{"id":"https://openalex.org/W2891314889","doi":"https://doi.org/10.1145/3234944.3234971","title":"Topic Set Size Design for Paired and Unpaired Data","display_name":"Topic Set Size Design for Paired and Unpaired Data","publication_year":2018,"publication_date":"2018-09-10","ids":{"openalex":"https://openalex.org/W2891314889","doi":"https://doi.org/10.1145/3234944.3234971","mag":"2891314889"},"language":"en","primary_location":{"id":"doi:10.1145/3234944.3234971","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3234944.3234971","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3234944.3234971","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3234944.3234971","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023595778","display_name":"Tetsuya Sakai","orcid":"https://orcid.org/0000-0002-6720-963X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Tetsuya Sakai","raw_affiliation_strings":["Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5023595778"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.2371,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57502116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"199","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11235","display_name":"Statistical Methods in Clinical Trials","score":0.9904000163078308,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13398","display_name":"Data Analysis with R","score":0.9781000018119812,"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":0.9745000004768372,"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/sample-size-determination","display_name":"Sample size determination","score":0.8095930814743042},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.6692278385162354},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.6026794910430908},{"id":"https://openalex.org/keywords/analysis-of-variance","display_name":"Analysis of variance","score":0.5962334275245667},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5830563902854919},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5609409809112549},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.5443439483642578},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5144891738891602},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5066419243812561},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.47281256318092346},{"id":"https://openalex.org/keywords/repeated-measures-design","display_name":"Repeated measures design","score":0.45613840222358704},{"id":"https://openalex.org/keywords/statistical-power","display_name":"Statistical power","score":0.44873884320259094},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.42108750343322754},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4105331003665924},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3965318202972412}],"concepts":[{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.8095930814743042},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.6692278385162354},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.6026794910430908},{"id":"https://openalex.org/C99476002","wikidata":"https://www.wikidata.org/wiki/Q42297","display_name":"Analysis of variance","level":2,"score":0.5962334275245667},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5830563902854919},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5609409809112549},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.5443439483642578},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5144891738891602},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5066419243812561},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.47281256318092346},{"id":"https://openalex.org/C102959455","wikidata":"https://www.wikidata.org/wiki/Q7313954","display_name":"Repeated measures design","level":2,"score":0.45613840222358704},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.44873884320259094},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.42108750343322754},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4105331003665924},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3965318202972412},{"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/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3234944.3234971","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3234944.3234971","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3234944.3234971","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3234944.3234971","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3234944.3234971","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3234944.3234971","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM SIGIR International Conference on Theory of Information Retrieval","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2891314889.pdf","grobid_xml":"https://content.openalex.org/works/W2891314889.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W39572901","https://openalex.org/W1484194788","https://openalex.org/W1824124613","https://openalex.org/W1990190154","https://openalex.org/W2015629112","https://openalex.org/W2017292914","https://openalex.org/W2021856948","https://openalex.org/W2023217403","https://openalex.org/W2058896506","https://openalex.org/W2163004772","https://openalex.org/W2892654592"],"related_works":["https://openalex.org/W1989415248","https://openalex.org/W977438452","https://openalex.org/W3041891053","https://openalex.org/W139386289","https://openalex.org/W2107645900","https://openalex.org/W2883778230","https://openalex.org/W2971193366","https://openalex.org/W3183286355","https://openalex.org/W1663268383","https://openalex.org/W4386762140"],"abstract_inverted_index":{"Topic":[0],"set":[1,114,154,186],"size":[2,115,155,187],"design":[3,116,156,188],"is":[4,100,171],"an":[5,13],"approach":[6,129],"to":[7,103],"determining":[8],"the":[9,33,39,54,77,87,91,104,109,112,126,136,143,160,163,167,175,201],"sample":[10,133,203],"sizes":[11,134,204],"of":[12,17,53,73,111,162,177,181],"experiment":[14],"(e.g.,":[15],"number":[16],"topics)":[18],"based":[19,118],"on":[20,32,60,119],"a":[21,25,30,50,58,70,194],"statistical":[22,27],"requirement,":[23],"namely":[24],"desired":[26,51,71],"power":[28,52,72],"or":[29],"cap":[31,59],"confidence":[34],"interval":[35],"(CI)":[36],"width":[37],"for":[38,49,57,69,86,90,148,166,197,205,212],"difference":[40],"in":[41],"means.":[42],"Previous":[43],"work":[44],"considered":[45],"paired":[46,144,168,213],"data":[47,67,169,207],"cases":[48,68,85,147],"t-test":[55,88,138],"and":[56,89,123,145,151,183,200],"CI":[61,92],"width,":[62],"as":[63,65,190],"well":[64],"unpaired":[66,82,146,206],"one-way":[74,95,127],"ANOVA.":[75],"In":[76],"present":[78],"study,":[79],"we":[80,107,141,173],"consider":[81],"(i.e.,":[83],"two-sample)":[84],"width.":[93],"Since":[94],"ANOVA":[96],"with":[97],"two":[98,121],"groups":[99],"strictly":[101],"equivalent":[102],"two-sample":[105,137],"t-test,":[106],"compare":[108,142],"outcomes":[110],"topic":[113,153,185],"results":[117],"these":[120],"approaches,":[122],"show":[124],"that":[125],"ANOVA-based":[128],"actually":[130],"returns":[131],"tighter":[132],"than":[135],"approach.":[139],"Moreover,":[140],"both":[149],"t-test-based":[150,182],"CI-based":[152,184],"approaches.":[157],"Because":[158],"estimating":[159],"variance":[161,195],"score":[164],"differences":[165],"setting":[170],"problematic,":[172],"recommend":[174],"use":[176],"our":[178],"unpaired-data":[179],"versions":[180],"tools,":[189],"they":[191],"only":[192],"require":[193],"estimate":[196],"individual":[198],"scores":[199],"appropriate":[202],"are":[208],"also":[209],"large":[210],"enough":[211],"data.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}