{"id":"https://openalex.org/W4411450050","doi":"https://doi.org/10.1145/3729391","title":"Expressing and Checking Statistical Assumptions","display_name":"Expressing and Checking Statistical Assumptions","publication_year":2025,"publication_date":"2025-06-19","ids":{"openalex":"https://openalex.org/W4411450050","doi":"https://doi.org/10.1145/3729391"},"language":"en","primary_location":{"id":"doi:10.1145/3729391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729391","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3729391","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024866221","display_name":"Alexi Turcotte","orcid":"https://orcid.org/0000-0002-0381-0477"},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Alexi Turcotte","raw_affiliation_strings":["CISPA Helmholtz Center for Information Security, Saabr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0000-0002-0381-0477","affiliations":[{"raw_affiliation_string":"CISPA Helmholtz Center for Information Security, Saabr\u00fccken, Germany","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5113129531","display_name":"Zheyuan Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I91712215","display_name":"Saarland University","ror":"https://ror.org/01jdpyv68","country_code":"DE","type":"education","lineage":["https://openalex.org/I91712215"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zheyuan Wu","raw_affiliation_strings":["Saarland University, Saarbr\u00fccken, Germany"],"raw_orcid":"https://orcid.org/0009-0005-2640-4673","affiliations":[{"raw_affiliation_string":"Saarland University, Saarbr\u00fccken, Germany","institution_ids":["https://openalex.org/I91712215"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024866221"],"corresponding_institution_ids":["https://openalex.org/I4210128801"],"apc_list":null,"apc_paid":null,"fwci":2.5549,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.89827036,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2","issue":"FSE","first_page":"2735","last_page":"2758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9922000169754028,"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/T10260","display_name":"Software Engineering Research","score":0.9922000169754028,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9873999953269958,"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/T13398","display_name":"Data Analysis with R","score":0.984499990940094,"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/python","display_name":"Python (programming language)","score":0.855157732963562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7401472330093384},{"id":"https://openalex.org/keywords/statistical-hypothesis-testing","display_name":"Statistical hypothesis testing","score":0.7148383855819702},{"id":"https://openalex.org/keywords/statistical-analysis","display_name":"Statistical analysis","score":0.6090381145477295},{"id":"https://openalex.org/keywords/statistical-model","display_name":"Statistical model","score":0.5052087903022766},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4289896488189697},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.35500848293304443},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2667124271392822},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.2021683156490326},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1439601182937622}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.855157732963562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401472330093384},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.7148383855819702},{"id":"https://openalex.org/C2986587452","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical analysis","level":2,"score":0.6090381145477295},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.5052087903022766},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4289896488189697},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35500848293304443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2667124271392822},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2021683156490326},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1439601182937622}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3729391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729391","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3729391","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3729391","pdf_url":null,"source":{"id":"https://openalex.org/S4404663975","display_name":"Proceedings of the ACM on software engineering.","issn_l":"2994-970X","issn":["2994-970X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM on Software