{"id":"https://openalex.org/W1990190154","doi":"https://doi.org/10.1145/1321440.1321528","title":"A comparison of statistical significance tests for information retrieval evaluation","display_name":"A comparison of statistical significance tests for information retrieval evaluation","publication_year":2007,"publication_date":"2007-11-06","ids":{"openalex":"https://openalex.org/W1990190154","doi":"https://doi.org/10.1145/1321440.1321528","mag":"1990190154"},"language":"en","primary_location":{"id":"doi:10.1145/1321440.1321528","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1321440.1321528","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F1321440.1321528&file=p623-smucker.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixteenth ACM conference on Conference on information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F1321440.1321528&file=p623-smucker.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049222552","display_name":"Mark D. Smucker","orcid":"https://orcid.org/0000-0003-4968-6405"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark D. Smucker","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034070218","display_name":"James Allan","orcid":"https://orcid.org/0000-0003-0132-5694"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James Allan","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078123101","display_name":"Ben Carterette","orcid":"https://orcid.org/0000-0001-9538-047X"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Carterette","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":720,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"623","last_page":"632"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9980999827384949,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9922999739646912,"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/T10028","display_name":"Topic Modeling","score":0.9922000169754028,"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/wilcoxon-signed-rank-test","display_name":"Wilcoxon signed-rank test","score":0.8926390409469604},{"id":"https://openalex.org/keywords/sign-test","display_name":"Sign test","score":0.8091511130332947},{"id":"https://openalex.org/keywords/statistical-significance","display_name":"Statistical significance","score":0.7660670876502991},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.5884494781494141},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.5823996663093567},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5504792332649231},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4919728934764862},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.48619240522384644},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.4555841386318207},{"id":"https://openalex.org/keywords/permutation","display_name":"Permutation (music)","score":0.4461548924446106},{"id":"https://openalex.org/keywords/mann\u2013whitney-u-test","display_name":"Mann\u2013Whitney U test","score":0.44405877590179443},{"id":"https://openalex.org/keywords/exact-test","display_name":"Exact test","score":0.43323010206222534},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.40577778220176697},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3610095977783203}],"concepts":[{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.8926390409469604},{"id":"https://openalex.org/C165793278","wikidata":"https://www.wikidata.org/wiki/Q2301904","display_name":"Sign test","level":4,"score":0.8091511130332947},{"id":"https://openalex.org/C65409693","wikidata":"https://www.wikidata.org/wiki/Q425265","display_name":"Statistical significance","level":2,"score":0.7660670876502991},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.5884494781494141},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.5823996663093567},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5504792332649231},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4919728934764862},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.48619240522384644},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.4555841386318207},{"id":"https://openalex.org/C21308566","wikidata":"https://www.wikidata.org/wiki/Q7169365","display_name":"Permutation (music)","level":2,"score":0.4461548924446106},{"id":"https://openalex.org/C12868164","wikidata":"https://www.wikidata.org/wiki/Q1424533","display_name":"Mann\u2013Whitney U test","level":2,"score":0.44405877590179443},{"id":"https://openalex.org/C191093355","wikidata":"https://www.wikidata.org/wiki/Q9250577","display_name":"Exact test","level":2,"score":0.43323010206222534},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.40577778220176697},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3610095977783203},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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":4,"locations":[{"id":"doi:10.1145/1321440.1321528","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1321440.1321528","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F1321440.1321528&file=p623-smucker.