{"id":"https://openalex.org/W7207523469","doi":"https://doi.org/10.48550/arxiv.2609.01656","title":"A normal-inverse-Wishart (NIW) Bayesian synthesizer for multivariate normal data with application to polygenic risk scores","display_name":"A normal-inverse-Wishart (NIW) Bayesian synthesizer for multivariate normal data with application to polygenic risk scores","publication_year":2026,"publication_date":"2026-08-31","ids":{"openalex":"https://openalex.org/W7207523469","doi":"https://doi.org/10.48550/arxiv.2609.01656"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.01656","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.01656","pdf_url":"https://arxiv.org/pdf/2609.01656","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":"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/2609.01656","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007239726","display_name":"Rasmus Rask Kragh J\u00f8rgensen","orcid":"https://orcid.org/0009-0000-7249-2196","observed_orcids":["https://orcid.org/0009-0000-7249-2196"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"J\u00f8rgensen, Rasmus Rask Kragh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035278938","display_name":"Anne Krogh N\u00f8hr","orcid":"https://orcid.org/0000-0002-4216-6354","observed_orcids":["https://orcid.org/0000-0002-4216-6354"]},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"N\u00f8hr, Anne Krogh","raw_affiliation_strings":["Center for Clinical Data Science , Aalborg University , Aalborg , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Clinical Data Science , Aalborg University , Aalborg , Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128201814","display_name":"Jan Reiter S\u00f8rensen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"S\u00f8rensen, Jan Reiter","raw_affiliation_strings":["Center for Clinical Data Science , Aalborg University , Aalborg , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Clinical Data Science , Aalborg University , Aalborg , Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077603718","display_name":"Martin B\u00f8gsted","orcid":"https://orcid.org/0000-0001-9192-1814","observed_orcids":["https://orcid.org/0000-0001-9192-1814"]},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"B\u00f8gsted, Martin","raw_affiliation_strings":["Center for Clinical Data Science , Aalborg University , Aalborg , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Clinical Data Science , Aalborg University , Aalborg , Denmark","institution_ids":["https://openalex.org/I891191580"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125540001","display_name":"Heidi S\u00f8gaard Christensen","orcid":"https://orcid.org/0000-0002-2692-168X","observed_orcids":["https://orcid.org/0000-0002-2692-168X"]},"institutions":[{"id":"https://openalex.org/I891191580","display_name":"Aalborg University","ror":"https://ror.org/04m5j1k67","country_code":"DK","type":"education","lineage":["https://openalex.org/I891191580"]}],"countries":["DK"],"is_corresponding":false,"raw_author_name":"Christensen, Heidi S\u00f8gaard","raw_affiliation_strings":["Center for Clinical Data Science , Aalborg University , Aalborg , Denmark"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Clinical Data Science , Aalborg University , Aalborg , Denmark","institution_ids":["https://openalex.org/I891191580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.9990000128746033,"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":0.9990000128746033,"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":0.00019999999494757503,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","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/synthetic-data-generation","display_name":"synthetic data generation","score":0.75},{"id":"https://openalex.org/keywords/multivariate-normal-data","display_name":"multivariate normal data","score":0.8709999918937683},{"id":"https://openalex.org/keywords/privacy-preserving-data-publishing","display_name":"privacy-preserving data publishing","score":0.5839999914169312},{"id":"https://openalex.org/keywords/posterior-predictive-distribution","display_name":"posterior predictive distribution","score":0.7379999756813049},{"id":"https://openalex.org/keywords/polygenic-risk-score","display_name":"polygenic risk score","score":0.8180000185966492},{"id":"https://openalex.org/keywords/conjugate-priors","display_name":"conjugate priors","score":0.6869999766349792},{"id":"https://openalex.org/keywords/feature-dimensionality","display_name":"feature dimensionality","score":0.6399999856948853},{"id":"https://openalex.org/keywords/synthetic-data-privacy","display_name":"synthetic data privacy","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.6567000150680542},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6523000001907349},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5684000253677368},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5648999810218811},{"id":"https://openalex.org/C161584116","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate