{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T16:37:04Z","timestamp":1790181424195,"version":"4.1.0"},"reference-count":68,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2024,10,21]],"date-time":"2024-10-21T00:00:00Z","timestamp":1729468800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1846210"],"award-info":[{"award-number":["1846210"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72201150"],"award-info":[{"award-number":["72201150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72322001"],"award-info":[{"award-number":["72322001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72293561"],"award-info":[{"award-number":["72293561"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0116700"],"award-info":[{"award-number":["2022ZD0116700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In many experimental and observational studies, the outcome of interest is often difficult or expensive to observe, reducing effective sample sizes for estimating average treatment effects (ATEs) even when identifiable. We study how incorporating data on units for which only surrogate outcomes not of primary interest are observed can increase the precision of ATE estimation. We refrain from imposing stringent surrogacy conditions, which permit surrogates as perfect replacements for the target outcome. Instead, we supplement the available, albeit limited, observations of the target outcome with abundant observations of surrogate outcomes, without any assumptions beyond unconfounded treatment assignment and missingness and corresponding overlap conditions. To quantify the potential gains, we derive the difference in efficiency bounds on ATE estimation with and without surrogates, both when an overwhelming or comparable number of units have missing outcomes. We develop robust ATE estimation and inference methods that realize these efficiency gains. We empirically demonstrate the gains by studying long-term-earning effects of job training.<\/jats:p>","DOI":"10.1093\/jrsssb\/qkae099","type":"journal-article","created":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T15:32:43Z","timestamp":1727191963000},"page":"480-509","source":"Crossref","is-referenced-by-count":11,"title":["On the role of surrogates in the efficient estimation of treatment effects with limited outcome data"],"prefix":"10.1093","volume":"87","author":[{"given":"Nathan","family":"Kallus","sequence":"first","affiliation":[{"name":"Cornell Tech, Cornell University , New York, NY 10044 ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojie","family":"Mao","sequence":"additional","affiliation":[{"name":"School of Economics and Management, Tsinghua University , Beijing 100084 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,10,21]]},"reference":[{"key":"2025102020022547700_qkae099-B1","doi-asserted-by":"publisher","author":"Athey","year":"2020","DOI":"10.48550\/arXiv.2006.09676"},{"key":"2025102020022547700_qkae099-B2","author":"Athey","year":"2019"},{"issue":"540","key":"2025102020022547700_qkae099-B3","doi-asserted-by":"crossref","first-page":"2238","DOI":"10.1080\/01621459.2021.1915320","article-title":"Semi-supervised linear regression","volume":"117","author":"Azriel","year":"2021","journal-title":"Journal of the American Statistical Association"},{"key":"2025102020022547700_qkae099-B4","volume-title":"Efficient and adaptive estimation for semiparametric models","author":"Bickel","year":"1993"},{"issue":"1","key":"2025102020022547700_qkae099-B5","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Machine Learning"},{"issue":"3","key":"2025102020022547700_qkae099-B6","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1111\/j.2517-6161.1991.tb01846.x","article-title":"Semiparametric estimation in logistic measurement error models","volume":"53","author":"Carroll","year":"1991","journal-title":"Journal of the Royal Statistical Society: Series B (Methodological)"},{"issue":"4","key":"2025102020022547700_qkae099-B7","doi-asserted-by":"publisher","first-page":"1541","DOI":"10.1214\/17-AOS1594","article-title":"Efficient and adaptive linear regression in semi-supervised settings","volume":"46","author":"Chakrabortty","year":"2018","journal-title":"The Annals of Statistics"},{"key":"2025102020022547700_qkae099-B8","doi-asserted-by":"publisher","author":"Chakrabortty","year":"2022","DOI":"10.48550\/arXiv.2201.10208"},{"key":"2025102020022547700_qkae099-B9","doi-asserted-by":"publisher","author":"Chakrabortty","year":"2022","DOI":"10.48550\/arXiv.2201.00468"},{"issue":"5","key":"2025102020022547700_qkae099-B10","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1111\/j.1467-9868.2007.00617.x","article-title":"Criteria for surrogate end points","volume":"69","author":"Chen","year":"2007","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"issue":"4","key":"2025102020022547700_qkae099-B11","doi-asserted-by":"publisher","first-page":"359","DOI":"10.2307\/3316021","article-title":"Semiparametric efficient estimation for the auxiliary outcome problem with the conditional mean model","volume":"32","author":"Chen","year":"2004","journal-title":"Canadian Journal of