Engineering","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8700000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1514425533","https://openalex.org/W1517053320","https://openalex.org/W1560643704","https://openalex.org/W1569348226","https://openalex.org/W1593793497","https://openalex.org/W1606809877","https://openalex.org/W1975025137","https://openalex.org/W1980038735","https://openalex.org/W1999176266","https://openalex.org/W2000219882","https://openalex.org/W2005970478","https://openalex.org/W2008571234","https://openalex.org/W2016887926","https://openalex.org/W2019781618","https://openalex.org/W2033263428","https://openalex.org/W2052561043","https://openalex.org/W2060438715","https://openalex.org/W2068699266","https://openalex.org/W2085247363","https://openalex.org/W2085259708","https://openalex.org/W2099932042","https://openalex.org/W2107399212","https://openalex.org/W2107399697","https://openalex.org/W2139597778","https://openalex.org/W2151570219","https://openalex.org/W2156661350","https://openalex.org/W2162286641","https://openalex.org/W2170051345","https://openalex.org/W2171992801","https://openalex.org/W2187153216","https://openalex.org/W2768343520","https://openalex.org/W2775363893","https://openalex.org/W2898180589","https://openalex.org/W2898228075","https://openalex.org/W2913593702","https://openalex.org/W2920681612","https://openalex.org/W2936534160","https://openalex.org/W2953682625","https://openalex.org/W2955724775","https://openalex.org/W2971454149","https://openalex.org/W2994988999","https://openalex.org/W3042912077","https://openalex.org/W3098635759","https://openalex.org/W3098865414","https://openalex.org/W3102186774","https://openalex.org/W3105735055","https://openalex.org/W3108760172","https://openalex.org/W3109537811","https://openalex.org/W4225085525","https://openalex.org/W4234335579","https://openalex.org/W4237149050","https://openalex.org/W4237993802","https://openalex.org/W4243529065","https://openalex.org/W4245743185","https://openalex.org/W4248173958","https://openalex.org/W4285782199","https://openalex.org/W4300544062","https://openalex.org/W4307217877","https://openalex.org/W4388336521","https://openalex.org/W4391318841","https://openalex.org/W4392645437"],"related_works":["https://openalex.org/W2207495067","https://openalex.org/W1906486629","https://openalex.org/W2350702655","https://openalex.org/W2319685803","https://openalex.org/W2026012944","https://openalex.org/W4387527746","https://openalex.org/W2359486277","https://openalex.org/W2356483589","https://openalex.org/W2289334277","https://openalex.org/W2785984867"],"abstract_inverted_index":{"Literate":[0],"programming":[1],"environments":[2],"like":[3,13],"Jupyter":[4],"and":[5,15,45,80,114,118,127,138,163],"R":[6],"Markdown":[7],"notebooks,":[8,162],"coupled":[9],"with":[10,70,133],"easy-to-use":[11],"languages":[12],"Python":[14],"R,":[16,117],"put":[17],"a":[18,25,189],"plethora":[19],"of":[20,160,166,174,198],"statistical":[21,39,71,128,136],"methods":[22,32,37,146],"right":[23],"at":[24],"data":[26,101],"analyst\u2019s":[27],"fingertips.":[28],"But":[29],"are":[30,56],"these":[31,96,185],"being":[33,43],"used":[34],"correctly?":[35],"Statistical":[36],"make":[38,184],"assumptions":[40,55,157,186],"about":[41,77],"samples":[42],"analyzed,":[44],"in":[46,108,158,164,196],"many":[47],"cases":[48],"produce":[49],"reasonable":[50],"looking":[51],"results":[52],"even":[53],"if":[54],"not":[57,183],"met.":[58],"We":[59,104],"propose":[60],"an":[61,178],"approach":[62,107],"that":[63,87,143,181],"allows":[64],"library":[65],"developers":[66],"to":[67,119,147,168],"annotate":[68,131],"functions":[69,97],"assumptions,":[72,137],"phrases":[73],"them":[74,121,132],"as":[75],"hypotheses":[76],"the":[78,85,88,134,172],"data,":[79],"inserts":[81],"hypothesis":[82,125,175],"tests":[83],"investigating":[84],"likelihood":[86],"assumption":[89],"is":[90],"met;":[91],"this":[92,106],"way,":[93],"analysts":[94],"using":[95],"will":[98],"have":[99,193],"their":[100],"checked":[102],"automatically.":[103],"implement":[105],"two":[109],"tools:":[110],"prob-check-py":[111],"for":[112,116],"Python,":[113],"prob-check-r":[115],"evaluate":[120],"we":[122],"identify":[123,148],"common":[124],"testing":[126],"modeling":[129],"functions,":[130],"relevant":[135],"run":[139],"128":[140],"Kaggle":[141],"notebooks":[142],"use":[144],"those":[145],"misuses.":[149],"Our":[150],"investigation":[151],"reveals":[152],"statistically":[153],"significant":[154],"evidence":[155],"against":[156],"84.38%":[159],"surveyed":[161],"53.36%":[165],"calls":[167],"annotated":[169],"functions.":[170],"In":[171],"case":[173],"tests,":[176],"had":[177],"equivalent":[179],"test":[180],"did":[182],"been":[187,194],"chosen,":[188],"different":[190],"conclusion":[191],"would":[192],"drawn":[195],"11.51%":[197],"cases.":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}