{"id":"https://openalex.org/W3169530247","doi":"https://doi.org/10.1007/s41060-021-00259-z","title":"Analyzing the impact of missing values and selection bias on fairness","display_name":"Analyzing the impact of missing values and selection bias on fairness","publication_year":2021,"publication_date":"2021-05-31","ids":{"openalex":"https://openalex.org/W3169530247","doi":"https://doi.org/10.1007/s41060-021-00259-z","mag":"3169530247"},"language":"en","primary_location":{"id":"doi:10.1007/s41060-021-00259-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-021-00259-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-021-00259-z.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s41060-021-00259-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072807699","display_name":"Yanchen Wang","orcid":"https://orcid.org/0000-0002-1215-2277"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yanchen Wang","raw_affiliation_strings":["Georgetown University, Washington DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgetown University, Washington DC, USA","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005384315","display_name":"Lisa Singh","orcid":"https://orcid.org/0000-0002-8300-2970"},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Lisa Singh","raw_affiliation_strings":["Georgetown University, Washington DC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgetown University, Washington DC, USA","institution_ids":["https://openalex.org/I184565670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005384315","https://openalex.org/A5072807699"],"corresponding_institution_ids":["https://openalex.org/I184565670"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":4.6875,"has_fulltext":true,"cited_by_count":43,"citation_normalized_percentile":{"value":0.94989399,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"12","issue":"2","first_page":"101","last_page":"119"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12520","display_name":"Psychology of Moral and Emotional Judgment","score":0.9046000242233276,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.8202340006828308},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.7304480075836182},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7146211862564087},{"id":"https://openalex.org/keywords/selection-bias","display_name":"Selection bias","score":0.640334963798523},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6262607574462891},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.6213387846946716},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5298340916633606},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.453808069229126},{"id":"https://openalex.org/keywords/real-world-data","display_name":"Real world data","score":0.4293132424354553},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39777714014053345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34191760420799255},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.21436920762062073},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.151615172624588},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14769163727760315}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.8202340006828308},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.7304480075836182},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7146211862564087},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.640334963798523},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6262607574462891},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.6213387846946716},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5298340916633606},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.453808069229126},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.4293132424354553},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39777714014053345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34191760420799255},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.21436920762062073},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.151615172624588},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14769163727760315},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s41060-021-00259-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-021-00259-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-021-00259-z.