statistics","level":2,"score":0.5415999889373779},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4645000100135803},{"id":"https://openalex.org/C26004113","wikidata":"https://www.wikidata.org/wiki/Q3711784","display_name":"Conjugate prior","level":4,"score":0.4235999882221222},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.40209999680519104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4018999934196472},{"id":"https://openalex.org/C177384507","wikidata":"https://www.wikidata.org/wiki/Q1149000","display_name":"Multivariate normal distribution","level":3,"score":0.39980000257492065},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.39899998903274536},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.36329999566078186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35910001397132874},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.35679998993873596},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3450999855995178},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33970001339912415},{"id":"https://openalex.org/C191413810","wikidata":"https://www.wikidata.org/wiki/Q17100952","display_name":"Bayesian hierarchical modeling","level":4,"score":0.3361999988555908},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3285999894142151},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.29339998960494995},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C38180746","wikidata":"https://www.wikidata.org/wiki/Q1952580","display_name":"Multivariate analysis","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.2551000118255615}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.01656","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.01656","pdf_url":"https://arxiv.org/pdf/2609.01656","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.01656","doi":"https://doi.org/10.48550/arxiv.2609.01656","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.01656","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.01656","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.01656","pdf_url":"https://arxiv.org/pdf/2609.01656","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322436","display_name":"Novo Nordisk","ror":"https://ror.org/0435rc536"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7207523469.pdf","grobid_xml":"https://content.openalex.org/works/W7207523469.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3136928382","https://openalex.org/W2963668919","https://openalex.org/W2912809136","https://openalex.org/W2892957215","https://openalex.org/W6894117824","https://openalex.org/W3199774140","https://openalex.org/W28725724","https://openalex.org/W3012064685","https://openalex.org/W149976140","https://openalex.org/W3186109309"],"abstract_inverted_index":{"Bayesian":[0,55],"synthesis,":[1],"which":[2],"generates":[3],"synthetic":[4,45,104,137,146,160,170],"data":[5,60,93,105,171],"by":[6,29],"sampling":[7],"from":[8],"the":[9,32,37,41,68,118,121,127,130,134,142,153,169,179],"posterior":[10],"predictive":[11],"distribution,":[12],"is":[13,27],"a":[14,52,63,163],"popular":[15],"approach":[16],"for":[17,57,67],"privatizing":[18],"sensitive":[19],"personal":[20],"data.":[21,181],"However,":[22],"how":[23],"attribute":[24],"disclosure":[25,114],"risk":[26,115,165],"affected":[28],"feature":[30,131],"dimensionality,":[31],"number":[33],"of":[34,43,84,103,120,129,136,144,162,178],"individuals":[35],"in":[36],"original":[38,122,180],"dataset,":[39,123,167],"and":[40,71,80,94,133],"amount":[42,135],"released":[44],"information":[46,138],"remains":[47],"poorly":[48],"understood.":[49],"We":[50,97],"propose":[51],"mathematically":[53],"tractable":[54],"synthesizer":[56,155],"multivariate":[58],"normal":[59],"based":[61],"on":[62],"conjugate":[64,75],"normal-inverse-Wishart":[65],"prior":[66],"mean":[69],"vector":[70],"covariance":[72],"matrix.":[73],"The":[74],"structure":[76],"yields":[77],"closed-form":[78],"posteriors":[79],"enables":[81],"direct":[82],"investigation":[83],"an":[85],"adversary's":[86],"ability":[87],"to":[88,158,176],"infer":[89],"records":[90],"under":[91],"different":[92],"release":[95,143],"settings.":[96],"then":[98],"demonstrate":[99],"several":[100,108],"intuitive":[101],"properties":[102,174],"generation":[106],"through":[107,141],"simulations.":[109],"Specifically,":[110],"we":[111],"show":[112],"that":[113],"decreases":[116],"with":[117,126,168],"size":[119],"but":[124],"increases":[125],"dimensionality":[128],"space":[132],"released,":[139],"whether":[140],"larger":[145],"datasets":[147],"or":[148],"multiple":[149],"generator":[150],"realizations.":[151],"Finally,":[152],"proposed":[154],"was":[156],"used":[157],"generate":[159],"versions":[161],"polygenic":[164],"score":[166],"exhibiting":[172],"distributional":[173],"comparable":[175],"those":[177]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-09-04T00:00:00"}