{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T19:37:42Z","timestamp":1787945862318,"version":"build-2784847793"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T00:00:00Z","timestamp":1761696000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,2,13]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>Algorithms for constraint-based causal discovery select graphical causal models among a space of possible candidates (e.g., all directed acyclic graphs) by executing a sequence of conditional independence tests. These may be used to inform the estimation of causal effects (e.g., average treatment effects) when there is uncertainty about which covariates ought to be adjusted for, or which variables act as confounders versus mediators. However, naively using the data twice, for model selection and estimation, would lead to invalid confidence intervals. Moreover, if the selected graph is incorrect, the inferential claims may apply to a selected functional that is distinct from the actual causal effect. We propose an approach to post-selection inference that is based on a resampling and screening procedure, which essentially performs causal discovery multiple times with randomly varying intermediate test statistics. Then, an estimate of the target causal effect and corresponding confidence sets are constructed from a union of individual graph-based estimates and intervals. We show that this construction has asymptotically correct coverage for the true causal effect parameter. Importantly, the guarantee holds for a fixed population-level effect, not a data-dependent or selection-dependent quantity. Most of our exposition focuses on the PC algorithm for learning directed acyclic graphs and on the multivariate Gaussian case for simplicity, but the approach is general and modular, so it may be used with other conditional-independence-based discovery algorithms and distributional families.<\/jats:p>","DOI":"10.1093\/biomet\/asaf073","type":"journal-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:01:55Z","timestamp":1761393715000},"source":"Crossref","is-referenced-by-count":4,"title":["Post-selection inference for causal effects after causal discovery"],"prefix":"10.1093","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6002-2947","authenticated-orcid":false,"given":"Ting-Hsuan","family":"Chang","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Columbia University , 722 West 168th Street , New York, New York 10032,","place":["U.S.A"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijian","family":"Guo","sequence":"additional","affiliation":[{"name":"Center for Data Science, Zhejiang University , Hangzhou, Zhejiang 310027, \u00a0 zijguo@zju.edu.cn","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Malinsky","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Columbia University , 722 West 168th Street , New York, New York 10032, . d.malinsky@columbia.edu","place":["U.S.A"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,10,29]]},"reference":[{"key":"2026032607091889100_asaf073-B1","author":"Andrews","year":"2022"},{"key":"2026032607091889100_asaf073-B2","first-page":"308","author":"Bellot","year":"2024"},{"key":"2026032607091889100_asaf073-B3","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1093\/restud\/rdt044","article-title":"Inference on treatment effects after selection among high-dimensional controls","volume":"81","author":"Belloni","year":"2014","journal-title":"Rev. Econ. Studies"},{"key":"2026032607091889100_asaf073-B4","first-page":"1","article-title":"A distribution free conditional independence test with applications to causal discovery","volume":"23","author":"Cai","year":"2022","journal-title":"J. Mach. Learn. Res"},{"key":"2026032607091889100_asaf073-B5","doi-asserted-by":"crossref","first-page":"351","DOI":"10.3390\/e24030351","article-title":"Nonparametric causal structure learning in high dimensions","volume":"24","author":"Chakraborty","year":"2022","journal-title":"Entropy"},{"key":"2026032607091889100_asaf073-B6","first-page":"3921","article-title":"Order-independent constraint-based causal structure learning","volume":"15","author":"Colombo","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"2026032607091889100_asaf073-B7","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1093\/biomet\/asad055","article-title":"Selective machine learning of doubly robust functionals","volume":"111","author":"Cui","year":"2024","journal-title":"Biometrika"},{"key":"2026032607091889100_asaf073-B8","first-page":"1778","article-title":"An automated approach to causal inference in discrete settings","volume":"119","author":"Duarte","year":"2023","journal-title":"J. Am. Statist. Assoc"},{"key":"2026032607091889100_asaf073-B9","doi-asserted-by":"crossref","first-page":"1429","DOI":"10.1093\/biomet\/asae020","article-title":"Sharp symbolic nonparametric bounds for measures of benefit in observational and imperfect randomized studies with ordinal outcomes","volume":"111","author":"Gabriel","year":"2024","journal-title":"Biometrika"},{"key":"2026032607091889100_asaf073-B10","author":"Gradu","year":"2024"},{"key":"2026032607091889100_asaf073-B11","first-page":"1847","volume-title":"Proc. 23rd Int. Conf. Neural Info. Proces. Syst","author":"Gretton","year":"2009"},{"key":"2026032607091889100_asaf073-B12","author":"Guo","year":"2023"},{"key":"2026032607091889100_asaf073-B13","first-page":"3365","article-title":"PC algorithm for nonparanormal graphical models","volume":"14","author":"Harris","year":"2013","journal-title":"J. Mach. Learn. Res"},{"key":"2026032607091889100_asaf073-B14","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1111\/rssb.12451","article-title":"Graphical criteria for efficient total effect estimation via adjustment in causal linear models","volume":"84","author":"Henckel","year":"2022","journal-title":"J. R. Statist. Soc. B"},{"key":"2026032607091889100_asaf073-B15","first-page":"613","article-title":"Estimating high-dimensional directed acyclic graphs with the PC-algorithm","volume":"8","author":"Kalisch","year":"2007","journal-title":"J. Mach. Learn. Res"},{"key":"2026032607091889100_asaf073-B16","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198522195.001.0001","volume-title":"Graphical Models","author":"Lauritzen","year":"1996"},{"key":"2026032607091889100_asaf073-B17","doi-asserted-by":"crossref","first-page":"3133","DOI":"10.1214\/09-AOS685","article-title":"Estimating high-dimensional intervention effects from observational data","volume":"37","author":"Maathuis","year":"2009","journal-title":"Ann. Statist."