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixteenth ACM conference on Conference on information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.134.5558","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.134.5558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.umass.edu/~smucker/publications/smucker-statSig-cikm07.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.366.7734","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.366.7734","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://maroo.cs.umass.edu/pub/web/getpdf.php?id=744","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.388.399","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.388.399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mansci.uwaterloo.ca/~msmucker/publications/smucker-statSig-cikm07.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1145/1321440.1321528","is_oa":true,"landing_page_url":"https://doi.org/10.1145/1321440.1321528","pdf_url":"https://dl.acm.org/action/downloadSupplement?doi=10.1145%2F1321440.1321528&file=p623-smucker.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the sixteenth ACM conference on Conference on information and knowledge management","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G3190074090","display_name":null,"funder_award_id":"HR0011-06-C-0023","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1990190154.pdf","grobid_xml":"https://content.openalex.org/works/W1990190154.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1515242458","https://openalex.org/W1968226729","https://openalex.org/W1995945562","https://openalex.org/W1998328714","https://openalex.org/W2015338694","https://openalex.org/W2015629112","https://openalex.org/W2016522586","https://openalex.org/W2058896506","https://openalex.org/W2077046902","https://openalex.org/W2085575316","https://openalex.org/W2095595785","https://openalex.org/W2111310810","https://openalex.org/W2121383450","https://openalex.org/W2140787629","https://openalex.org/W2143292997","https://openalex.org/W2165695298","https://openalex.org/W2582743722","https://openalex.org/W2612575796","https://openalex.org/W2793613633","https://openalex.org/W2796084947","https://openalex.org/W2802411782","https://openalex.org/W3144113100","https://openalex.org/W4210551050","https://openalex.org/W4252684946","https://openalex.org/W4310299640","https://openalex.org/W6630696253","https://openalex.org/W6649611171","https://openalex.org/W6655260962","https://openalex.org/W6827666898","https://openalex.org/W6983359285","https://openalex.org/W7037462566"],"related_works":["https://openalex.org/W584167426","https://openalex.org/W1599875686","https://openalex.org/W1589014849","https://openalex.org/W4238928523","https://openalex.org/W2753714105","https://openalex.org/W4212970993","https://openalex.org/W2753412502","https://openalex.org/W1604592383","https://openalex.org/W4302333831","https://openalex.org/W3126033952"],"abstract_inverted_index":{"Information":[0],"retrieval":[1,61],"(IR)":[2],"researchers":[3,25],"commonly":[4],"use":[5,141],"three":[6],"tests":[7,41,46,131],"of":[8,53,73,80,125,135,149],"statistical":[9,78],"significance:":[10],"the":[11,15,21,31,59,77,81,97,104,118,136,147],"Student's":[12],"paired":[13],"t-test,":[14],"Wilcoxon":[16,105,128],"signed":[17],"rank":[18],"test,":[19],"and":[20,33,67,69,100,106,116,129,139],"sign":[22,107,130],"test.":[23],"Other":[24],"have":[26,47,109,117],"previously":[27],"proposed":[28],"using":[29],"both":[30],"bootstrap":[32],"Fisher's":[34],"randomization":[35,137],"(permutation)":[36],"test":[37,108,138],"as":[38],"non-parametric":[39],"significance":[40,79,115,148],"for":[42,70,145],"IR":[43],"but":[44],"these":[45,54],"seen":[48],"little":[49,93],"use.":[50],"For":[51],"each":[52,71],"five":[55],"tests,":[56],"we":[57,75],"took":[58],"ad-hoc":[60],"runs":[62],"submitted":[63],"to":[64,113,120,122],"TRECs":[65],"3":[66],"5-8,":[68],"pair":[72],"runs,":[74],"measured":[76],"difference":[82,95,151],"in":[83],"their":[84,140],"mean":[85],"average":[86],"precision.":[87],"We":[88],"discovered":[89],"that":[90],"there":[91],"is":[92],"practical":[94],"between":[96,152],"randomization,":[98],"bootstrap,":[99],"t":[101],"tests.":[102],"Both":[103],"a":[110,150],"poor":[111],"ability":[112],"detect":[114],"potential":[119],"lead":[121],"false":[123],"detections":[124],"significance.":[126],"The":[127],"are":[132],"simplified":[133],"variants":[134],"should":[142],"be":[143],"discontinued":[144],"measuring":[146],"means.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":10},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":46},{"year":2023,"cited_by_count":24},{"year":2022,"cited_by_count":33},{"year":2021,"cited_by_count":53},{"year":2020,"cited_by_count":36},{"year":2019,"cited_by_count":39},{"year":2018,"cited_by_count":57},{"year":2017,"cited_by_count":42},{"year":2016,"cited_by_count":70},{"year":2015,"cited_by_count":64},{"year":2014,"cited_by_count":63},{"year":2013,"cited_by_count":44},{"year":2012,"cited_by_count":43}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}