{"id":"https://openalex.org/W2135985057","doi":"https://doi.org/10.1145/2484028.2484038","title":"On the measurement of test collection reliability","display_name":"On the measurement of test collection reliability","publication_year":2013,"publication_date":"2013-07-28","ids":{"openalex":"https://openalex.org/W2135985057","doi":"https://doi.org/10.1145/2484028.2484038","mag":"2135985057"},"language":"en","primary_location":{"id":"doi:10.1145/2484028.2484038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484038","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"],"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"],"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/A5088729727","display_name":"Diego 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"],"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":13.7521,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.98512382,"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":"393","last_page":"402"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.994700014591217,"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":0.994700014591217,"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":0.9882000088691711,"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/T11106","display_name":"Data Management and Algorithms","score":0.9707000255584717,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/generalizability-theory","display_name":"Generalizability theory","score":0.8645657300949097},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.730143129825592},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6795758605003357},{"id":"https://openalex.org/keywords/data-collection","display_name":"Data collection","score":0.6106940507888794},{"id":"https://openalex.org/keywords/reliability-theory","display_name":"Reliability theory","score":0.5515298247337341},{"id":"https://openalex.org/keywords/classical-test-theory","display_name":"Classical test theory","score":0.5033747553825378},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.5033602118492126},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4609224796295166},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4400276839733124},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.4286400079727173},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.3810056447982788},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.37536653876304626},{"id":"https://openalex.org/keywords/econometrics","display_name":"Econometrics","score":0.34329164028167725},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18958055973052979},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.17483210563659668},{"id":"https://openalex.org/keywords/psychometrics","display_name":"Psychometrics","score":0.12623366713523865},{"id":"https://openalex.org/keywords/item-response-theory","display_name":"Item response theory","score":0.10036727786064148},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08118796348571777}],"concepts":[{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.8645657300949097},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.730143129825592},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6795758605003357},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.6106940507888794},{"id":"https://openalex.org/C201729545","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability theory","level":3,"score":0.5515298247337341},{"id":"https://openalex.org/C140390113","wikidata":"https://www.wikidata.org/wiki/Q389391","display_name":"Classical test theory","level":4,"score":0.5033747553825378},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.5033602118492126},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4609224796295166},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4400276839733124},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.4286400079727173},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3810056447982788},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.37536653876304626},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.34329164028167725},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18958055973052979},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.17483210563659668},{"id":"https://openalex.org/C171606756","wikidata":"https://www.wikidata.org/wiki/Q506132","display_name":"Psychometrics","level":2,"score":0.12623366713523865},{"id":"https://openalex.org/C19875794","wikidata":"https://www.wikidata.org/wiki/Q1207340","display_name":"Item response theory","level":3,"score":0.10036727786064148},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08118796348571777},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/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},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2484028.2484038","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2484028.2484038","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1579063438","https://openalex.org/W1857290810","https://openalex.org/W1958015814","https://openalex.org/W1966835268","https://openalex.org/W1987690005","https://openalex.org/W1992112896","https://openalex.org/W1999331679","https://openalex.org/W2009948657","https://openalex.org/W2015338694","https://openalex.org/W2018182435","https://openalex.org/W2021856948","https://openalex.org/W2022995284","https://openalex.org/W2030649971","https://openalex.org/W2041098697","https://openalex.org/W2073392286","https://openalex.org/W2073722401","https://openalex.org/W2075893676","https://openalex.org/W2110202502","https://openalex.org/W2154884126","https://openalex.org/W2160892561","https://openalex.org/W2161417756","https://openalex.org/W2163004772","https://openalex.org/W2589336814","https://openalex.org/W2917931906","https://openalex.org/W4233760227","https://openalex.org/W4238804190"],"related_works":["https://openalex.org/W81327019","https://openalex.org/W2189229849","https://openalex.org/W2385481685","https://openalex.org/W2579998932","https://openalex.org/W2391379999","https://openalex.org/W2056865070","https://openalex.org/W4245710307","https://openalex.org/W3028623446","https://openalex.org/W2122068924","https://openalex.org/W2363599533"],"abstract_inverted_index":{"The":[0],"reliability":[1,32,43,79,87,169],"of":[2,11,40,75,129,137,150,161,168,174,180,206,226],"a":[3,17,29,165,187,204],"test":[4,41,194,208],"collection":[5,18,42,195],"is":[6,22,229],"proportional":[7],"to":[8,27,91,100,163,192],"the":[9,38,123,126,135,148,158,178,223],"number":[10,160],"queries":[12,21,153,162,228],"it":[13],"contains.":[14],"But":[15],"building":[16],"with":[19],"many":[20],"expensive,":[23],"so":[24,155],"researchers":[25],"have":[26],"find":[28],"balance":[30],"between":[31],"and":[33,54,61,140,152,221],"cost.":[34],"Previous":[35],"work":[36],"on":[37,45,73,82,114,147],"measurement":[39],"relied":[44],"data-based":[46],"approaches":[47],"that":[48,77,142,157,211,222],"contemplated":[49],"random":[50],"what":[51],"if":[52],"scenarios,":[53],"provided":[55],"indicators":[56,80,88,103],"such":[57],"as":[58,69,216,218],"swap":[59],"rates":[60],"Kendall":[62,105],"tau":[63,106],"correlations.":[64],"Generalizability":[65,130],"Theory":[66],"was":[67],"proposed":[68],"an":[70],"alternative":[71],"founded":[72],"analysis":[74],"variance":[76],"provides":[78],"based":[81,113],"statistical":[83],"theory.":[84],"However,":[85],"these":[86,111,138,184,200],"are":[89,144,213],"hard":[90],"interpret":[92],"in":[93,125,172],"practice,":[94],"because":[95],"they":[96,143,212],"do":[97],"not":[98,215],"correspond":[99],"well":[101],"known":[102],"like":[104],"correlation.":[107],"We":[108,132,176],"empirically":[109],"established":[110],"relationships":[112],"data":[115],"from":[116],"over":[117],"40":[118],"TREC":[119,207],"collections,":[120,209],"thus":[121],"filling":[122],"gap":[124],"practical":[127],"interpretation":[128],"Theory.":[131],"also":[133],"review":[134,203],"computation":[136,179],"indicators,":[139],"show":[141],"extremely":[145],"dependent":[146],"sample":[149],"systems":[151],"used,":[154],"much":[156,188],"required":[159],"achieve":[164],"certain":[166],"level":[167],"can":[170],"vary":[171],"orders":[173],"magnitude.":[175],"discuss":[177],"confidence":[181],"intervals":[182],"for":[183,232],"statistics,":[185],"providing":[186],"more":[189],"reliable":[190,217],"tool":[191],"measure":[193],"reliability.":[196],"Reflecting":[197],"upon":[198],"all":[199],"results,":[201],"we":[202],"wealth":[205],"arguing":[210],"possibly":[214],"generally":[219],"accepted":[220],"common":[224],"choice":[225],"50":[227],"insufficient":[230],"even":[231],"stable":[233],"rankings.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}