{"id":"https://openalex.org/W7224776691","doi":"https://doi.org/10.48550/arxiv.2610.39274","title":"TwinPoSI: Statistical Twins for Powerful Post-Selection Inference on Population-Based Regression Coefficients","display_name":"TwinPoSI: Statistical Twins for Powerful Post-Selection Inference on Population-Based Regression Coefficients","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224776691","doi":"https://doi.org/10.48550/arxiv.2610.39274"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39274","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39274","pdf_url":"https://arxiv.org/pdf/2610.39274","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39274","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160173208","display_name":"Changhu Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Changhu","raw_affiliation_strings":["Biostatistics Program , Public Health Science Division Fred","School of Mathematical Sciences , Peking University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biostatistics Program , Public Health Science Division Fred","institution_ids":[]},{"raw_affiliation_string":"School of Mathematical Sciences , Peking University","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160212942","display_name":"Zhifei Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhifei","raw_affiliation_strings":["Hutchinson Cancer Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hutchinson Cancer Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135939124","display_name":"Jingyi Jessica Li","orcid":"https://orcid.org/0000-0002-9288-5648","observed_orcids":["https://orcid.org/0000-0002-9288-5648"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jingyi Jessica","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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/T10136","display_name":"Statistical Methods and Inference","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9990000128746033,"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/T11235","display_name":"Statistical Methods in Clinical Trials","score":9.999999747378752e-05,"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/T10845","display_name":"Advanced Causal Inference Techniques","score":9.999999747378752e-05,"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/post-selection-inference","display_name":"post-selection inference","score":0.9980000257492065},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.609000027179718},{"id":"https://openalex.org/keywords/feature-selection","display_name":"feature selection","score":0.6110000014305115},{"id":"https://openalex.org/keywords/linear-gaussian-models","display_name":"linear Gaussian models","score":0.6930000185966492},{"id":"https://openalex.org/keywords/riboflavin-production","display_name":"riboflavin production","score":0.8299999833106995},{"id":"https://openalex.org/keywords/genetic-association","display_name":"genetic association","score":0.5130000114440918}],"concepts":[{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6105999946594238},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5582000017166138},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.5198000073432922},{"id":"https://openalex.org/C48921125","wikidata":"https://www.wikidata.org/wiki/Q10861030","display_name":"Linear regression","level":2,"score":0.4903999865055084},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.4447999894618988},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.41589999198913574},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3977000117301941},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.39640000462532043},{"id":"https://openalex.org/C2776292839","wikidata":"https://www.wikidata.org/wiki/Q5179217","display_name":"Coverage probability","level":3,"score":0.38760000467300415},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3758000135421753},{"id":"https://openalex.org/C121683094","wikidata":"https://www.wikidata.org/wiki/Q3554721","display_name":"Control variates","level":5,"score":0.3675999939441681},{"id":"https://openalex.org/C183905921","wikidata":"https://www.wikidata.org/wiki/Q1038757","display_name":"Multiple comparisons problem","level":2,"score":0.3637000024318695},{"id":"https://openalex.org/C143380155","wikidata":"https://www.wikidata.org/wiki/Q5160088","display_name":"Confidence region","level":3,"score":0.33649998903274536},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.32280001044273376},{"id":"https://openalex.org/C152877465","wikidata":"https://www.wikidata.org/wiki/Q208042","display_name":"Regression analysis","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2924000024795532},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.28690001368522644},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C41587187","wikidata":"https://www.wikidata.org/wiki/Q1501882","display_name":"Generalized