{"id":"https://openalex.org/W3203973319","doi":"https://doi.org/10.48550/arxiv.2109.12717","title":"Assessing, visualizing and improving the utility of synthetic data","display_name":"Assessing, visualizing and improving the utility of synthetic data","publication_year":2021,"publication_date":"2021-09-26","ids":{"openalex":"https://openalex.org/W3203973319","doi":"https://doi.org/10.48550/arxiv.2109.12717","mag":"3203973319"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2109.12717","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.12717","pdf_url":"https://arxiv.org/pdf/2109.12717","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/2109.12717","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034206730","display_name":"GILLIAN M. RAAB","orcid":"https://orcid.org/0000-0002-2708-4326","observed_orcids":["https://orcid.org/0000-0002-2708-4326"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Raab, Gillian M","raw_affiliation_strings":["University of Edinburgh University of Edinburgh University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh University of Edinburgh University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056203631","display_name":"Beata Nowok","orcid":"https://orcid.org/0000-0002-0713-2271","observed_orcids":["https://orcid.org/0000-0002-0713-2271"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nowok, Beata","raw_affiliation_strings":["University of Edinburgh University of Edinburgh University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh University of Edinburgh University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056544632","display_name":"Chris J L Dibben","orcid":"https://orcid.org/0000-0003-1769-3774","observed_orcids":["https://orcid.org/0000-0003-1769-3774"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dibben, Chris","raw_affiliation_strings":["University of Edinburgh University of Edinburgh University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh University of Edinburgh University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I98677209"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.788100004196167,"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"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.788100004196167,"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/T14509","display_name":"demographic modeling and climate adaptation","score":0.18479999899864197,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.00430000014603138,"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/synthetic-data","display_name":"synthetic data","score":0.9739999771118164},{"id":"https://openalex.org/keywords/utility-measures","display_name":"utility measures","score":0.5879999995231628},{"id":"https://openalex.org/keywords/propensity-score-models","display_name":"propensity score models","score":0.8529999852180481},{"id":"https://openalex.org/keywords/microdata-confidentiality","display_name":"microdata confidentiality","score":0.5759999752044678},{"id":"https://openalex.org/keywords/data-dissemination","display_name":"data dissemination","score":0.39100000262260437}],"concepts":[{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.7747230529785156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6562358140945435},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4736928939819336},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2944374084472656}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2109.12717","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.12717","pdf_url":"https://arxiv.org/pdf/2109.12717","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":"mag:3203973319","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2109.12717.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2109.12717","doi":"https://doi.org/10.48550/arxiv.2109.12717","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2109.12717","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2109.12717","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2109.12717","pdf_url":"https://arxiv.org/pdf/2109.12717","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1530664329","https://openalex.org/W2030652107","https://openalex.org/W2081985429","https://openalex.org/W2544063074","https://openalex.org/W2593512180","https://openalex.org/W2772564103","https://openalex.org/W2963679759","https://openalex.org/W3110683067","https://openalex.org/W3113284709","https://openalex.org/W3139365575"],"related_works":["https://openalex.org/W1779546711","https://openalex.org/W2187276023","https://openalex.org/W3202291205","https://openalex.org/W2953387381","https://openalex.org/W2499319642","https://openalex.org/W2398834799","https://openalex.org/W3124433989","https://openalex.org/W2470089128","https://openalex.org/W2760583512","https://openalex.org/W3040840557","https://openalex.org/W1513998414","https://openalex.org/W2943972974","https://openalex.org/W2276544228","https://openalex.org/W3000458627","https://openalex.org/W2243220491","https://openalex.org/W1528046055","https://openalex.org/W2322360800","https://openalex.org/W1532352832","https://openalex.org/W2397534153","https://openalex.org/W2502955103"],"abstract_inverted_index":{"The":[0,29,88,114,168],"synthpop":[1,142],"package":[2,143],"for":[3,177],"R":[4,214],"https://www.synthpop.org.uk":[5],"provides":[6],"tools":[7],"to":[8,12,34,56,111,117,147,156,164,174,198],"allow":[9,157],"data":[10,42,163,179,204,215,220],"custodians":[11],"create":[13],"synthetic":[14,47,67,162,178],"versions":[15],"of":[16,51,65,129,181,219],"confidential":[17],"microdata":[18],"that":[19,36,71,144],"can":[20,31,80,194],"be":[21,32,81,91,112,175,196],"distributed":[22],"with":[23,206],"fewer":[24],"restrictions":[25],"than":[26,126],"the":[27,40,46,63,66,101,119,127,141,149,158,161,186,207,211],"original.":[28],"synthesis":[30],"customized":[33],"ensure":[35],"relationships":[37],"evident":[38],"in":[39,45,140],"real":[41],"are":[43,104,109,135,213],"reproduced":[44],"data.":[48,68],"A":[49],"number":[50],"measures":[52,89,102,132],"have":[53],"been":[54],"proposed":[55],"assess":[57],"this":[58],"aspect,":[59],"commonly":[60],"known":[61],"as":[62],"utility":[64,138,169],"We":[69],"show":[70],"all":[72],"these":[73],"measures,":[74],"including":[75],"those":[76],"calculated":[77],"from":[78,83],"tabulations,":[79],"derived":[82],"a":[84],"propensity":[85,120],"score":[86,121],"model.":[87],"will":[90],"reviewed":[92],"and":[93,95,107,133,151],"compared,":[94],"relations":[96],"between":[97],"them":[98],"illustrated.":[99],"All":[100],"compared":[103],"highly":[105],"correlated":[106],"some":[108],"shown":[110],"identical.":[113],"method":[115],"used":[116,176,197],"define":[118],"model":[122],"is":[123],"more":[124,202],"important":[125],"choice":[128],"measure.":[130],"These":[131],"methods":[134,146],"incorporated":[136],"into":[137],"modules":[139],"include":[145],"visualize":[148],"results":[150],"thus":[152],"provide":[153],"immediate":[154],"feedback":[155],"person":[159],"creating":[160],"improve":[165],"its":[166],"quality.":[167],"functions":[170],"were":[171],"originally":[172],"designed":[173],"objects":[180],"class":[182],"\\code{synds},":[183],"created":[184],"by":[185],"\\pkg{synthpop}":[187],"function":[188],"syn()":[189],"or":[190,201,217],"syn.strata(),":[191],"but":[192],"they":[193],"now":[195],"compare":[199],"one":[200],"synthesised":[203],"sets":[205],"original":[208],"records,":[209],"where":[210],"records":[212],"frames":[216],"lists":[218],"frames.":[221]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-10T00:00:00"}