{"id":"https://openalex.org/W4402391002","doi":"https://doi.org/10.23889/ijpds.v9i5.2660","title":"Automating thresholds in probabilistic linkage","display_name":"Automating thresholds in probabilistic linkage","publication_year":2024,"publication_date":"2024-09-10","ids":{"openalex":"https://openalex.org/W4402391002","doi":"https://doi.org/10.23889/ijpds.v9i5.2660"},"language":"en","primary_location":{"id":"doi:10.23889/ijpds.v9i5.2660","doi":"https://doi.org/10.23889/ijpds.v9i5.2660","is_oa":true,"landing_page_url":"http://dx.doi.org/10.23889/ijpds.v9i5.2660","pdf_url":"https://ijpds.org/article/download/2660/5549","source":{"id":"https://openalex.org/S2764528117","display_name":"International Journal for Population Data Science","issn_l":"2399-4908","issn":["2399-4908"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","ki-jl-1","medline","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310311758","host_organization_name":"Swansea University","host_organization_lineage":["https://openalex.org/P4310311758"],"host_organization_lineage_names":["Swansea University"],"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 Population Data Science","raw_type":"journal-article"},"volume":null,"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ijpds.org/article/download/2660/5549","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081719452","display_name":"Zoe White","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1327095140","display_name":"Office for National Statistics","ror":"https://ror.org/021fhft25","country_code":"GB","type":"government","lineage":["https://openalex.org/I1327095140"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zoe White","raw_affiliation_strings":["Office for National Statistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Office for National Statistics","institution_ids":["https://openalex.org/I1327095140"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043126608","display_name":"Josie Plachta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1327095140","display_name":"Office for National Statistics","ror":"https://ror.org/021fhft25","country_code":"GB","type":"government","lineage":["https://openalex.org/I1327095140"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Josie Plachta","raw_affiliation_strings":["Office for National Statistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Office for National Statistics","institution_ids":["https://openalex.org/I1327095140"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038357111","display_name":"Rachel Shipsey","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1327095140","display_name":"Office for National Statistics","ror":"https://ror.org/021fhft25","country_code":"GB","type":"government","lineage":["https://openalex.org/I1327095140"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rachel Shipsey","raw_affiliation_strings":["Office for National Statistics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Office for National Statistics","institution_ids":["https://openalex.org/I1327095140"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1327095140"],"apc_list":{"value":1425,"currency":"GBP","value_usd":1747},"apc_paid":{"value":1425,"currency":"GBP","value_usd":1747},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.17341854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":"5","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":1.0,"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":1.0,"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/T11539","display_name":"Survey Methodology and Nonresponse","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"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/T13546","display_name":"Census and Population Estimation","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/probabilistic-record-linkage","display_name":"probabilistic record linkage","score":0.8460000157356262},{"id":"https://openalex.org/keywords/administrative-data","display_name":"administrative data","score":0.4300000071525574},{"id":"https://openalex.org/keywords/2021-census","display_name":"2021 Census","score":0.7580000162124634},{"id":"https://openalex.org/keywords/data-linkage","display_name":"data linkage","score":0.3019999861717224}],"concepts":[{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.651608407497406},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6168740391731262},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5272471308708191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2500086724758148},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.13915225863456726},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1295706331729889},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07075288891792297}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.23889/ijpds.v9i5.2660","doi":"https://doi.org/10.23889/ijpds.v9i5.2660","is_oa":true,"landing_page_url":"http://dx.doi.org/10.23889/ijpds.v9i5.2660","pdf_url":"https://ijpds.org/article/download/2660/5549","source":{"id":"https://openalex.org/S2764528117","display_name":"International