{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T20:36:09Z","timestamp":1791923769353,"version":"4.3.4"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T00:00:00Z","timestamp":1676851200000},"content-version":"vor","delay-in-days":1869,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-16-1-2712"],"award-info":[{"award-number":["N00014-16-1-2712"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000893","name":"Simons Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000893","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation Career","doi-asserted-by":"publisher","award":["DMS-1150318"],"award-info":[{"award-number":["DMS-1150318"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health training","doi-asserted-by":"publisher","award":["T32GM096982"],"award-info":[{"award-number":["T32GM096982"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6,1]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>Many contemporary large-scale applications involve building interpretable models linking a large set of potential covariates to a response in a non-linear fashion, such as when the response is binary. Although this modelling problem has been extensively studied, it remains unclear how to control the fraction of false discoveries effectively even in high dimensional logistic regression, not to mention general high dimensional non-linear models. To address such a practical problem, we propose a new framework of \u2018model-X\u2019 knockoffs, which reads from a different perspective the knockoff procedure that was originally designed for controlling the false discovery rate in linear models. Whereas the knockoffs procedure is constrained to homoscedastic linear models with n\u2a7ep, the key innovation here is that model-X knockoffs provide valid inference from finite samples in settings in which the conditional distribution of the response is arbitrary and completely unknown. Furthermore, this holds no matter the number of covariates. Correct inference in such a broad setting is achieved by constructing knockoff variables probabilistically instead of geometrically. To do this, our approach requires that the covariates are random (independent and identically distributed rows) with a distribution that is known, although we provide preliminary experimental evidence that our procedure is robust to unknown or estimated distributions. To our knowledge, no other procedure solves the controlled variable selection problem in such generality but, in the restricted settings where competitors exist, we demonstrate the superior power of knockoffs through simulations. Finally, we apply our procedure to data from a case\u2013control study of Crohn's disease in the UK, making twice as many discoveries as the original analysis of the same data.<\/jats:p>","DOI":"10.1111\/rssb.12265","type":"journal-article","created":{"date-parts":[[2018,1,10]],"date-time":"2018-01-10T01:33:29Z","timestamp":1515548009000},"page":"551-577","source":"Crossref","is-referenced-by-count":562,"title":["Panning for Gold: \u2018Model-X\u2019 Knockoffs for High Dimensional Controlled Variable Selection"],"prefix":"10.1093","volume":"80","author":[{"given":"Emmanuel","family":"Cand\u00e8s","sequence":"first","affiliation":[{"name":"Stanford University , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingying","family":"Fan","sequence":"additional","affiliation":[{"name":"University of Southern California , Los Angeles , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucas","family":"Janson","sequence":"additional","affiliation":[{"name":"Stanford University , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinchi","family":"Lv","sequence":"additional","affiliation":[{"name":"University of Southern California , Los Angeles , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,1,8]]},"reference":[{"key":"2023022101112300600_","article-title":"Efficient inference of average treatment effects in high dimensions via approximate residual balancing","volume-title":"Preprint arXiv:1604.07125","author":"Athey","year":"2016"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"2055","DOI":"10.1214\/15-AOS1337","article-title":"Controlling the false discovery rate via knockoffs","volume":"43","author":"Barber","year":"2015","journal-title":"Ann. Statist."},{"issue":"11","key":"2023022101112300600_","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0080908","article-title":"Macrophage polarisation: an immunohistochemical approach for identifying m1 and m2 macrophages","volume":"8","author":"Barros","year":"2013","journal-title":"PLOS One"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1111\/j.1467-9868.2010.00746.x","article-title":"Discovering the false discovery rate","volume":"72","author":"Benjamini","year":"2010","journal-title":"J. R. Statist. Soc."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1214\/08-AOAS194","article-title":"A simple forward selection procedure based on false discovery rate control","volume":"3","author":"Benjamini","year":"2009","journal-title":"Ann. Appl. Statist."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/j.2517-6161.1995.tb02031.x","article-title":"Controlling the false discovery rate: a practical and powerful approach to multiple testing","volume":"57","author":"Benjamini","year":"1995","journal-title":"J. R. Statist. Soc."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1214\/aos\/1013699998","article-title":"The control of the false discovery rate in multiple testing under dependency","volume":"29","author":"Benjamini","year":"2001","journal-title":"Ann. Statist."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1214\/12-AOS1077","article-title":"Valid post-selection inference","volume":"41","author":"Berk","year":"2013","journal-title":"Ann. Statist."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.1214\/15-AOAS842","article-title":"SLOPE\u2014adaptive variable selection via convex optimization","volume":"9","author":"Bogdan","year":"2015","journal-title":"Ann. Appl. Statist."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"2145","DOI":"10.1214\/08-AOS653","article-title":"Near-ideal model selection by l1 minimization","volume":"37","author":"Cand\u00e8s","year":"2009","journal-title":"Ann. Statist."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"819","DOI":"10.1126\/science.1231143","article-title":"Multiplex genome engineering using crispr\/cas systems","volume":"339","author":"Cong","year":"2013","journal-title":"Science"},{"key":"2023022101112300600_","article-title":"The knockoff filter for fdr control in group-sparse and multitask regression","volume-title":"Preprint arXiv:1602.03589","author":"Dai","year":"2016"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1214\/15-STS527","article-title":"High-dimensional inference: confidence intervals, p-values and r-software hdi","volume":"30","author":"Dezeure","year":"2015","journal-title":"Statist. Sci."