{"id":"https://openalex.org/W1715327985","doi":"https://doi.org/10.48550/arxiv.1212.5203","title":"An Experiment with Hierarchical Bayesian Record Linkage","display_name":"An Experiment with Hierarchical Bayesian Record Linkage","publication_year":2012,"publication_date":"2012-12-20","ids":{"openalex":"https://openalex.org/W1715327985","doi":"https://doi.org/10.48550/arxiv.1212.5203","mag":"1715327985"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1212.5203","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1212.5203","pdf_url":"https://arxiv.org/pdf/1212.5203","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1212.5203","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035231652","display_name":"Michael D. Larsen","orcid":"https://orcid.org/0000-0002-6680-2730","observed_orcids":["https://orcid.org/0000-0002-6680-2730"]},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Larsen, Michael D.","raw_affiliation_strings":["george Washington University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"george Washington University","institution_ids":["https://openalex.org/I193531525"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5035231652"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9994999766349792,"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":0.9994999766349792,"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/T13546","display_name":"Census and Population Estimation","score":9.999999747378752e-05,"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":0.0,"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/data-linkage","display_name":"data linkage","score":0.9990000128746033},{"id":"https://openalex.org/keywords/prior-information","display_name":"prior information","score":0.8349999785423279},{"id":"https://openalex.org/keywords/match-scoring","display_name":"match scoring","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.6714410781860352},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6508652567863464},{"id":"https://openalex.org/C191413810","wikidata":"https://www.wikidata.org/wiki/Q17100952","display_name":"Bayesian hierarchical modeling","level":4,"score":0.4701271951198578},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.4363335371017456},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42894574999809265},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.381356805562973},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34986913204193115},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2661139965057373},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.18579044938087463},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15628188848495483},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.10948652029037476},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:1212.5203","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1212.5203","pdf_url":"https://arxiv.org/pdf/1212.5203","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.753.1646","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.753.1646","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://arxiv.org/pdf/1212.5203.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1212.5203","doi":"https://doi.org/10.48550/arxiv.1212.5203","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1212.5203","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1212.5203","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1212.5203","pdf_url":"https://arxiv.org/pdf/1212.5203","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7400000095367432,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1547556487","https://openalex.org/W1579271636","https://openalex.org/W1673955757","https://openalex.org/W1907304379","https://openalex.org/W1975723136","https://openalex.org/W1981519674","https://openalex.org/W2020999234","https://openalex.org/W2034190452","https://openalex.org/W2045656233","https://openalex.org/W2049633694","https://openalex.org/W2049855118","https://openalex.org/W2073471108","https://openalex.org/W2083875149","https://openalex.org/W2093223772","https://openalex.org/W2094414211","https://openalex.org/W2099400440","https://openalex.org/W2128600649","https://openalex.org/W2138309709","https://openalex.org/W2148534890","https://openalex.org/W2913519381","https://openalex.org/W3146174752"],"related_works":["https://openalex.org/W2487032012","https://openalex.org/W2211355040","https://openalex.org/W2808916796","https://openalex.org/W3088855600","https://openalex.org/W2176311362","https://openalex.org/W3012491082","https://openalex.org/W3211905090","https://openalex.org/W1936317645","https://openalex.org/W2178148352","https://openalex.org/W786367546"],"abstract_inverted_index":{"In":[0],"record":[1],"linkage":[2],"(RL),":[3],"or":[4,21],"exact":[5],"file":[6,128],"matching,":[7],"the":[8,13,33,94,105,140,151],"goal":[9],"is":[10,25,47,60,71],"to":[11,92,102],"identify":[12],"links":[14],"between":[15],"entities":[16],"with":[17,73],"information":[18,70,91,108,144],"on":[19,62,83],"two":[20],"more":[22],"files.":[23],"RL":[24,46],"an":[26,76],"important":[27],"activity":[28],"in":[29,150],"areas":[30],"including":[31],"counting":[32],"population,":[34],"enhancing":[35],"survey":[36],"frames":[37],"and":[38,40,43,68,89,145],"data,":[39],"conducting":[41],"epidemiological":[42],"follow-up":[44],"studies.":[45],"challenging":[48],"when":[49],"files":[50,64],"are":[51],"very":[52],"large,":[53],"no":[54],"accurate":[55],"personal":[56],"identification":[57],"(ID)":[58],"number":[59,79],"present":[61],"all":[63,66],"for":[65,109,114],"units,":[67],"some":[69],"recorded":[72],"error.":[74],"Without":[75],"unique":[77],"ID":[78],"one":[80],"must":[81],"rely":[82],"comparisons":[84,119],"of":[85,107,123,142,153],"names,":[86],"addresses,":[87],"dates,":[88],"other":[90],"find":[93],"links.":[95],"Latent":[96],"class":[97,148],"models":[98,116,149],"can":[99,133],"be":[100],"used":[101],"automatically":[103],"score":[104],"value":[106],"determining":[110],"match":[111],"status.":[112],"Data":[113,131],"fitting":[115],"come":[117],"from":[118],"made":[120],"within":[121],"groups":[122],"units":[124],"that":[125],"pass":[126],"initial":[127],"blocking":[129],"requirements.":[130],"distributions":[132],"vary":[134],"across":[135],"blocks.":[136],"This":[137],"article":[138],"examines":[139],"use":[141],"prior":[143],"hierarchical":[146],"latent":[147],"context":[152],"RL.":[154]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-09-22T06:50:58.402377","created_date":"2025-10-10T00:00:00"}