{"id":"https://openalex.org/W3158689111","doi":"https://doi.org/10.1145/3412841.3441945","title":"Testing the tests","display_name":"Testing the tests","publication_year":2021,"publication_date":"2021-03-22","ids":{"openalex":"https://openalex.org/W3158689111","doi":"https://doi.org/10.1145/3412841.3441945","mag":"3158689111"},"language":"en","primary_location":{"id":"doi:10.1145/3412841.3441945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3412841.3441945","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 Annual ACM Symposium on Applied Computing","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/A5046723532","display_name":"Javier Parapar","orcid":"https://orcid.org/0000-0002-5997-8252"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Javier Parapar","raw_affiliation_strings":["Universidade da Coru\u00f1a, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Universidade da Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020247368","display_name":"David E. Losada","orcid":"https://orcid.org/0000-0001-8823-7501"},"institutions":[{"id":"https://openalex.org/I200284239","display_name":"Universidade de Santiago de Compostela","ror":"https://ror.org/030eybx10","country_code":"ES","type":"education","lineage":["https://openalex.org/I200284239"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David E. Losada","raw_affiliation_strings":["Universidade de Santiago de Compostela, Santiago de Compostela, Spain"],"affiliations":[{"raw_affiliation_string":"Universidade de Santiago de Compostela, Santiago de Compostela, Spain","institution_ids":["https://openalex.org/I200284239"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056469959","display_name":"\u00c1lvaro Barreiro","orcid":"https://orcid.org/0000-0002-6698-2946"},"institutions":[{"id":"https://openalex.org/I11019714","display_name":"Universidade da Coru\u00f1a","ror":"https://ror.org/01qckj285","country_code":"ES","type":"education","lineage":["https://openalex.org/I11019714"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"\u00c1lvaro Barreiro","raw_affiliation_strings":["Universidade da Coru\u00f1a, A Coru\u00f1a, Spain"],"affiliations":[{"raw_affiliation_string":"Universidade da Coru\u00f1a, A Coru\u00f1a, Spain","institution_ids":["https://openalex.org/I11019714"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046723532"],"corresponding_institution_ids":["https://openalex.org/I11019714"],"apc_list":null,"apc_paid":null,"fwci":3.3049,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.92864857,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"655","last_page":"664"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.996999979019165,"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":0.996999979019165,"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":0.9925000071525574,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9753000140190125,"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/wilcoxon-signed-rank-test","display_name":"Wilcoxon signed-rank test","score":0.8016707897186279},{"id":"https://openalex.org/keywords/null-hypothesis","display_name":"Null hypothesis","score":0.7675387859344482},{"id":"https://openalex.org/keywords/sign-test","display_name":"Sign test","score":0.7060451507568359},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.6795636415481567},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.6036893129348755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.60100919008255},{"id":"https://openalex.org/keywords/null","display_name":"Null (SQL)","score":0.5747050642967224},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.5703039765357971},{"id":"https://openalex.org/keywords/type-i-and-type-ii-errors","display_name":"Type I and type II errors","score":0.486975759267807},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.478685200214386},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.4724871516227722},{"id":"https://openalex.org/keywords/sign","display_name":"Sign (mathematics)","score":0.47077271342277527},{"id":"https://openalex.org/keywords/alternative-hypothesis","display_name":"Alternative hypothesis","score":0.44902125000953674},{"id":"https://openalex.org/keywords/multiple-comparisons-problem","display_name":"Multiple comparisons problem","score":0.4304954707622528},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.42640718817710876},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4134463965892792},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4117535948753357},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.362676203250885},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3602054715156555},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25794118642807007},{"id":"https://openalex.org/keywords/mann\u2013whitney-u-test","display_name":"Mann\u2013Whitney U test","score":0.2161272168159485}],"concepts":[{"id":"https://openalex.org/C206041023","wikidata":"https://www.wikidata.org/wiki/Q1751970","display_name":"Wilcoxon signed-rank test","level":3,"score":0.8016707897186279},{"id":"https://openalex.org/C191988596","wikidata":"https://www.wikidata.org/wiki/Q628374","display_name":"Null hypothesis","level":2,"score":0.7675387859344482},{"id":"https://openalex.org/C165793278","wikidata":"https://www.wikidata.org/wiki/Q2301904","display_name":"Sign test","level":4,"score":0.7060451507568359},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.6795636415481567},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.6036893129348755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.60100919008255},{"id":"https://openalex.org/C203763787","wikidata":"https://www.wikidata.org/wiki/Q371029","display_name":"Null (SQL)","level":2,"score":0.5747050642967224},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5703039765357971},{"id":"https://openalex.org/C40696583","wikidata":"https://www.wikidata.org/wiki/Q989120","display_name":"Type I and type II