linear model","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.2766000032424927},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2757999897003174},{"id":"https://openalex.org/C70519679","wikidata":"https://www.wikidata.org/wiki/Q6666755","display_name":"Log-linear model","level":3,"score":0.27459999918937683},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C154606282","wikidata":"https://www.wikidata.org/wiki/Q7048579","display_name":"Nominal level","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C2777205145","wikidata":"https://www.wikidata.org/wiki/Q4944080","display_name":"Bootstrap model","level":4,"score":0.259799987077713},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39274","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39274","pdf_url":"https://arxiv.org/pdf/2610.39274","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":"doi:10.48550/arxiv.2610.39274","doi":"https://doi.org/10.48550/arxiv.2610.39274","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39274","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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39274","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39274","pdf_url":"https://arxiv.org/pdf/2610.39274","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224776691.pdf","grobid_xml":"https://content.openalex.org/works/W7224776691.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1921286109","https://openalex.org/W3088350445","https://openalex.org/W7008824033","https://openalex.org/W1535995764","https://openalex.org/W3024648710","https://openalex.org/W1502184303","https://openalex.org/W4400131760","https://openalex.org/W1580173816","https://openalex.org/W4226356811","https://openalex.org/W7117159519"],"abstract_inverted_index":{"Post-selection":[0],"inference":[1],"(PoSI)":[2],"quantifies":[3,223],"uncertainty":[4],"about":[5],"regression":[6],"coefficients":[7,23,47],"after":[8],"data-driven":[9],"feature":[10,140],"selection.":[11,141],"A":[12],"central":[13],"question":[14],"is":[15],"the":[16,22,25,31,37,44,49,120,147,150,177,186,212,232,237],"inferential":[17],"target.":[18],"Projection-based":[19],"targets":[20,42,63,76,98,202],"are":[21,43,54],"of":[24,132,228],"best":[26],"linear":[27,51,168],"approximation":[28,162],"restricted":[29],"to":[30,118,154,182],"selected":[32,45],"features":[33],"and":[34,53,77,158,200,208,226,230],"depend":[35],"on":[36,74,96],"selection":[38],"procedure,":[39],"whereas":[40],"population-based":[41,97,199],"features'":[46],"in":[48,67,165],"full":[50],"model":[52,117,169],"often":[55],"more":[56],"relevant":[57],"for":[58,93,135,197],"scientific":[59],"interpretation.":[60],"The":[61],"two":[62],"can":[64],"differ,":[65],"even":[66],"sign.":[68],"Existing":[69],"PoSI":[70,95],"methods":[71,187,238],"largely":[72],"focus":[73],"projection-based":[75,201],"may":[78],"yield":[79],"overly":[80],"wide":[81],"confidence":[82,133,206],"intervals.":[83],"We":[84,142],"propose":[85],"TwinPoSI":[86,105,145,174,192,219],"(statistical":[87],"twin":[88],"post-selection":[89],"inference),":[90],"a":[91,115,166],"method":[92],"powerful":[94],"with":[99,170],"false":[100],"coverage":[101],"rate":[102],"(FCR)":[103],"control.":[104],"leverages":[106],"\\textit{statistical":[107],"twins},":[108],"defined":[109],"as":[110],"synthetic":[111],"datasets":[112],"generated":[113],"from":[114],"fitted":[116],"mimic":[119],"original":[121],"data.":[122],"With":[123],"generating":[124],"parameters":[125],"known,":[126],"statistical":[127],"twins":[128],"enable":[129],"direct":[130],"calibration":[131],"intervals":[134,207,235],"bias":[136],"introduced":[137],"by":[138],"data-dependent":[139],"establish":[143],"that":[144,191],"controls":[146],"FCR":[148,195],"at":[149],"nominal":[151],"level,":[152],"up":[153],"Monte":[155],"Carlo":[156],"error":[157],"an":[159,171],"asymptotically":[160],"negligible":[161],"error.":[163],"Moreover,":[164],"Gaussian":[167],"orthogonal":[172],"design,":[173],"uniquely":[175],"attains":[176],"oracle":[178],"average":[179,234],"interval":[180],"length":[181],"first":[183],"order":[184],"among":[185,236],"considered.":[188,239],"Simulations":[189],"show":[190],"maintains":[193],"reliable":[194],"control":[196],"both":[198],"while":[203],"yielding":[204],"shorter":[205],"higher":[209],"power":[210],"than":[211],"competing":[213],"methods.":[214],"In":[215],"riboflavin":[216],"production":[217],"data,":[218],"identifies":[220],"associated":[221],"genes,":[222],"their":[224],"directions":[225],"magnitudes":[227],"association,":[229],"yields":[231],"shortest":[233]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-31T00:00:00"}