{"id":"https://openalex.org/W2017826930","doi":"https://doi.org/10.1145/1571941.1572050","title":"Agreement among statistical significance tests for information retrieval evaluation at varying sample sizes","display_name":"Agreement among statistical significance tests for information retrieval evaluation at varying sample sizes","publication_year":2009,"publication_date":"2009-07-19","ids":{"openalex":"https://openalex.org/W2017826930","doi":"https://doi.org/10.1145/1571941.1572050","mag":"2017826930"},"language":"en","primary_location":{"id":"doi:10.1145/1571941.1572050","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"conference-paper","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/A5049222552","display_name":"Mark D. Smucker","orcid":"https://orcid.org/0000-0003-4968-6405"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Mark D. Smucker","raw_affiliation_strings":["University of Waterloo, Waterloo, ON, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, ON, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"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, USA","University Of Massachusetts Amherst, Amherst, MA, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]},{"raw_affiliation_string":"University Of Massachusetts Amherst, Amherst, MA, USA#TAB#","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/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ben Carterette","raw_affiliation_strings":["University of Delaware, Newark, DE, USA","University of Delaware, Newark, DE. USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware, Newark, DE. USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"630","last_page":"631"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9646000266075134,"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":0.9646000266075134,"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/T13398","display_name":"Data Analysis with R","score":0.9603999853134155,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9589999914169312,"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/randomization","display_name":"Randomization","score":0.6892179846763611},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.6181444525718689},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5983390212059021},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.5733084678649902},{"id":"https://openalex.org/keywords/sample-size-determination","display_name":"Sample size determination","score":0.5558576583862305},{"id":"https://openalex.org/keywords/statistical-significance","display_name":"Statistical significance","score":0.5181145071983337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4668448865413666},{"id":"https://openalex.org/keywords/post-hoc","display_name":"Post hoc","score":0.4580089747905731},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4568319022655487},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.421725332736969},{"id":"https://openalex.org/keywords/randomized-controlled-trial","display_name":"Randomized controlled trial","score":0.14126095175743103},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.11036443710327148}],"concepts":[{"id":"https://openalex.org/C204243189","wikidata":"https://www.wikidata.org/wiki/Q1363085","display_name":"Randomization","level":3,"score":0.6892179846763611},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.6181444525718689},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5983390212059021},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5733084678649902},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.5558576583862305},{"id":"https://openalex.org/C65409693","wikidata":"https://www.wikidata.org/wiki/Q425265","display_name":"Statistical significance","level":2,"score":0.5181145071983337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4668448865413666},{"id":"https://openalex.org/C2992886853","wikidata":"https://www.wikidata.org/wiki/Q18381816","display_name":"Post hoc","level":2,"score":0.4580089747905731},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4568319022655487},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.421725332736969},{"id":"https://openalex.org/C168563851","wikidata":"https://www.wikidata.org/wiki/Q1436668","display_name":"Randomized controlled trial","level":2,"score":0.14126095175743103},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.11036443710327148},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C141071460","wikidata":"https://www.wikidata.org/wiki/Q40821","display_name":"Surgery","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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C199343813","wikidata":"https://www.wikidata.org/wiki/Q12128","display_name":"Dentistry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1571941.1572050","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1571941.1572050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.366.8139","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.366.8139","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=885","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.388.2185","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.388.2185","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-statSigPart2-sigir2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.800000011920929,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":2,"referenced_works":["https://openalex.org/W1990190154","https://openalex.org/W2021856948"],"related_works":["https://openalex.org/W4378232449","https://openalex.org/W4386762140","https://openalex.org/W2093946342","https://openalex.org/W3195377381","https://openalex.org/W1505970868","https://openalex.org/W241182866","https://openalex.org/W2979681497","https://openalex.org/W2904195262","https://openalex.org/W2911405330","https://openalex.org/W4318819743"],"abstract_inverted_index":{"Research":[0],"has":[1],"shown":[2],"that":[3,44],"little":[4],"practical":[5],"difference":[6],"exists":[7],"between":[8],"the":[9,51,61,70,88,95,102,105,109,117],"randomization,":[10],"Student's":[11],"paired":[12],"t,":[13],"and":[14],"bootstrap":[15,78],"tests":[16,32,46],"of":[17,53,59,97,104,119],"statistical":[18],"significance":[19],"for":[20,72],"TREC":[21],"ad-hoc":[22],"retrieval":[23],"experiments":[24],"with":[25,35,90],"50":[26],"topics.":[27,41],"We":[28,42,100],"compared":[29],"these":[30,45],"three":[31],"on":[33],"runs":[34],"topic":[36],"sizes":[37],"down":[38],"to":[39,65,112],"10":[40],"found":[43],"show":[47],"increasing":[48,93],"disagreement":[49],"as":[50,94],"number":[52,96,118],"topics":[54,98,120],"decreases.":[55],"At":[56],"smaller":[57,67],"numbers":[58],"topics,":[60],"randomization":[62,106],"test":[63,107],"tended":[64],"produce":[66],"p-values":[68,73,84],"than":[69,75,87],"t-test":[71,89,110],"less":[74,86],"0.1.":[76],"The":[77],"exhibited":[79],"a":[80],"systematic":[81],"bias":[82,92],"towards":[83],"strictly":[85],"this":[91],"decreased.":[99],"recommend":[101],"use":[103],"although":[108],"appears":[111],"be":[113],"suitable":[114],"even":[115],"when":[116],"is":[121],"small.":[122]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-16T13:24:37.021932","created_date":"2025-10-10T00:00:00"}
