987690005","https://openalex.org/W1990190154","https://openalex.org/W1994594731","https://openalex.org/W1998328714","https://openalex.org/W1999331679","https://openalex.org/W2006667248","https://openalex.org/W2008285050","https://openalex.org/W2010616235","https://openalex.org/W2015338694","https://openalex.org/W2015629112","https://openalex.org/W2017292914","https://openalex.org/W2017826930","https://openalex.org/W2021856948","https://openalex.org/W2039017419","https://openalex.org/W2050058698","https://openalex.org/W2052569738","https://openalex.org/W2058896506","https://openalex.org/W2064459117","https://openalex.org/W2068086934","https://openalex.org/W2075893676","https://openalex.org/W2077046902","https://openalex.org/W2083599439","https://openalex.org/W2091509754","https://openalex.org/W2111310810","https://openalex.org/W2113026607","https://openalex.org/W2120308175","https://openalex.org/W2135985057","https://openalex.org/W2140787629","https://openalex.org/W2160892561","https://openalex.org/W2161417756","https://openalex.org/W2163004772","https://openalex.org/W2312704740","https://openalex.org/W2336806308","https://openalex.org/W2463093044","https://openalex.org/W2740387847","https://openalex.org/W2756726346","https://openalex.org/W2798550416","https://openalex.org/W2802622649","https://openalex.org/W3100184886","https://openalex.org/W4205110562","https://openalex.org/W4249463359","https://openalex.org/W4251022264","https://openalex.org/W4252684946","https://openalex.org/W4253411719","https://openalex.org/W4310299640"],"related_works":["https://openalex.org/W3003558595","https://openalex.org/W4361270669","https://openalex.org/W2015235728","https://openalex.org/W154531455","https://openalex.org/W2915316750","https://openalex.org/W4385586894","https://openalex.org/W3069995450","https://openalex.org/W4249473446","https://openalex.org/W1995992573","https://openalex.org/W4200219293"],"abstract_inverted_index":{"Statistical":[0],"significance":[1,257],"testing":[2],"is":[3,47,161],"widely":[4],"accepted":[5],"as":[6,23,84],"a":[7,13,188,209,232,250],"means":[8],"to":[9,25,35,145,166,180,195,252],"assess":[10],"how":[11,170,254],"well":[12,255],"difference":[14,20],"in":[15,114,124,132,176,183,249],"effectiveness":[16,214],"reflects":[17],"an":[18],"actual":[19,147],"between":[21],"systems,":[22,213],"opposed":[24],"random":[26],"noise":[27],"because":[28],"of":[29,32,91,211,235,242],"the":[30,45,48,64,67,85,89,138,142,225,243],"selection":[31],"topics.":[33],"According":[34],"recent":[36,189],"surveys":[37],"on":[38,72,109],"SIGIR,":[39],"CIKM,":[40],"ECIR":[41],"and":[42,100,127,150,219,222,227,264],"TOIS":[43],"papers,":[44],"t-test":[46],"most":[49],"popular":[50],"choice":[51],"among":[52],"IR":[53,99,125,236,262],"researchers.":[54],"However,":[55],"previous":[56],"work":[57],"has":[58,97],"suggested":[59,80],"computer":[60],"intensive":[61],"tests":[62,93,258],"like":[63],"bootstrap":[65],"or":[66],"permutation":[68],"test,":[69],"based":[70],"mainly":[71],"theoretical":[73,107],"arguments.":[74],"On":[75],"empirical":[76,128],"grounds,":[77],"others":[78],"have":[79,137],"non-parametric":[81],"alternatives":[82],"such":[83,231],"Wilcoxon":[86],"test.":[87],"Indeed,":[88],"question":[90],"which":[92,164],"we":[94,116,134,173,186,246],"should":[95,174],"use":[96],"accompanied":[98],"related":[101],"fields":[102],"for":[103,208,223,268],"decades":[104],"now.":[105],"Previous":[106],"studies":[108,129],"this":[110,184],"matter":[111],"were":[112,130],"limited":[113,131],"that":[115,118,133],"know":[117],"test":[119,165],"assumptions":[120],"are":[121,247],"not":[122,136,159],"met":[123],"experiments,":[126],"do":[135],"necessary":[139],"control":[140],"over":[141,203],"null":[143,244],"hypotheses":[144],"compute":[146],"Type":[148,151],"I":[149],"II":[152],"error":[153],"rates":[154],"under":[155],"realistic":[156],"conditions.":[157],"Therefore,":[158],"only":[160],"it":[162],"unclear":[163],"use,":[167],"but":[168],"also":[169],"much":[171],"trust":[172],"put":[175],"them.":[177],"In":[178],"contrast":[179],"past":[181],"studies,":[182],"paper":[185],"employ":[187],"simulation":[190],"methodology":[191],"from":[192],"TREC":[193],"data":[194,238],"go":[196],"around":[197],"these":[198],"limitations.":[199],"Our":[200],"study":[201],"comprises":[202],"500":[204],"million":[205],"p-values":[206],"computed":[207],"range":[210],"tests,":[212],"measures,":[215],"topic":[216],"set":[217],"sizes":[218],"effect":[220],"sizes,":[221],"both":[224],"2-tail":[226],"1-tail":[228],"cases.":[229],"Having":[230],"large":[233],"supply":[234],"evaluation":[237],"with":[239,261],"full":[240],"knowledge":[241],"hypotheses,":[245],"finally":[248],"position":[251],"evaluate":[253],"statistical":[256],"really":[259],"behave":[260],"data,":[263],"make":[265],"sound":[266],"recommendations":[267],"practitioners.":[269]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":3}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2022-07-28T00:00:00"}