{"id":"https://openalex.org/W4321453929","doi":"https://doi.org/10.1145/3580487","title":"To Link or Synthesize? An Approach to Data Quality Comparison","display_name":"To Link or Synthesize? An Approach to Data Quality Comparison","publication_year":2023,"publication_date":"2023-02-21","ids":{"openalex":"https://openalex.org/W4321453929","doi":"https://doi.org/10.1145/3580487"},"language":"en","primary_location":{"id":"doi:10.1145/3580487","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580487","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580487","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3580487","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022864582","display_name":"Duncan Smith","orcid":"https://orcid.org/0000-0002-1162-1772"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Duncan Smith","raw_affiliation_strings":["The University of Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The University of Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018732292","display_name":"Mark Elliot","orcid":"https://orcid.org/0000-0002-3142-4493"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mark Elliot","raw_affiliation_strings":["The University of Manchester, United Kingdom"],"affiliations":[{"raw_affiliation_string":"The University of Manchester, United Kingdom","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037354101","display_name":"Joseph W. Sakshaug","orcid":"https://orcid.org/0000-0001-7520-353X"},"institutions":[{"id":"https://openalex.org/I2607685603","display_name":"Institut f\u00fcr Arbeitsmarkt und Berufsforschung","ror":"https://ror.org/02qcqwf93","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2607685603"]},{"id":"https://openalex.org/I8204097","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55","country_code":"DE","type":"education","lineage":["https://openalex.org/I8204097"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Joseph W. Sakshaug","raw_affiliation_strings":["Institute for Employment Research &amp; Ludwig Maximilian University of Munich, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Employment Research &amp; Ludwig Maximilian University of Munich, Germany","institution_ids":["https://openalex.org/I8204097","https://openalex.org/I2607685603"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022864582"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":null,"apc_paid":null,"fwci":1.4974,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8273163,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"15","issue":"2","first_page":"1","last_page":"20"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.996999979019165,"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/T11819","display_name":"Data-Driven Disease Surveillance","score":0.9722999930381775,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8184798955917358},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.7393161654472351},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5953677892684937},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5665966272354126},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5501294732093811},{"id":"https://openalex.org/keywords/linkage","display_name":"Linkage (software)","score":0.4909132122993469},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.4684619605541229},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.32937949895858765},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.3243902921676636},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.14981502294540405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184798955917358},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.7393161654472351},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5953677892684937},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5665966272354126},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5501294732093811},{"id":"https://openalex.org/C31266012","wikidata":"https://www.wikidata.org/wiki/Q6554340","display_name":"Linkage (software)","level":3,"score":0.4909132122993469},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.4684619605541229},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.32937949895858765},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3243902921676636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.14981502294540405},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3580487","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580487","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580487","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/83425ad4-2c9e-4855-9660-db8263efbaf6","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/83425ad4-2c9e-4855-9660-db8263efbaf6","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Smith, D, Elliot, M & Sakshaug, J W 2023, 'To Link or Synthesize? An Approach to Data Quality Comparison', Journal of Data and Information Quality, vol. 15, no. 2, 14. https://doi.org/10.1145/3580487","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1145/3580487","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3580487","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3580487","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2355988775","display_name":"National Centre for Research Methods 2014-2019","funder_award_id":"ES/L008351/1","funder_id":"https://openalex.org/F4320334630","funder_display_name":"Economic and Social Research Council"}],"funders":[{"id":"https://openalex.org/F4320334630","display_name":"Economic and Social Research Council","ror":"https://ror.org/03n0ht308"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4321453929.pdf","grobid_xml":"https://content.openalex.org/works/W4321453929.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W187651740","https://openalex.org/W1491523329","https://openalex.org/W1498374183","https://openalex.org/W1518069667","https://openalex.org/W1525535529","https://openalex.org/W1558603883","https://openalex.org/W1578810938","https://openalex.org/W1594031697","https://openalex.org/W2011590821","https://openalex.org/W2017353792","https://openalex.org/W2034190452","https://openalex.org/W2047464260","https://openalex.org/W2049633694","https://openalex.org/W2073471108","https://openalex.org/W2104926310","https://openalex.org/W2105149552","https://openalex.org/W2108354408","https://openalex.org/W2133470535","https://openalex.org/W2141965543","https://openalex.org/W2142074194","https://openalex.org/W2143668817","https://openalex.org/W2149342630","https://openalex.org/W2159024459","https://openalex.org/W2164744796","https://openalex.org/W2166167139","https://openalex.org/W2222512263","https://openalex.org/W2272596129","https://openalex.org/W2544063074","https://openalex.org/W2577090845","https://openalex.org/W2582743722","https://openalex.org/W2586761039","https://openalex.org/W2593512180","https://openalex.org/W2597746054","https://openalex.org/W2774473742","https://openalex.org/W2803749461","https://openalex.org/W2967880504","https://openalex.org/W3041131115","https://openalex.org/W3089052958","https://openalex.org/W3092364842","https://openalex.org/W4234451204","https://openalex.org/W4239489793","https://openalex.org/W4284958403","https://openalex.org/W4299943454","https://openalex.org/W4312111414","https://openalex.org/W6824196707","https://openalex.org/W6929911312","https://openalex.org/W6948801944"],"related_works":["https://openalex.org/W4282976635","https://openalex.org/W2362702199","https://openalex.org/W2067086158","https://openalex.org/W2350014578","https://openalex.org/W2751469835","https://openalex.org/W1967666613","https://openalex.org/W2060472104","https://openalex.org/W2015084710","https://openalex.org/W54884023","https://openalex.org/W3017044880"],"abstract_inverted_index":{"Linking":[0],"administrative":[1],"data":[2,7,36,39,42,52,58,80,109,112,139],"to":[3,45,62,91,110],"produce":[4],"more":[5],"informative":[6],"for":[8],"subsequent":[9],"analysis":[10],"has":[11],"become":[12],"an":[13,70,130],"increasingly":[14],"common":[15],"practice.":[16],"However,":[17,85],"there":[18],"might":[19,73,120],"be":[20,121,134],"concomitant":[21],"risks":[22,34],"of":[23,77,103,107],"disclosing":[24],"sensitive":[25],"information":[26],"about":[27],"individuals.":[28],"One":[29],"practice":[30],"that":[31,93],"reduces":[32],"these":[33],"is":[35],"synthesis.":[37],"In":[38],"synthesis":[40,88],"the":[41,75,101,105,118,137],"are":[43,53,59,66,89,125],"used":[44],"fit":[46],"a":[47],"model":[48],"from":[49],"which":[50],"synthetic":[51,57],"then":[54,60],"generated.":[55],"The":[56],"released":[61],"end":[63,71,131],"users.":[64],"There":[65],"some":[67],"scenarios":[68],"where":[69,143],"user":[72,132],"have":[74],"option":[76],"using":[78],"linked":[79,108],"or":[81],"accepting":[82],"synthesized":[83,111],"data.":[84],"linkage":[86],"and":[87,113,140],"susceptible":[90],"errors":[92],"could":[94],"limit":[95],"their":[96],"usefulness.":[97],"Here,":[98],"we":[99],"investigate":[100],"problem":[102,119],"comparing":[104],"quality":[106],"demonstrate":[114],"through":[115],"simulations":[116],"how":[117,129],"approached.":[122],"These":[123],"comparisons":[124],"important":[126],"when":[127],"considering":[128],"can":[133],"supplied":[135],"with":[136],"highest-quality":[138],"in":[141],"situations":[142],"one":[144],"must":[145],"consider":[146],"risk/utility":[147],"tradeoffs.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
