{"id":"https://openalex.org/W7128686130","doi":"https://doi.org/10.1016/j.softx.2026.102541","title":"SynMicrodata: An R package for generating synthetic microdata via a nonparametric Bayesian approach","display_name":"SynMicrodata: An R package for generating synthetic microdata via a nonparametric Bayesian approach","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128686130","doi":"https://doi.org/10.1016/j.softx.2026.102541"},"language":"en","primary_location":{"id":"doi:10.1016/j.softx.2026.102541","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2026.102541","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.softx.2026.102541","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100371933","display_name":"Juhee Lee","orcid":"https://orcid.org/0000-0003-2307-6107"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juhee Lee","raw_affiliation_strings":["Department of Statistics, Kyungpook National University, Daegu 41566, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Kyungpook National University, Daegu 41566, South Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080201608","display_name":"Hang J. Kim","orcid":"https://orcid.org/0000-0003-2029-2293"},"institutions":[{"id":"https://openalex.org/I63135867","display_name":"University of Cincinnati","ror":"https://ror.org/01e3m7079","country_code":"US","type":"education","lineage":["https://openalex.org/I63135867"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang J. Kim","raw_affiliation_strings":["Division of Statistics and Data Science, Department of Mathematical Sciences, University of Cincinnati, Cincinnati, OH 45221, USA"],"affiliations":[{"raw_affiliation_string":"Division of Statistics and Data Science, Department of Mathematical Sciences, University of Cincinnati, Cincinnati, OH 45221, USA","institution_ids":["https://openalex.org/I63135867"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033884286","display_name":"Jared S. Murray","orcid":"https://orcid.org/0000-0003-3328-9413"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jared S. Murray","raw_affiliation_strings":["Department of Statistics and Data Science, University of Texas at Austin, Austin, TX 78712, USA"],"affiliations":[{"raw_affiliation_string":"Department of Statistics and Data Science, University of Texas at Austin, Austin, TX 78712, USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":null,"display_name":"Young Min Kim","orcid":"https://orcid.org/0000-0001-6295-1758"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Young Min Kim","raw_affiliation_strings":["Department of Statistics, Kyungpook National University, Daegu 41566, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Statistics, Kyungpook National University, Daegu 41566, South Korea","institution_ids":["https://openalex.org/I31419693"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31419693"],"apc_list":{"value":500,"currency":"USD","value_usd":500},"apc_paid":{"value":500,"currency":"USD","value_usd":500},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.35294786,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"34","issue":null,"first_page":"102541","last_page":"102541"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.7257000207901001,"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":0.7257000207901001,"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/T10243","display_name":"Statistical Methods and Bayesian Inference","score":0.04360000044107437,"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":0.031099999323487282,"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/categorical-variable","display_name":"Categorical variable","score":0.6484000086784363},{"id":"https://openalex.org/keywords/dirichlet-process","display_name":"Dirichlet process","score":0.6473000049591064},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5874999761581421},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.5435000061988831},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5162000060081482},{"id":"https://openalex.org/keywords/nonparametric-statistics","display_name":"Nonparametric statistics","score":0.5109999775886536},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.49639999866485596},{"id":"https://openalex.org/keywords/microdata","display_name":"Microdata (statistics)","score":0.4828000068664551},{"id":"https://openalex.org/keywords/r-package","display_name":"R package","score":0.45820000767707825},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.41190001368522644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7864999771118164},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.6484000086784363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6478999853134155},{"id":"https://openalex.org/C2781280628","wikidata":"https://www.wikidata.org/wiki/Q5280766","display_name":"Dirichlet process","level":3,"score":0.6473000049591064},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5874999761581421},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.5109999775886536},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.49639999866485596},{"id":"https://openalex.org/C2778355071","wikidata":"https://www.wikidata.org/wiki/Q1933849","display_name":"Microdata (statistics)","level":4,"score":0.4828000068664551},{"id":"https://openalex.org/C2984074130","wikidata":"https://www.wikidata.org/wiki/Q73539779","display_name":"R package","level":2,"score":0.45820000767707825},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.3977999985218048},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.36890000104904175},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3465000092983246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30820000171661377},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C141318989","wikidata":"https://www.wikidata.org/wiki/Q5753066","display_name":"Hierarchical Dirichlet process","level":4,"score":0.28049999475479126},{"id":"https://openalex.org/C17618745","wikidata":"https://www.wikidata.org/wiki/Q207509","display_name":"Copula (linguistics)","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C158424031","wikidata":"https://www.wikidata.org/wiki/Q1191905","display_name":"Gibbs sampling","level":3,"score":0.2669000029563904},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.2619999945163727},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.2572999894618988},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.2533000111579895},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1016/j.softx.2026.102541","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2026.102541","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:7c879108a6824117a7782ad0baf07719","is_oa":true,"landing_page_url":"https://doaj.org/article/7c879108a6824117a7782ad0baf07719","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"SoftwareX, Vol 34, Iss , Pp 102541- (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1016/j.softx.2026.102541","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.softx.2026.102541","pdf_url":null,"source":{"id":"https://openalex.org/S2506067282","display_name":"SoftwareX","issn_l":"2352-7110","issn":["2352-7110"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SoftwareX","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2095053294","display_name":null,"funder_award_id":"2022-0-00937","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G3151700349","display_name":null,"funder_award_id":"2025S1A5C3A020118","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4492132176","display_name":null,"funder_award_id":"DMS-2413823","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W92430206","https://openalex.org/W2544063074","https://openalex.org/W2593512180","https://openalex.org/W2742634874","https://openalex.org/W4396675632"],"related_works":[],"abstract_inverted_index":{"The":[0,78],"synMicrodata":[1,68,99],"package":[2,32,79],"provides":[3],"a":[4,23,53,101],"flexible":[5],"and":[6,18,61,73,94],"fully":[7],"joint":[8],"modeling":[9],"approach":[10],"for":[11,56,104],"generating":[12],"synthetic":[13,50,87],"microdata":[14],"containing":[15],"both":[16,92],"continuous":[17],"categorical":[19],"variables.":[20],"Built":[21],"on":[22,115],"nonparametric":[24],"Bayesian":[25],"model":[26,59],"with":[27],"Dirichlet":[28],"process":[29],"priors,":[30],"the":[31,42],"captures":[33],"complex":[34],"multivariate":[35],"dependencies":[36],"in":[37,41,107],"original":[38],"datasets,":[39],"even":[40],"presence":[43],"of":[44],"missing":[45,95],"values.":[46],"It":[47],"generates":[48],"multiple":[49],"datasets":[51],"through":[52,118],"modular":[54],"workflow":[55],"data":[57,62,88,96,108,117],"preprocessing,":[58],"fitting,":[60],"synthesis.":[63],"Simulation":[64],"studies":[65],"demonstrate":[66],"that":[67],"preserves":[69],"key":[70],"marginal":[71],"statistics":[72],"achieves":[74],"nominal":[75],"coverage":[76],"rates.":[77],"produces":[80],"competitive":[81],"results":[82],"when":[83],"compared":[84],"to":[85],"existing":[86],"generation":[89],"methods,":[90],"under":[91],"complete":[93],"scenarios.":[97],"Consequently,":[98],"is":[100],"valuable":[102],"tool":[103],"ensuring":[105],"privacy":[106],"dissemination":[109],"while":[110],"enabling":[111],"valid":[112],"statistical":[113],"inference":[114],"confidential":[116],"simulation.":[119]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-02-13T00:00:00"}