},{"key":"2026032607091889100_asaf073-B18","first-page":"403","volume-title":"Proc. 11th Conf. Uncertainty Artif. Intel","author":"Meek","year":"1995"},{"key":"2026032607091889100_asaf073-B19","first-page":"3919","article-title":"Joint causal inference from multiple contexts","volume":"21","author":"Mooij","year":"2020","journal-title":"J. Mach. Learn. Res"},{"issue":"1","key":"2026032607091889100_asaf073-B20","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1214\/21-STS843","article-title":"The costs and benefits of uniformly valid causal inference with high-dimensional nuisance parameters","volume":"38","author":"Moosavi","year":"2023","journal-title":"Statist. Sci."},{"key":"2026032607091889100_asaf073-B21","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511803161","volume-title":"Causality","author":"Pearl","year":"2009"},{"key":"2026032607091889100_asaf073-B22","doi-asserted-by":"crossref","first-page":"1898","DOI":"10.1093\/aje\/kwab087","article-title":"Data-driven model building for life-course epidemiology","volume":"190","author":"Petersen","year":"2021","journal-title":"Am. J. Epidemiol."},{"key":"2026032607091889100_asaf073-B23","first-page":"1","article-title":"Testing conditional independence via quantile regression based partial copulas","volume":"22","author":"Petersen","year":"2021","journal-title":"J. Mach. Learn. Res"},{"key":"2026032607091889100_asaf073-B24","author":"R Development Core Team","year":"2026"},{"key":"2026032607091889100_asaf073-B25","author":"Ramsey","year":"2018"},{"key":"2026032607091889100_asaf073-B26","doi-asserted-by":"crossref","first-page":"e183","DOI":"10.1002\/sta4.183","article-title":"Learning directed acyclic graph models based on sparsest permutations","volume":"7","author":"Raskutti","year":"2018","journal-title":"Statist"},{"key":"2026032607091889100_asaf073-B27","first-page":"1","article-title":"Efficient adjustment sets for population average causal treatment effect estimation in graphical models","volume":"21","author":"Rotnitzky","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"2026032607091889100_asaf073-B28","doi-asserted-by":"crossref","first-page":"523","DOI":"10.1126\/science.1105809","article-title":"Causal protein-signaling networks derived from multiparameter single-cell data","volume":"308","author":"Sachs","year":"2005","journal-title":"Science"},{"key":"2026032607091889100_asaf073-B29","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1080\/10618600.2022.2071905","article-title":"A general method for deriving tight symbolic bounds on causal effects","volume":"32","author":"Sachs","year":"2023","journal-title":"J. Comp. Graph. Statist"},{"key":"2026032607091889100_asaf073-B30","doi-asserted-by":"crossref","first-page":"1514","DOI":"10.1214\/19-AOS1857","article-title":"The hardness of conditional independence testing and the generalised covariance measure","volume":"48","author":"Shah","year":"2020","journal-title":"Ann. Statist."},{"key":"2026032607091889100_asaf073-B31","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1093\/biomet\/asab018","article-title":"Efficient adjustment sets in causal graphical models with hidden variables","volume":"109","author":"Smucler","year":"2022","journal-title":"Biometrika"},{"key":"2026032607091889100_asaf073-B32","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1093\/biomet\/asaa104","article-title":"Consistency guarantees for greedy permutation-based causal inference algorithms","volume":"108","author":"Solus","year":"2021","journal-title":"Biometrika"},{"key":"2026032607091889100_asaf073-B33","first-page":"1","article-title":"The reduced pc-algorithm: improved causal structure learning in large random networks","volume":"20","author":"Sondhi","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"2026032607091889100_asaf073-B34","volume-title":"Causation, Prediction, and Search","author":"Spirtes","year":"2000"},{"key":"2026032607091889100_asaf073-B35","doi-asserted-by":"crossref","first-page":"20230030","DOI":"10.1515\/jci-2023-0030","article-title":"Confidence in causal inference under structure uncertainty in linear causal models with equal variances","volume":"11","author":"Strieder","year":"2023","journal-title":"J. Causal Infer"},{"key":"2026032607091889100_asaf073-B36","first-page":"1217","author":"Strieder","year":"2021"},{"key":"2026032607091889100_asaf073-B37","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1214\/12-AOS1080","article-title":"Geometry of the faithfulness assumption in causal inference","volume":"41","author":"Uhler","year":"2013","journal-title":"Ann. Statist."},{"key":"2026032607091889100_asaf073-B38","author":"Witte","year":"2023"},{"key":"2026032607091889100_asaf073-B39","first-page":"1","article-title":"On efficient adjustment in causal graphs","volume":"21","author":"Witte","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"2026032607091889100_asaf073-B40","first-page":"10442","author":"Xiang","year":"2020"},{"key":"2026032607091889100_asaf073-B41","author":"Xie","year":"2022"}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asaf073\/65025572\/asaf073.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/113\/1\/asaf073\/65025572\/asaf073.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/113\/1\/asaf073\/65025572\/asaf073.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T11:09:26Z","timestamp":1774523366000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/doi\/10.1093\/biomet\/asaf073\/8306019"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,29]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2,13]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asaf073","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026]]},"published":{"date-parts":[[2025,10,29]]},"article-number":"asaf073"}}