{"id":"https://openalex.org/W2051055051","doi":"https://doi.org/10.1145/1515693.1515695","title":"A Bayesian Approach for Estimating and Replacing Missing Categorical Data","display_name":"A Bayesian Approach for Estimating and Replacing Missing Categorical Data","publication_year":2009,"publication_date":"2009-06-01","ids":{"openalex":"https://openalex.org/W2051055051","doi":"https://doi.org/10.1145/1515693.1515695","mag":"2051055051"},"language":"en","primary_location":{"id":"doi:10.1145/1515693.1515695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1515693.1515695","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"Journal of Data and Information Quality","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/A5101691489","display_name":"Xiao\u2010Bai Li","orcid":null},"institutions":[{"id":"https://openalex.org/I133738476","display_name":"University of Massachusetts Lowell","ror":"https://ror.org/03hamhx47","country_code":"US","type":"education","lineage":["https://openalex.org/I133738476"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xiao-Bai Li","raw_affiliation_strings":["University of Massachusetts Lowell","University Of Massachusetts-Lowell"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Lowell","institution_ids":["https://openalex.org/I133738476"]},{"raw_affiliation_string":"University Of Massachusetts-Lowell","institution_ids":["https://openalex.org/I133738476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101691489"],"corresponding_institution_ids":["https://openalex.org/I133738476"],"apc_list":null,"apc_paid":null,"fwci":0.8199,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.77084827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"1","issue":"1","first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9959999918937683,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9843999743461609,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/categorical-variable","display_name":"Categorical variable","score":0.8556721210479736},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.8325322866439819},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6711961627006531},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.6108393669128418},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5868132710456848},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5775789022445679},{"id":"https://openalex.org/keywords/bayes-theorem","display_name":"Bayes' theorem","score":0.49267488718032837},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.44872891902923584},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.416820764541626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3262297213077545},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2552390694618225},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24559494853019714}],"concepts":[{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.8556721210479736},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.8325322866439819},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6711961627006531},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.6108393669128418},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5868132710456848},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5775789022445679},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.49267488718032837},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.44872891902923584},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.416820764541626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3262297213077545},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2552390694618225},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24559494853019714}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1515693.1515695","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1515693.1515695","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"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":"Journal of Data and Information Quality","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W128984794","https://openalex.org/W655912526","https://openalex.org/W1530010412","https://openalex.org/W1534707631","https://openalex.org/W1570448133","https://openalex.org/W1585032225","https://openalex.org/W1594031697","https://openalex.org/W1700821812","https://openalex.org/W2008524883","https://openalex.org/W2044478943","https://openalex.org/W2071762633","https://openalex.org/W2072191579","https://openalex.org/W2078937669","https://openalex.org/W2114760008","https://openalex.org/W2117366235","https://openalex.org/W2122789628","https://openalex.org/W2125055259","https://openalex.org/W2127856300","https://openalex.org/W2136000097","https://openalex.org/W2140481308","https://openalex.org/W2154744054","https://openalex.org/W2161067131","https://openalex.org/W2479363696","https://openalex.org/W2799061466","https://openalex.org/W2966207845","https://openalex.org/W2973651390","https://openalex.org/W3085162807","https://openalex.org/W3120740533"],"related_works":["https://openalex.org/W4380150146","https://openalex.org/W3024870410","https://openalex.org/W2519761320","https://openalex.org/W2032094637","https://openalex.org/W2040227828","https://openalex.org/W2060045818","https://openalex.org/W2330406685","https://openalex.org/W2131935101","https://openalex.org/W856257623","https://openalex.org/W2892315154"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,19,25,62],"new":[3],"approach":[4,80],"for":[5,38,90],"estimating":[6],"and":[7,93],"replacing":[8,39],"missing":[9,20,41,49],"categorical":[10],"data.":[11],"With":[12],"this":[13],"approach,":[14],"the":[15,31,40,48,52,55,59,71,78,99,103,106],"posterior":[16,73],"probabilities":[17],"of":[18,77,98,105],"attribute":[21],"value":[22,42,50,53,63],"belonging":[23],"to":[24,70],"certain":[26],"category":[27],"are":[28,43],"estimated":[29,56,72],"using":[30],"simple":[32],"Bayes":[33],"method.":[34],"Two":[35],"alternative":[36],"methods":[37],"proposed:":[44],"The":[45,75,96],"first":[46],"replaces":[47],"with":[51,67],"having":[54],"maximum":[57],"probability;":[58],"second":[60],"uses":[61],"that":[64],"is":[65,81],"selected":[66],"probability":[68],"proportional":[69],"distribution.":[74],"effectiveness":[76,104],"proposed":[79,107],"evaluated":[82],"based":[83],"on":[84],"some":[85],"important":[86],"data":[87,91,94],"quality":[88],"measures":[89],"warehousing":[92],"mining.":[95],"results":[97],"experimental":[100],"study":[101],"demonstrate":[102],"approach.":[108]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}