Statistics"},{"issue":"2","key":"2025102020022547700_qkae099-B12","doi-asserted-by":"publisher","first-page":"105545","DOI":"10.1016\/j.jeconom.2023.105545","article-title":"Semiparametric estimation of long-term treatment effects","volume":"237","author":"Chen","year":"2023","journal-title":"Journal of Econometrics"},{"issue":"464","key":"2025102020022547700_qkae099-B13","doi-asserted-by":"publisher","first-page":"1052","DOI":"10.1198\/016214503000000972","article-title":"Information recovery in a study with surrogate endpoints","volume":"98","author":"Chen","year":"2003","journal-title":"Journal of the American Statistical Association"},{"issue":"4","key":"2025102020022547700_qkae099-B14","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1111\/j.1467-9868.2008.00662.x","article-title":"Improving semiparametric estimation by using surrogate data","volume":"70","author":"Chen","year":"2008","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2025102020022547700_qkae099-B15","author":"Chen","year":"2016"},{"key":"2025102020022547700_qkae099-B16","doi-asserted-by":"publisher","first-page":"5549","DOI":"10.1016\/S1573-4412(07)06076-X","article-title":"Large sample sieve estimation of semi-nonparametric models","volume":"6","author":"Chen","year":"2007","journal-title":"Handbook of Econometrics"},{"issue":"2","key":"2025102020022547700_qkae099-B17","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1111\/roes.2005.72.issue-2","article-title":"Measurement error models with auxiliary data","volume":"72","author":"Chen","year":"2005","journal-title":"The Review of Economic Studies"},{"issue":"2","key":"2025102020022547700_qkae099-B18","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1214\/009053607000000947","article-title":"Semiparametric efficiency in GMM models with auxiliary data","volume":"36","author":"Chen","year":"2008","journal-title":"The Annals of Statistics"},{"issue":"3","key":"2025102020022547700_qkae099-B19","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1111\/1467-9868.00243","article-title":"A unified approach to regression analysis under double-sampling designs","volume":"62","author":"Chen","year":"2000","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"issue":"2","key":"2025102020022547700_qkae099-B20","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1111\/biom.v77.2","article-title":"Robust and efficient semi-supervised estimation of average treatment effects with application to electronic health records data","volume":"77","author":"Cheng","year":"2021","journal-title":"Biometrics"},{"issue":"1","key":"2025102020022547700_qkae099-B21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1111\/ectj.12097","article-title":"Double\/debiased machine learning for treatment and structural parameters","volume":"21","author":"Chernozhukov","year":"2018","journal-title":"The Econometrics Journal"},{"key":"2025102020022547700_qkae099-B22","volume-title":"Sampling techniques","author":"Cochran","year":"2007"},{"issue":"12","key":"2025102020022547700_qkae099-B23","doi-asserted-by":"publisher","first-page":"781","DOI":"10.1056\/NEJM199103213241201","article-title":"Mortality and morbidity in patients receiving encainide, flecainide, or placebo: The cardiac arrhythmia suppression trial","volume":"324","author":"Echt","year":"1991","journal-title":"New England Journal of Medicine"},{"issue":"1","key":"2025102020022547700_qkae099-B24","doi-asserted-by":"publisher","first-page":"13","DOI":"10.2307\/2532491","article-title":"Increasing precision or reducing expense in regression experiments by using information from a concomitant variable","volume":"47","author":"Engel","year":"1991","journal-title":"Biometrics"},{"key":"2025102020022547700_qkae099-B25","author":"FDA","year":"2016"},{"issue":"7","key":"2025102020022547700_qkae099-B26","doi-asserted-by":"publisher","first-page":"605","DOI":"10.7326\/0003-4819-125-7-199610010-00011","article-title":"Surrogate end points in clinical trials: Are we being misled?","volume":"125","author":"Fleming","year":"1996","journal-title":"Annals of Internal Medicine"},{"issue":"9","key":"2025102020022547700_qkae099-B27","doi-asserted-by":"publisher","first-page":"955","DOI":"10.1002\/sim.v13:9","article-title":"Surrogate and auxiliary endpoints in clinical trials, with potential applications in cancer and aids research","volume":"13","author":"Fleming","year":"1994","journal-title":"Statistics in Medicine"},{"issue":"1","key":"2025102020022547700_qkae099-B28","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1111\/biom.2002.58.issue-1","article-title":"Principal stratification in causal inference","volume":"58","author":"Frangakis","year":"2002","journal-title":"Biometrics"},{"issue":"5","key":"2025102020022547700_qkae099-B29","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Annals of Statistics"},{"issue":"1","key":"2025102020022547700_qkae099-B30","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1111\/biom.2008.64.issue-1","article-title":"Semiparametric inference for surrogate endpoints with bivariate censored data","volume":"64","author":"Ghosh","year":"2008","journal-title":"Biometrics"},{"key":"2025102020022547700_qkae099-B31","volume-title":"Deep