Journal for Population Data Science","issn_l":"2399-4908","issn":["2399-4908"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","ki-jl-1","medline","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310311758","host_organization_name":"Swansea University","host_organization_lineage":["https://openalex.org/P4310311758"],"host_organization_lineage_names":["Swansea University"],"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 Population Data Science","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:d483c7442be243bfb2d65e1e6cefad52","doi":null,"is_oa":true,"landing_page_url":"https://doaj.org/article/d483c7442be243bfb2d65e1e6cefad52","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"International Journal of Population Data Science, Vol 9, Iss 5 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.23889/ijpds.v9i5.2660","doi":"https://doi.org/10.23889/ijpds.v9i5.2660","is_oa":true,"landing_page_url":"http://dx.doi.org/10.23889/ijpds.v9i5.2660","pdf_url":"https://ijpds.org/article/download/2660/5549","source":{"id":"https://openalex.org/S2764528117","display_name":"International Journal for Population Data Science","issn_l":"2399-4908","issn":["2399-4908"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","doaj","dongbi-c","jufo-1","ki-jl-1","medline","norway-1","poland-20","russia-white-list-1"],"host_organization":"https://openalex.org/P4310311758","host_organization_name":"Swansea University","host_organization_lineage":["https://openalex.org/P4310311758"],"host_organization_lineage_names":["Swansea University"],"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 Population Data Science","raw_type":"journal-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402391002.pdf","grobid_xml":"https://content.openalex.org/works/W4402391002.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4282976635","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2784199898"],"abstract_inverted_index":{"ObjectiveThe":[0],"Office":[1],"for":[2],"National":[3],"Statistics":[4],"aim":[5,38],"is":[6,27,35,45,76,188,209],"to":[7,32,60,84],"create":[8],"a":[9,12,36,46,55,86,93,154,164,168,232],"platform":[10],"containing":[11],"variety":[13,233],"of":[14,39,112,125,140,156,213,234],"datasets":[15,26,230],"interlinked":[16],"via":[17],"data":[18,215,219],"spines.":[19],"The":[20,185,198],"resource":[21],"burden":[22],"linking":[23],"this":[24,226],"many":[25],"high,":[28],"and":[29,133,147,167,177,204,237],"so":[30],"research":[31,68],"maximise":[33],"automation":[34],"key":[37],"the":[40,79,110,114,119,123,138,180,193,218],"platform\u2019s":[41],"methodology.":[42],"Probabilistic":[43],"linkage":[44,48],"standard":[47,101,142,195],"technique":[49],"that":[50,159],"utilises":[51],"clerical":[52],"resolution":[53],"\u2013":[54,59],"very":[56],"costly":[57],"process":[58],"find":[61,118],"acceptance":[62],"threshold":[63,71,88,95,157],"parameters.":[64],"Here,":[65],"we":[66],"present":[67],"into":[69],"automating":[70],"assignment.":[72],"Every":[73],"admin":[74],"dataset":[75,103,190],"different,":[77],"causing":[78],"probabilistically":[80],"matched":[81],"pairs":[82],"scores":[83],"change,":[85],"set":[87],"cannot":[89],"be":[90,97],"used.":[91],"Instead,":[92],"data-informed":[94],"must":[96],"set.":[98],"ApproachA":[99],"gold":[100,141,194],"linked":[102,105,191,196],"was":[104],"through":[106],"Fellegi-Sunter,":[107],"stopping":[108],"at":[109,127,137],"point":[111],"finding":[113],"probabilistic":[115,149],"threshold.":[116,170],"To":[117],"threshold,":[120,166],"graphs":[121,176],"plotting":[122],"number":[124],"records":[126],"each":[128],"rounded":[129],"score":[130],"were":[131],"created":[132],"reviewed,":[134],"specifically":[135],"looking":[136],"spread":[139],"links,":[143,145],"deterministic":[144],"unique":[146],"non-unique":[148],"links.":[150],"This":[151,171],"review":[152],"suggested":[153],"method":[155,227],"assignment":[158],"provides":[160],"multiple":[161],"quality":[162,203],"levels:":[163],"high-precision":[165],"high-recall":[169],"presentation":[172],"will":[173],"showcase":[174],"these":[175],"explain":[178],"how":[179],"two":[181],"thresholds":[182],"are":[183,224],"calculated.":[184],"2021":[186,199],"Census":[187,200],"one":[189],"within":[192],"dataset.":[197],"has":[201],"high":[202],"relatively":[205],"clean":[206],"data,":[207],"but":[208],"likely":[210],"not":[211],"representative":[212],"administrative":[214],"needed":[216],"in":[217],"platform.":[220],"Therefore,":[221],"next":[222],"steps":[223],"testing":[225],"on":[228],"other":[229],"with":[231],"quality,":[235],"characteristics,":[236],"types.":[238]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2025-10-10T00:00:00"}