{"id":"https://openalex.org/W2046793639","doi":"https://doi.org/10.1145/1147234.1147247","title":"The problem of disguised missing data","display_name":"The problem of disguised missing data","publication_year":2006,"publication_date":"2006-06-01","ids":{"openalex":"https://openalex.org/W2046793639","doi":"https://doi.org/10.1145/1147234.1147247","mag":"2046793639"},"language":"en","primary_location":{"id":"doi:10.1145/1147234.1147247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1147234.1147247","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/A5015068464","display_name":"Ronald K. Pearson","orcid":"https://orcid.org/0000-0002-0302-2390"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ronald K. Pearson","raw_affiliation_strings":["ProSanos Corporation, Harrisburg, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ProSanos Corporation, Harrisburg, PA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5015068464"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9649,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.94146924,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"8","issue":"1","first_page":"83","last_page":"92"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.9991000294685364,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9973000288009644,"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":0.9847000241279602,"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/missing-data","display_name":"Missing data","score":0.9512090682983398},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.812371551990509},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5479356050491333},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.5403673052787781},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47425925731658936},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4441341161727905},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3776063621044159},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.22498145699501038}],"concepts":[{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.9512090682983398},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812371551990509},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5479356050491333},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.5403673052787781},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47425925731658936},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4441341161727905},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3776063621044159},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.22498145699501038},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1147234.1147247","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1147234.1147247","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":[{"display_name":"Reduced inequalities","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W277824517","https://openalex.org/W1483032785","https://openalex.org/W1513289763","https://openalex.org/W1513618424","https://openalex.org/W1522984953","https://openalex.org/W1619226191","https://openalex.org/W1970655212","https://openalex.org/W1975221647","https://openalex.org/W1987355242","https://openalex.org/W2030315716","https://openalex.org/W2039644604","https://openalex.org/W2040001152","https://openalex.org/W2044758663","https://openalex.org/W2049675797","https://openalex.org/W2050127204","https://openalex.org/W2073738917","https://openalex.org/W2076395872","https://openalex.org/W2117853077","https://openalex.org/W2138709157","https://openalex.org/W2156267802","https://openalex.org/W2242296106","https://openalex.org/W2335152673","https://openalex.org/W2507199603","https://openalex.org/W2610934626","https://openalex.org/W2912934387","https://openalex.org/W3125750734","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2378767206","https://openalex.org/W1540871478","https://openalex.org/W328308450","https://openalex.org/W282641168","https://openalex.org/W2376963063","https://openalex.org/W2066396794","https://openalex.org/W2366734808","https://openalex.org/W2002476357","https://openalex.org/W2391444248","https://openalex.org/W2390716080"],"abstract_inverted_index":{"Missing":[0],"data":[1,15,54,68,109,125,138],"is":[2,41],"a":[3,71,127,132],"well-recognized":[4],"problem":[5,50,76],"in":[6,11,56,120],"large":[7],"datasets,":[8],"widely":[9],"discussed":[10],"the":[12,44,48,75,98,104,137],"statistics":[13],"and":[14,32,87,129],"analysis":[16],"literature.":[17],"Many":[18],"programming":[19],"environments":[20],"provide":[21],"explicit":[22],"codes":[23],"for":[24],"missing":[25,53,80,91,108,124],"data,":[26,81,92],"but":[27],"these":[28,101],"are":[29,33,64],"not":[30,34],"standardized":[31],"always":[35],"used.":[36],"This":[37],"lack":[38],"of":[39,43,47,51,74,77,89,100,106,136],"standardization":[40],"one":[42],"leading":[45],"causes":[46],"subtle":[49],"disguised":[52,90,107,123],",":[55],"which":[57],"unknown,":[58],"inapplicable,":[59],"or":[60],"otherwise":[61],"nonspecified":[62],"responses":[63],"encoded":[65],"as":[66,126],"valid":[67],"values.":[69],"Following":[70],"brief":[72],"overview":[73],"explicitly":[78],"coded":[79],"this":[82],"paper":[83],"discusses":[84],"sources,":[85],"consequences,":[86],"detection":[88,118],"including":[93],"two":[94],"real-world":[95],"examples.":[96],"As":[97],"first":[99],"examples":[102],"illustrates,":[103],"consequences":[105],"can":[110],"be":[111],"quite":[112],"serious.":[113],"The":[114],"key":[115],"to":[116,139],"its":[117,141],"lies":[119],"first,":[121],"recognizing":[122],"possibility":[128],"second,":[130],"finding":[131],"sufficiently":[133],"informative":[134],"view":[135],"reveal":[140],"presence.":[142]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":8}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}