learning","author":"Goodfellow","year":"2016"},{"issue":"2","key":"2025102020022547700_qkae099-B32","doi-asserted-by":"publisher","first-page":"315","DOI":"10.2307\/2998560","article-title":"On the role of the propensity score in efficient semiparametric estimation of average treatment effects","volume":"66","author":"Hahn","year":"1998","journal-title":"Econometrica"},{"issue":"3","key":"2025102020022547700_qkae099-B33","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1086\/505050","article-title":"Evaluating the differential effects of alternative welfare-to-work training components: A reanalysis of the California gain program","volume":"24","author":"Hotz","year":"2006","journal-title":"Journal of Labor Economics"},{"issue":"265","key":"2025102020022547700_qkae099-B34","first-page":"1","article-title":"Surrogate assisted semi-supervised inference for high dimensional risk prediction","volume":"24","author":"Hou","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"2025102020022547700_qkae099-B35","doi-asserted-by":"publisher","author":"Imbens","year":"2022","DOI":"10.48550\/arXiv.2202.07234"},{"key":"2025102020022547700_qkae099-B36","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139025751","volume-title":"Causal inference in statistics, social, and biomedical sciences","author":"Imbens","year":"2015"},{"issue":"4","key":"2025102020022547700_qkae099-B37","first-page":"523","article-title":"Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data","volume":"22","author":"Kang","year":"2007","journal-title":"Statistical Science"},{"issue":"2","key":"2025102020022547700_qkae099-B38","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1111\/sjos.2004.31.issue-2","article-title":"Discussion on causality [with reply]","volume":"31","author":"Lauritzen","year":"2004","journal-title":"Scandinavian Journal of Statistics"},{"issue":"13","key":"2025102020022547700_qkae099-B39","doi-asserted-by":"publisher","first-page":"1515","DOI":"10.1002\/(ISSN)1097-0258","article-title":"Estimating the proportion of treatment effect explained by a surrogate marker","volume":"16","author":"Lin","year":"1997","journal-title":"Statistics in Medicine"},{"key":"2025102020022547700_qkae099-B40","volume-title":"Statistical analysis with missing data","author":"Little","year":"2019"},{"key":"2025102020022547700_qkae099-B41","author":"NCATS","year":"2019"},{"key":"2025102020022547700_qkae099-B42","doi-asserted-by":"publisher","author":"Newey","year":"2018","DOI":"10.48550\/arXiv.1801.09138"},{"issue":"4","key":"2025102020022547700_qkae099-B43","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1214\/ss\/1177012031","article-title":"On the application of probability theory to agricultural experiments. Essay on principles. Section 9","volume":"5","author":"Neyman","year":"1923","journal-title":"Statistical Science"},{"issue":"11","key":"2025102020022547700_qkae099-B44","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1002\/sim.v36.11","article-title":"Evaluating surrogate marker information using censored data","volume":"36","author":"Parast","year":"2017","journal-title":"Statistics in Medicine"},{"issue":"2","key":"2025102020022547700_qkae099-B45","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1093\/biomet\/79.2.355","article-title":"Inference using surrogate outcome data and a validation sample","volume":"79","author":"Pepe","year":"1992","journal-title":"Biometrika"},{"issue":"1-2","key":"2025102020022547700_qkae099-B46","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1016\/0378-3758(94)90194-5","article-title":"Auxiliary outcome data and the mean score method","volume":"42","author":"Pepe","year":"1994","journal-title":"Journal of Statistical Planning and Inference"},{"issue":"1","key":"2025102020022547700_qkae099-B47","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s11136-009-9564-1","article-title":"The analysis of longitudinal quality of life measures with informative drop-out: A pattern mixture approach","volume":"19","author":"Post","year":"2010","journal-title":"Quality of Life Research"},{"issue":"4","key":"2025102020022547700_qkae099-B48","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1002\/sim.v8:4","article-title":"Surrogate endpoints in clinical trials: Definition and operational criteria","volume":"8","author":"Prentice","year":"1989","journal-title":"Statistics in Medicine"},{"issue":"4","key":"2025102020022547700_qkae099-B49","doi-asserted-by":"publisher","first-page":"1271","DOI":"10.1111\/biom.12879","article-title":"Estimation of the optimal surrogate based on a randomized trial","volume":"74","author":"Price","year":"2018","journal-title":"Biometrics"},{"issue":"2","key":"2025102020022547700_qkae099-B50","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1093\/biomet\/82.2.299","article-title":"A mean score method for missing and auxiliary covariate data in regression models","volume":"82","author":"Reilly","year":"1995","journal-title":"Biometrika"},{"issue":"429","key":"2025102020022547700_qkae099-B51","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1080\/01621459.1995.10476494","article-title":"Semiparametric