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4612-0493-0","volume-title":"Introduction to Graphical Modelling","author":"Edwards","year":"2000"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.1038\/ng.717","article-title":"Genome-wide meta-analysis increases to 71 the number of confirmed Crohn's disease susceptibility loci","volume":"42","author":"Franke","year":"2010","journal-title":"Nat. Genet."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1214\/14-AOS1221","article-title":"On asymptotically optimal confidence regions and tests for high-dimensional models","volume":"42","author":"van de Geer","year":"2014","journal-title":"Ann. Statist."},{"key":"2023022101112300600_","first-page":"339","article-title":"Approaches for bayesian variable selection","volume":"7","author":"George","year":"1997","journal-title":"Statist. Sin."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"1250","DOI":"10.1038\/mi.2016.1","article-title":"KLF6 contributes to myeloid cell plasticity in the pathogenesis of intestinal inflammation","volume":"9","author":"Goodman","year":"2016","journal-title":"Mucsl Immun"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"1780","DOI":"10.1214\/11-AOAS455","article-title":"Bayesian variable selection regression for genome-wide association studies and other large-scale problems","volume":"5","author":"Guan","year":"2011","journal-title":"Ann. Appl. Statist."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1093\/genetics\/16.4.357","article-title":"Inbreeding and linkage","volume":"16","author":"Haldane","year":"1931","journal-title":"Genetics"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/bioinformatics\/btq600","article-title":"A variable selection method for genome-wide association studies","volume":"27","author":"He","year":"2011","journal-title":"Bioinformatics"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"960","DOI":"10.1214\/16-EJS1129","article-title":"Familywise error rate control via knockoffs","volume":"10","author":"Janson","year":"2016","journal-title":"Electron. J. Statist."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"907","DOI":"10.1214\/15-AOS1371","article-title":"Exact post-selection inference, with application to the lasso","volume":"44","author":"Lee","year":"2016","journal-title":"Ann. Statist."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1093\/bioinformatics\/btq688","article-title":"The bayesian lasso for genome-wide association studies","volume":"27","author":"Li","year":"2011","journal-title":"Bioinformatics"},{"key":"2023022101112300600_","article-title":"Topological false discovery rates for brain mapping based on signal height","volume-title":"Neuroimage","author":"Li","year":"2016"},{"key":"2023022101112300600_","first-page":"413","article-title":"A significance test for the lasso","volume":"42","author":"Lockhart","year":"2014","journal-title":"Ann. Statist."},{"key":"2023022101112300600_","volume-title":"MATLAB 2015b","author":"MATLAB","year":"2015"},{"key":"2023022101112300600_","volume-title":"Probabilistic Inference in Intelligent Systems","author":"Pearl","year":"1988"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1016\/j.cell.2016.05.003","article-title":"A comprehensive, CRISPR-based functional analysis of essential genes in bacteria","volume":"165","author":"Peters","year":"2016","journal-title":"Cell"},{"key":"2023022101112300600_","volume-title":"Global Sensitivity Analysis: the Primer","author":"Saltelli","year":"2008"},{"key":"2023022101112300600_","first-page":"59","article-title":"Danger: High power!? \u2014 exploring the statistical properties of a test for random forest variable importance","volume-title":"COMPSTAT 2008\u2013Proceedings in Computational Statistics","author":"Strobl","year":"2008"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1086\/504302","article-title":"Reconstructing genetic ancestry blocks in admixed individuals","volume":"79","author":"Tang","year":"2006","journal-title":"Am. J. Hum. Genet."},{"key":"2023022101112300600_","article-title":"Estimation and inference of heterogeneous treatment effects using random forests","volume-title":"Preprint arXiv:1510.04342","author":"Wager","year":"2016"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1038\/nature05911","article-title":"Genome-wide association study of 14, 000 cases of seven common diseases and 3, 000 shared controls","volume":"447","author":"Wellcome Trust Case Control Consortium","year":"2007","journal-title":"Nature"},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"1158","DOI":"10.1214\/10-AOAS338","article-title":"Using linear predictors to impute allele frequencies from summary or pooled genotype data","volume":"4","author":"Wen","year":"2010","journal-title":"Ann. Appl. Statist."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"745","DOI":"10.1002\/bimj.200710456","article-title":"Multiple testing with minimal assumptions","volume":"50","author":"Westfall","year":"2008","journal-title":"Biometr. J."},{"key":"2023022101112300600_","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1093\/bioinformatics\/btp041","article-title":"Genome-wide association analysis by lasso penalized logistic regression","volume":"25","author":"Wu","year":"2009","journal-title":"Bioinformatics"},{"key":"2023022101112300600_","first-page":"2541","article-title":"On model selection consistency of lasso","volume":"7","author":"Zhao","year":"2006","journal-title":"J. Mach. Learn. Res."}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Frssb.12265","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/rssb.12265","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/rssb.12265","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/am-pdf\/10.1111\/rssb.12265","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/80\/3\/551\/49274696\/jrsssb_80_3_551.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/80\/3\/551\/49274696\/jrsssb_80_3_551.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T07:28:48Z","timestamp":1719732528000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/80\/3\/551\/7048447"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1,8]]},"references-count":38,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2018,1,8]]},"published-print":{"date-parts":[[2018,6,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12265","relation":{"has-review":[{"id-type":"doi","id":"10.3410\/f.732703320.793559523","asserted-by":"object"}]},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,6]]},"published":{"date-parts":[[2018,1,8]]}}}