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s41060-021-00259-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s41060-021-00259-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s41060-021-00259-z.pdf","source":{"id":"https://openalex.org/S4210195017","display_name":"International Journal of Data Science and Analytics","issn_l":"2364-415X","issn":["2364-415X","2364-4168"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319972","host_organization_name":"Springer International Publishing","host_organization_lineage":["https://openalex.org/P4310319972","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer International Publishing","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Data Science and Analytics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G2730983362","display_name":"GCR: Collaborative Research: The Future of Quantitative Research in Social Science","funder_award_id":"1934925","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8754337231","display_name":"GCR: Collaborative Research: The Future of Quantitative Research in Social Science","funder_award_id":"1934494","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G90012497","display_name":"CAREER: Diagnosing Distributed Systems with Provenance","funder_award_id":"1453392","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310223","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3169530247.pdf","grobid_xml":"https://content.openalex.org/works/W3169530247.grobid-xml"},"referenced_works_count":52,"referenced_works":["https://openalex.org/W584462734","https://openalex.org/W612972800","https://openalex.org/W1961345416","https://openalex.org/W1977098485","https://openalex.org/W2006447892","https://openalex.org/W2014352947","https://openalex.org/W2040825624","https://openalex.org/W2044758663","https://openalex.org/W2074184525","https://openalex.org/W2097246321","https://openalex.org/W2100358124","https://openalex.org/W2100960835","https://openalex.org/W2116666691","https://openalex.org/W2116814040","https://openalex.org/W2116984840","https://openalex.org/W2118502261","https://openalex.org/W2139075905","https://openalex.org/W2150997454","https://openalex.org/W2156267802","https://openalex.org/W2159798994","https://openalex.org/W2162670686","https://openalex.org/W2164788271","https://openalex.org/W2170674956","https://openalex.org/W2323554062","https://openalex.org/W2480680997","https://openalex.org/W2483215953","https://openalex.org/W2563852449","https://openalex.org/W2597390287","https://openalex.org/W2748003190","https://openalex.org/W2772803673","https://openalex.org/W2788284633","https://openalex.org/W2788481061","https://openalex.org/W2804927761","https://openalex.org/W2809878087","https://openalex.org/W2891381594","https://openalex.org/W2897978524","https://openalex.org/W2901481055","https://openalex.org/W2947121494","https://openalex.org/W2950538796","https://openalex.org/W2963174898","https://openalex.org/W2963808661","https://openalex.org/W2964031043","https://openalex.org/W2965153324","https://openalex.org/W3023309920","https://openalex.org/W3023525240","https://openalex.org/W3120740533","https://openalex.org/W3121539865","https://openalex.org/W4205701142","https://openalex.org/W4211017048","https://openalex.org/W4243072198","https://openalex.org/W4301518628","https://openalex.org/W6600466347"],"related_works":["https://openalex.org/W2052515325","https://openalex.org/W2050948537","https://openalex.org/W2767646790","https://openalex.org/W4380150146","https://openalex.org/W3024870410","https://openalex.org/W2410652950","https://openalex.org/W2352041579","https://openalex.org/W4283773154","https://openalex.org/W3139174110","https://openalex.org/W2519761320"],"abstract_inverted_index":{"Abstract":[0],"Algorithmic":[1],"decision":[2],"making":[3],"is":[4],"becoming":[5],"more":[6,67],"prevalent,":[7],"increasingly":[8],"impacting":[9],"people\u2019s":[10],"daily":[11],"lives.":[12],"Recently,":[13],"discussions":[14],"have":[15,27,48,62],"been":[16,49],"emerging":[17],"about":[18],"the":[19,33,79,125],"fairness":[20,34,144],"of":[21,35,74,81,119],"decisions":[22],"made":[23],"by":[24,77],"machines.":[25],"Researchers":[26],"proposed":[28],"different":[29,117,149,154],"approaches":[30,40],"for":[31,106],"improving":[32],"these":[36,39,75],"algorithms.":[37],"While":[38],"can":[41],"help":[42],"machines":[43],"make":[44,65],"fairer":[45],"decisions,":[46],"they":[47],"developed":[50],"and":[51,89,98,121,139,146,156],"validated":[52],"on":[53,86,136],"fairly":[54,167],"clean":[55],"data":[56,61,84,107,141],"sets.":[57],"Unfortunately,":[58],"most":[59],"real-world":[60,83,138],"complexities":[63,76],"that":[64,115],"them":[66],"dirty":[68],".":[69],"This":[70],"work":[71],"considers":[72],"two":[73,82],"analyzing":[78],"impact":[80,159],"issues":[85],"fairness\u2014missing":[87],"values":[88,111,151],"selection":[90,113,157],"bias\u2014for":[91],"categorical":[92],"data.":[93],"After":[94],"formulating":[95],"this":[96],"problem":[97],"showing":[99],"its":[100],"existence,":[101],"we":[102],"propose":[103],"fixing":[104],"algorithms":[105],"sets":[108],"containing":[109],"missing":[110,126,150],"and/or":[112],"bias":[114,158],"use":[116],"forms":[118],"reweighting":[120],"resampling":[122],"based":[123],"upon":[124],"value":[127],"generation":[128],"process.":[129],"We":[130],"conduct":[131],"an":[132],"extensive":[133],"empirical":[134],"evaluation":[135],"both":[137],"synthetic":[140],"using":[142],"various":[143],"metrics,":[145],"demonstrate":[147],"how":[148],"generated":[152],"from":[153],"mechanisms":[155],"prediction":[160,164],"fairness,":[161],"even":[162],"when":[163],"accuracy":[165],"remains":[166],"constant.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":6},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}