efficiency in multivariate regression models with missing data","volume":"90","author":"Robins","year":"1995","journal-title":"Journal of the American Statistical Association"},{"issue":"427","key":"2025102020022547700_qkae099-B52","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1080\/01621459.1994.10476818","article-title":"Estimation of regression coefficients when some regressors are not always observed","volume":"89","author":"Robins","year":"1994","journal-title":"Journal of the American Statistical Association"},{"issue":"469","key":"2025102020022547700_qkae099-B53","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1198\/016214504000001880","article-title":"Causal inference using potential outcomes: Design, modeling, decisions","volume":"100","author":"Rubin","year":"2005","journal-title":"Journal of the American Statistical Association"},{"issue":"448","key":"2025102020022547700_qkae099-B54","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1080\/01621459.1999.10473862","article-title":"Adjusting for nonignorable drop-out using semiparametric nonresponse models","volume":"94","author":"Scharfstein","year":"1999","journal-title":"Journal of the American Statistical Association"},{"key":"2025102020022547700_qkae099-B55","volume-title":"Learning with kernels","author":"Smola","year":"1998"},{"key":"2025102020022547700_qkae099-B56","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9780262017091.001.0001","volume-title":"Machine learning in non-stationary environments: Introduction to covariate shift adaptation","author":"Sugiyama","year":"2012"},{"key":"2025102020022547700_qkae099-B57","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139035613","volume-title":"Density ratio estimation in machine learning","author":"Sugiyama","year":"2012"},{"key":"2025102020022547700_qkae099-B58","volume-title":"Semiparametric theory and missing data","author":"Tsiatis","year":"2007"},{"key":"2025102020022547700_qkae099-B59","author":"van der Laan","year":"2003"},{"key":"2025102020022547700_qkae099-B60","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511802256","volume-title":"Asymptotic statistics","author":"van der Vaart","year":"1998"},{"issue":"3","key":"2025102020022547700_qkae099-B61","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1111\/biom.v69.3","article-title":"Surrogate measures and consistent surrogates","volume":"69","author":"VanderWeele","year":"2013","journal-title":"Biometrics"},{"issue":"5","key":"2025102020022547700_qkae099-B62","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1111\/j.1467-9868.2009.00712.x","article-title":"Causal inference in outcome-dependent two-phase sampling designs","volume":"71","author":"Wang","year":"2009","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"issue":"1","key":"2025102020022547700_qkae099-B63","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1093\/biomet\/asz065","article-title":"Model-free approach to quantifying the proportion of treatment effect explained by a surrogate marker","volume":"107","author":"Wang","year":"2020","journal-title":"Biometrika"},{"issue":"4","key":"2025102020022547700_qkae099-B64","first-page":"1193","article-title":"A revisit of semiparametric regression models with missing data","volume":"16","author":"Yu","year":"2006","journal-title":"Statistica Sinica"},{"issue":"5","key":"2025102020022547700_qkae099-B65","doi-asserted-by":"publisher","first-page":"2538","DOI":"10.1214\/18-AOS1756","article-title":"Semi-supervised inference: General theory and estimation of means","volume":"47","author":"Zhang","year":"2019","journal-title":"The Annals of Statistics"},{"issue":"2","key":"2025102020022547700_qkae099-B66","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1093\/biomet\/asab042","article-title":"High-dimensional semi-supervised learning: in search of optimal inference of the mean","volume":"109","author":"Zhang","year":"2022","journal-title":"Biometrika"},{"issue":"3","key":"2025102020022547700_qkae099-B67","doi-asserted-by":"publisher","first-page":"2066","DOI":"10.1093\/imaiai\/iaad021","article-title":"Double robust semi-supervised inference for the mean: selection bias under MAR labeling with decaying overlap","volume":"12","author":"Zhang","year":"2023","journal-title":"Information and Inference: A Journal of the IMA"},{"key":"2025102020022547700_qkae099-B68","author":"Zheng","year":"2011"}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/87\/2\/480\/59931819\/qkae099.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/87\/2\/480\/59931819\/qkae099.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:02:37Z","timestamp":1761004957000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/87\/2\/480\/7829031"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,21]]},"references-count":68,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,10,21]]},"published-print":{"date-parts":[[2025,4,11]]}},"URL":"https:\/\/doi.org\/10.1093\/jrsssb\/qkae099","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,4]]},"published":{"date-parts":[[2024,10,21]]}}}