{"id":"https://openalex.org/W2895183493","doi":"https://doi.org/10.1145/3239572","title":"Estimating Measurement Uncertainty for Information Retrieval Effectiveness Metrics","display_name":"Estimating Measurement Uncertainty for Information Retrieval Effectiveness Metrics","publication_year":2018,"publication_date":"2018-09-29","ids":{"openalex":"https://openalex.org/W2895183493","doi":"https://doi.org/10.1145/3239572","mag":"2895183493"},"language":"en","primary_location":{"id":"doi:10.1145/3239572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3239572","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Estimating_measurement_uncertainty_for_information_retrieval_effectiveness_metrics/27518445","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081861848","display_name":"Alistair Moffat","orcid":"https://orcid.org/0000-0002-6638-0232"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Alistair Moffat","raw_affiliation_strings":["The University of Melbourne, Victoria, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6638-0232","affiliations":[{"raw_affiliation_string":"The University of Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085925326","display_name":"Falk Scholer","orcid":"https://orcid.org/0000-0001-9094-0810"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Falk Scholer","raw_affiliation_strings":["RMIT University, Victoria, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9094-0810","affiliations":[{"raw_affiliation_string":"RMIT University, Victoria, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015195541","display_name":"Ziying Yang","orcid":"https://orcid.org/0000-0001-7705-3280"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ziying Yang","raw_affiliation_strings":["The University of Melbourne, Victoria, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Melbourne, Victoria, Australia","institution_ids":["https://openalex.org/I165779595"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.208,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.85866124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"10","issue":"3","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9994000196456909,"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":0.9994000196456909,"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/T11719","display_name":"Data Quality and Management","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9854999780654907,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/pooling","display_name":"Pooling","score":0.7709786891937256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7443395853042603},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6670326590538025},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6412749290466309},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5312884449958801},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5272682905197144},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.49756887555122375},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49516645073890686},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.49076542258262634},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.47103410959243774},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.44827035069465637},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.4176942706108093},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.33462488651275635},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.3274093270301819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29548853635787964},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2201809585094452},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16430801153182983}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.7709786891937256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7443395853042603},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6670326590538025},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6412749290466309},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5312884449958801},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5272682905197144},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.49756887555122375},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49516645073890686},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.49076542258262634},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.47103410959243774},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.44827035069465637},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.4176942706108093},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.33462488651275635},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.3274093270301819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29548853635787964},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2201809585094452},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16430801153182983},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3239572","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3239572","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},{"id":"pmh:oai:figshare.com:article/27518445","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Estimating_measurement_uncertainty_for_information_retrieval_effectiveness_metrics/27518445","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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:figshare.com:article/27518445","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Estimating_measurement_uncertainty_for_information_retrieval_effectiveness_metrics/27518445","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"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/G2759510716","display_name":"Finding