{"id":"https://openalex.org/W4311079932","doi":"https://doi.org/10.1145/3575637.3575645","title":"Finding Multidimensional Simpson's Paradox","display_name":"Finding Multidimensional Simpson's Paradox","publication_year":2022,"publication_date":"2022-11-29","ids":{"openalex":"https://openalex.org/W4311079932","doi":"https://doi.org/10.1145/3575637.3575645"},"language":"en","primary_location":{"id":"doi:10.1145/3575637.3575645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3575637.3575645","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"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":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-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/A5048030238","display_name":"Jay Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2802647910","display_name":"Burnaby Hospital","ror":"https://ror.org/00z6pvt32","country_code":"CA","type":"healthcare","lineage":["https://openalex.org/I2802647910"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jay Xu","raw_affiliation_strings":["Burnaby Mountain Secondary School, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Burnaby Mountain Secondary School, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I2802647910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062247330","display_name":"Jian Pei","orcid":"https://orcid.org/0000-0002-2200-8711"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Pei","raw_affiliation_strings":["Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052333474","display_name":"Zicun Cong","orcid":"https://orcid.org/0000-0001-7937-1936"},"institutions":[{"id":"https://openalex.org/I18014758","display_name":"Simon Fraser University","ror":"https://ror.org/0213rcc28","country_code":"CA","type":"education","lineage":["https://openalex.org/I18014758"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Zicun Cong","raw_affiliation_strings":["Simon Fraser University, Burnaby, BC, Canada"],"affiliations":[{"raw_affiliation_string":"Simon Fraser University, Burnaby, BC, Canada","institution_ids":["https://openalex.org/I18014758"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048030238"],"corresponding_institution_ids":["https://openalex.org/I2802647910"],"apc_list":null,"apc_paid":null,"fwci":0.3031,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.63140783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"24","issue":"2","first_page":"48","last_page":"60"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9998999834060669,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9914000034332275,"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":0.9799000024795532,"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/computer-science","display_name":"Computer science","score":0.7288123965263367},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5093585252761841},{"id":"https://openalex.org/keywords/multidimensional-data","display_name":"Multidimensional data","score":0.4924484193325043},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4796486496925354},{"id":"https://openalex.org/keywords/phenomenon","display_name":"Phenomenon","score":0.44148463010787964},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.30925655364990234},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.26923704147338867},{"id":"https://openalex.org/keywords/epistemology","display_name":"Epistemology","score":0.23816359043121338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7288123965263367},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5093585252761841},{"id":"https://openalex.org/C3019022308","wikidata":"https://www.wikidata.org/wiki/Q1418353","display_name":"Multidimensional data","level":2,"score":0.4924484193325043},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4796486496925354},{"id":"https://openalex.org/C50335755","wikidata":"https://www.wikidata.org/wiki/Q483247","display_name":"Phenomenon","level":2,"score":0.44148463010787964},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30925655364990234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26923704147338867},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.23816359043121338},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3575637.3575645","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3575637.3575645","pdf_url":null,"source":{"id":"https://openalex.org/S4210176598","display_name":"ACM SIGKDD Explorations Newsletter","issn_l":"1931-0145","issn":["1931-0145","1931-0153"],"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":"ACM SIGKDD Explorations Newsletter","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1585646276","https://openalex.org/W2018300356","https://openalex.org/W2035841117","https://openalex.org/W2048087720","https://openalex.org/W2063841934","https://openalex.org/W2140190241","https://openalex.org/W2905472553","https://openalex.org/W2950416404","https://openalex.org/W2963061618","https://openalex.org/W4230230708","https://openalex.org/W4241830353","https://openalex.org/W6680704940"],"related_works":["https://openalex.org/W4300450609","https://openalex.org/W4386931570","https://openalex.org/W2391010541","https://openalex.org/W2357367123","https://openalex.org/W4388930439","https://openalex.org/W2387276901","https://openalex.org/W2385953334","https://openalex.org/W2351303360","https://openalex.org/W1989881521","https://openalex.org/W2081307663"],"abstract_inverted_index":{"Finding":[0],"and":[1,61,97,155],"analyzing":[2,21],"Simpson's":[3,27,35,54,77],"paradox,":[4,28],"a":[5,45,65,101,107,121,135],"well":[6],"known":[7],"statistical":[8],"phenomenon,":[9],"has":[10],"found":[11],"many":[12],"applications.":[13],"While":[14],"the":[15,22,72,75],"existing":[16],"literature":[17],"focuses":[18],"on":[19,34,80],"only":[20],"causes":[23],"of":[24,74,90,93,103],"identi":[25],"ed":[26],"there":[29],"is":[30,131],"no":[31],"systematic":[32],"analysis":[33],"paradox":[36,55,78],"in":[37,64,148],"multidimensional":[38,66,76],"spaces.":[39],"In":[40],"this":[41,129],"paper,":[42],"we":[43,70],"develop":[44],"simple":[46],"yet":[47],"practical":[48],"approach":[49],"to":[50,87,120,153],"automatically":[51],"identify":[52],"all":[53],"instances":[56,79],"formed":[57],"by":[58],"various":[59],"sub-populations":[60],"separator":[62],"attributes":[63],"data":[67,83,150],"set.":[68],"Moreover,":[69,128],"analyze":[71],"distribution":[73],"three":[81],"real":[82],"sets":[84],"with":[85],"respect":[86],"dimensionality,":[88],"size":[89],"sub-populations,":[91],"participation":[92],"individual":[94],"records,":[95],"redundancy,":[96],"more.":[98],"We":[99],"obtain":[100],"series":[102],"interesting":[104,123],"observations":[105],"about":[106],"few":[108,122],"questions":[109],"that":[110],"have":[111],"never":[112],"been":[113],"asked":[114],"before.":[115],"The":[116],"results":[117],"open":[118],"doors":[119],"directions":[124],"for":[125],"future":[126],"study.":[127],"paper":[130],"an":[132],"outcome":[133],"from":[134],"high-school":[136],"student":[137],"summer":[138],"research":[139,152],"internship.":[140],"It":[141],"re":[142],"ects":[143],"our":[144],"on-going":[145],"e":[146],"ort":[147],"promoting":[149],"science":[151],"youth":[154],"high":[156],"school":[157],"students.":[158]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