errors","level":2,"score":0.486975759267807},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.478685200214386},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.4724871516227722},{"id":"https://openalex.org/C139676723","wikidata":"https://www.wikidata.org/wiki/Q1193832","display_name":"Sign (mathematics)","level":2,"score":0.47077271342277527},{"id":"https://openalex.org/C120577422","wikidata":"https://www.wikidata.org/wiki/Q843558","display_name":"Alternative hypothesis","level":3,"score":0.44902125000953674},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.4304954707622528},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.42640718817710876},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4134463965892792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4117535948753357},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.362676203250885},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3602054715156555},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25794118642807007},{"id":"https://openalex.org/C12868164","wikidata":"https://www.wikidata.org/wiki/Q1424533","display_name":"Mann\u2013Whitney U test","level":2,"score":0.2161272168159485},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3412841.3441945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3412841.3441945","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 Annual ACM Symposium on Applied Computing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5799999833106995}],"awards":[{"id":"https://openalex.org/G2998566577","display_name":null,"funder_award_id":"ED431B 2019/03, ED431G/01, ED431G-2019/04 and ED431C 2018/29","funder_id":"https://openalex.org/F4320326655","funder_display_name":"Xunta de Galicia"},{"id":"https://openalex.org/G6924016019","display_name":null,"funder_award_id":"RTI2018-093336-B-C21 and RTI2018-093336-B-C22","funder_id":"https://openalex.org/F4320315062","funder_display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades"}],"funders":[{"id":"https://openalex.org/F4320315062","display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","ror":null},{"id":"https://openalex.org/F4320326655","display_name":"Xunta de Galicia","ror":"https://ror.org/0181xnw06"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W103650626","https://openalex.org/W1983482950","https://openalex.org/W1990190154","https://openalex.org/W1997917263","https://openalex.org/W1998328714","https://openalex.org/W1998481788","https://openalex.org/W2010497813","https://openalex.org/W2015338694","https://openalex.org/W2015727153","https://openalex.org/W2027615005","https://openalex.org/W2028699459","https://openalex.org/W2042899581","https://openalex.org/W2048489440","https://openalex.org/W2052569738","https://openalex.org/W2053584122","https://openalex.org/W2057216062","https://openalex.org/W2075893676","https://openalex.org/W2165685161","https://openalex.org/W2303308758","https://openalex.org/W2336806308","https://openalex.org/W2463093044","https://openalex.org/W2793679191","https://openalex.org/W2798550416","https://openalex.org/W2914164530","https://openalex.org/W3100125037","https://openalex.org/W3100184886","https://openalex.org/W4243617875","https://openalex.org/W4253292190","https://openalex.org/W4254065450","https://openalex.org/W4288280764"],"related_works":["https://openalex.org/W154531455","https://openalex.org/W2113330311","https://openalex.org/W2058846847","https://openalex.org/W2113381189","https://openalex.org/W2915316750","https://openalex.org/W1505944461","https://openalex.org/W104021676","https://openalex.org/W2906877126","https://openalex.org/W2106547200","https://openalex.org/W1995992573"],"abstract_inverted_index":{"Null":[0],"Hypothesis":[1],"Significance":[2],"Testing":[3],"(NHST)":[4],"has":[5],"been":[6],"recurrently":[7],"employed":[8],"as":[9,31,191],"the":[10,15,32,34,39,42,46,50,58,94,108,120,130,140,145,159,176,180,192],"reference":[11,193],"framework":[12],"to":[13,71,115,119,195],"assess":[14,196],"difference":[16],"in":[17,61,82,99],"performance":[18],"between":[19,198],"Information":[20],"Retrieval":[21],"(IR)":[22],"systems.":[23,200],"IR":[24,62,186,199],"practitioners":[25,187],"customarily":[26],"apply":[27],"significance":[28,97,121],"tests,":[29],"such":[30,124],"t-test,":[33],"Wilcoxon":[35,177],"Signed":[36],"Rank":[37],"test,":[38,41],"Permutation":[40],"Sign":[43],"test":[44,178,183],"or":[45,142],"Bootstrap":[47],"test.":[48],"However,":[49],"question":[51],"of":[52,54,96,144,155,161],"which":[53],"these":[55],"tests":[56,98],"is":[57,64,179],"most":[59,181],"reliable":[60,182],"experimentation":[63],"still":[65],"controversial.":[66],"Different":[67],"authors":[68],"have":[69],"tried":[70],"shed":[72],"light":[73],"on":[74],"this":[75,85],"issue,":[76],"but":[77],"their":[78],"conclusions":[79],"are":[80],"not":[81],"agreement.":[83],"In":[84],"paper,":[86],"we":[87,127,151],"present":[88],"a":[89,153],"new":[90],"methodology":[91],"for":[92],"assessing":[93],"behavior":[95],"typical":[100],"ranking":[101],"tasks.":[102],"Our":[103],"method":[104],"creates":[105],"models":[106,114],"from":[107],"search":[109],"systems":[110],"and":[111,133,164],"uses":[112],"those":[113],"simulate":[116],"different":[117,170],"inputs":[118],"tests.":[122,171],"With":[123],"an":[125],"approach,":[126],"can":[128],"control":[129],"experimental":[131],"conditions":[132],"run":[134],"experiments":[135],"with":[136],"full":[137],"knowledge":[138],"about":[139],"truth":[141],"falseness":[143],"null":[146],"hypothesis.":[147],"Following":[148],"our":[149],"methodology,":[150],"computed":[152],"series":[154],"simulations":[156],"that":[157,175],"estimate":[158],"proportion":[160],"Type":[162,165],"I":[163],"II":[166],"errors":[167],"made":[168],"by":[169],"Results":[172],"conclusively":[173],"suggest":[174],"and,":[184],"thus,":[185],"should":[188],"adopt":[189],"it":[190],"tool":[194],"differences":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2021-05-10T00:00:00"}