answers for complex questions","funder_award_id":"DP180102687","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1237471683","https://openalex.org/W1507150160","https://openalex.org/W1515852583","https://openalex.org/W1546195864","https://openalex.org/W1966835268","https://openalex.org/W1968927634","https://openalex.org/W1990190154","https://openalex.org/W2001142465","https://openalex.org/W2004737172","https://openalex.org/W2004918107","https://openalex.org/W2008285050","https://openalex.org/W2009543464","https://openalex.org/W2021581601","https://openalex.org/W2022995284","https://openalex.org/W2034173707","https://openalex.org/W2037140704","https://openalex.org/W2053100920","https://openalex.org/W2058896506","https://openalex.org/W2059120814","https://openalex.org/W2068098598","https://openalex.org/W2069870183","https://openalex.org/W2073913493","https://openalex.org/W2075893676","https://openalex.org/W2081033951","https://openalex.org/W2081983182","https://openalex.org/W2096623622","https://openalex.org/W2102698119","https://openalex.org/W2109244020","https://openalex.org/W2113640060","https://openalex.org/W2120308175","https://openalex.org/W2124504084","https://openalex.org/W2126712138","https://openalex.org/W2141175968","https://openalex.org/W2183117384","https://openalex.org/W2231711798","https://openalex.org/W2336806308","https://openalex.org/W2388783363","https://openalex.org/W2469056188","https://openalex.org/W2530530386","https://openalex.org/W2604466072","https://openalex.org/W2609795610","https://openalex.org/W2617066442","https://openalex.org/W2624553223","https://openalex.org/W2740692915","https://openalex.org/W2752377997","https://openalex.org/W2794432940","https://openalex.org/W4255492838","https://openalex.org/W4298982457"],"related_works":["https://openalex.org/W3127142483","https://openalex.org/W4385565564","https://openalex.org/W2898073868","https://openalex.org/W2138488530","https://openalex.org/W2798835721","https://openalex.org/W2971071571","https://openalex.org/W2387658907","https://openalex.org/W2922169395","https://openalex.org/W2385796165","https://openalex.org/W25098770"],"abstract_inverted_index":{"One":[0],"typical":[1],"way":[2],"of":[3,10,20,49,51,63,68,82,137,153,165,200,207,214,244,263,272],"building":[4],"test":[5,276],"collections":[6,277],"for":[7,34,60],"offline":[8],"measurement":[9,139,208,264],"information":[11],"retrieval":[12],"systems":[13,22],"is":[14],"to":[15,24,57,78,91,116,197,204,241,258,269],"pool":[16,155],"the":[17,45,52,61,65,69,80,87,101,108,117,130,151,159,181,186,198,201,205,212,242,248,270],"ranked":[18],"outputs":[19],"different":[21],"down":[23],"some":[25],"chosen":[26],"depth":[27],"d":[28,47],"and":[29,96,104,157,169,203],"then":[30,55,128],"form":[31],"relevance":[32],"judgments":[33],"those":[35,123],"documents":[36,274],"only.":[37],"Non-pooled":[38],"documents\u2014ones":[39],"that":[40,83,132,161,180,232,266],"did":[41],"not":[42],"appear":[43],"in":[44,141,144,163,239,275],"top-":[46],"sets":[48],"any":[50],"contributing":[53],"systems\u2014are":[54],"deemed":[56],"be":[58,113],"non-relevant":[59],"purposes":[62],"evaluating":[64],"relative":[66],"behavior":[67],"systems.":[70],"In":[71],"this":[72],"article,":[73],"we":[74],"use":[75],"RBP-derived":[76],"residuals":[77],"re-examine":[79],"reliability":[81],"process.":[84],"By":[85],"fitting":[86],"RBP":[88],"parameter":[89],"\u03d5":[90],"maximize":[92],"similarity":[93],"between":[94],"AP-":[95],"NDCG-induced":[97],"system":[98,170],"rankings,":[99,106],"on":[100,107],"one":[102],"hand,":[103],"RBP-induced":[105],"other,":[109],"an":[110,135],"estimate":[111],"can":[112],"made":[114],"as":[115,224],"potential":[118],"score":[119,168],"uncertainty":[120,140,209,265],"associated":[121],"with":[122,146,278],"two":[124],"recall-based":[125,147],"metrics.":[126],"We":[127,229],"consider":[129],"effect":[131,152],"residual":[133,202,249],"size\u2014as":[134],"indicator":[136],"possible":[138],"utility-based":[142],"metrics\u2014has":[143],"connection":[145],"metrics":[148],"by":[149,190,211,252],"computing":[150],"increasing":[154],"sizes":[156],"examining":[158],"trends":[160],"arise":[162],"terms":[164],"both":[166],"metric":[167],"separability":[171],"using":[172],"standard":[173],"statistical":[174,191,245],"tests.":[175],"The":[176],"experimental":[177,235],"results":[178,236],"show":[179],"confidence":[182,218],"levels":[183],"expressed":[184],"via":[185],"p":[187],"-values":[188],"generated":[189,251],"tests":[192],"are":[193,227],"only":[194],"weakly":[195],"connected":[196],"size":[199],"degree":[206],"caused":[210],"presence":[213,271],"unjudged":[215,273],"documents.":[216],"Statistical":[217],"estimates":[219],"are,":[220],"however,":[221],"largely":[222],"consistent":[223],"pooling":[225],"depths":[226],"altered.":[228],"therefore":[230],"recommend":[231],"all":[233],"such":[234],"should":[237],"report,":[238],"addition":[240],"outcomes":[243],"significance":[246],"tests,":[247],"measurements":[250],"a":[253,260],"suitably":[254],"matched":[255],"weighted-precision":[256],"metric,":[257],"give":[259],"clear":[261],"indication":[262],"arises":[267],"due":[268],"finite":[279],"pooled":[280],"judgments.":[281]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}