{"id":"https://openalex.org/W2064459117","doi":"https://doi.org/10.1145/2808194.2809469","title":"Bayesian Inference for Information Retrieval Evaluation","display_name":"Bayesian Inference for Information Retrieval Evaluation","publication_year":2015,"publication_date":"2015-09-22","ids":{"openalex":"https://openalex.org/W2064459117","doi":"https://doi.org/10.1145/2808194.2809469","mag":"2064459117"},"language":"en","primary_location":{"id":"doi:10.1145/2808194.2809469","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808194.2809469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 International Conference on The Theory of 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/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":true,"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":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5078123101"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"31","last_page":"40"},"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/T10028","display_name":"Topic Modeling","score":0.995199978351593,"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/T11719","display_name":"Data Quality and Management","score":0.9945999979972839,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7390422224998474},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.7148654460906982},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6449312567710876},{"id":"https://openalex.org/keywords/randomness","display_name":"Randomness","score":0.6285930871963501},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.5500754117965698},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5137999653816223},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.5061933398246765},{"id":"https://openalex.org/keywords/wilcoxon-signed-rank-test","display_name":"Wilcoxon signed-rank test","score":0.4981210231781006},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4848952889442444},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4666813313961029},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4650047719478607},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4614601731300354},{"id":"https://openalex.org/keywords/statistical-inference","display_name":"Statistical inference","score":0.4592582583427429},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.4518468379974365},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.43987682461738586},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4157494604587555},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.21797701716423035},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14984768629074097}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7390422224998474},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.7148654460906982},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6449312567710876},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.6285930871963501},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.5500754117965698},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5137999653816223},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5061933398246765},{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.4981210231781006},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4848952889442444},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4666813313961029},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4650047719478607},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4614601731300354},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.4592582583427429},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.4518468379974365},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.43987682461738586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4157494604587555},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.21797701716423035},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14984768629074097},{"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/C12868164","wikidata":"https://www.wikidata.org/wiki/Q1424533","display_name":"Mann\u2013Whitney U test","level":2,"score":0.0},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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":1,"locations":[{"id":"doi:10.1145/2808194.2809469","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2808194.2809469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2015 International Conference on The Theory of Information Retrieval","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W137875067","https://openalex.org/W603193392","https://openalex.org/W1513618424","https://openalex.org/W1968927634","https://openalex.org/W1990190154","https://openalex.org/W1992411228","https://openalex.org/W2017292914","https://openalex.org/W2031858317","https://openalex.org/W2046011778","https://openalex.org/W2058896506","https://openalex.org/W2069870183","https://openalex.org/W2070192299","https://openalex.org/W2075893676","https://openalex.org/W2104822358","https://openalex.org/W2113640060","https://openalex.org/W2130076000","https://openalex.org/W2132314908","https://openalex.org/W2148440018","https://openalex.org/W4205418141","https://openalex.org/W4232383088","https://openalex.org/W6662203318"],"related_works":["https://openalex.org/W4377083194","https://openalex.org/W3039360660","https://openalex.org/W2461683294","https://openalex.org/W4226211120","https://openalex.org/W1987205174","https://openalex.org/W2380849986","https://openalex.org/W4321447026","https://openalex.org/W1993033667","https://openalex.org/W4253480028","https://openalex.org/W2504417049"],"abstract_inverted_index":{"A":[0,28,95],"key":[1],"component":[2],"of":[3,22,46,101,108,158,169],"experimentation":[4],"in":[5,41,63,70,91,110,141],"IR":[6,71,111],"is":[7,49,58,112],"statistical":[8,29],"hypothesis":[9,30],"testing,":[10],"which":[11],"researchers":[12],"and":[13,56,121,165],"developers":[14],"use":[15],"to":[16,26,51,147],"make":[17],"inferences":[18],"about":[19],"the":[20,35,44,66,73,75,87,102,105,113,118,148,156],"effectiveness":[21,42,119,149],"their":[23],"system":[24],"relative":[25],"others.":[27],"test":[31,78],"can":[32],"tell":[33],"us":[34],"likelihood":[36],"that":[37,104,124,138],"small":[38],"mean":[39],"differences":[40],"(on":[43],"order":[45],"5%,":[47],"say)":[48],"due":[50],"randomness":[52],"or":[53],"measurement":[54,109],"error,":[55],"thus":[57],"critical":[59],"for":[60,86],"making":[61],"progress":[62],"research.":[64],"But":[65],"tests":[67,123],"typically":[68],"used":[69],"-":[72,79],"t-test,":[74],"Wilcoxon":[76],"signed-rank":[77],"are":[80],"very":[81],"general,":[82],"not":[83],"developed":[84],"specifically":[85],"problems":[88],"we":[89,131,151],"face":[90],"information":[92],"retrieval":[93],"evaluation.":[94],"better":[96],"approach":[97],"would":[98],"take":[99],"advantage":[100],"fact":[103],"atomic":[106],"unit":[107],"relevance":[114,126,140],"judgment":[115],"rather":[116],"than":[117],"measure,":[120],"develop":[122],"model":[125,160],"directly.":[127],"In":[128],"this":[129,142],"work":[130],"present":[132],"such":[133],"an":[134],"approach,":[135],"showing":[136],"theoretically":[137],"modeling":[139],"way":[143],"naturally":[144],"gives":[145],"rise":[146],"measures":[150],"care":[152],"about.":[153],"We":[154],"demonstrate":[155],"usefulness":[157],"our":[159],"on":[161],"both":[162],"simulated":[163],"data":[164],"a":[166],"diverse":[167],"set":[168],"runs":[170],"from":[171],"various":[172],"TREC":[173],"tracks.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}