{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:52:21Z","timestamp":1782971541108,"version":"3.54.5"},"reference-count":27,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2008,9,16]],"date-time":"2008-09-16T00:00:00Z","timestamp":1221523200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Interuniversity Attraction Pole research network","award":["P06\/03"],"award-info":[{"award-number":["P06\/03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,11,1]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>When regression models adjust for mediators on the causal path from exposure to outcome, the regression coefficient of exposure is commonly viewed as a measure of the direct exposure effect. This interpretation can be misleading, even with a randomly assigned exposure. This is because adjustment for post-exposure measurements introduces bias whenever their association with the outcome is confounded by more than just the exposure. By the same token, adjustment for such confounders stays problematic when these are themselves affected by the exposure. Robins accommodated this by introducing linear structural nested direct effect models with direct effect parameters that can be estimated by using inverse probability weighting by a conditional distribution of the mediator. The resulting estimators are consistent, but inefficient, and can be extremely unstable when the mediator is absolutely continuous. We develop direct effect estimators which are not only more efficient but also consistent under a less demanding model for a conditional expectation of the outcome. We find that the one estimator which avoids inverse probability weighting altogether performs best. This estimator is intuitive, computationally straightforward and, as demonstrated by simulation, competes extremely well with ordinary least squares estimators in settings where standard regression is valid.<\/jats:p>","DOI":"10.1111\/j.1467-9868.2008.00673.x","type":"journal-article","created":{"date-parts":[[2008,9,16]],"date-time":"2008-09-16T12:17:51Z","timestamp":1221567471000},"page":"1049-1066","source":"Crossref","is-referenced-by-count":79,"title":["Estimation of Controlled Direct Effects"],"prefix":"10.1093","volume":"70","author":[{"given":"Sylvie","family":"Goetgeluk","sequence":"first","affiliation":[{"name":"Ghent University , Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stijn","family":"Vansteelandt","sequence":"additional","affiliation":[{"name":"Ghent University , Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Els","family":"Goetghebeur","sequence":"additional","affiliation":[{"name":"Ghent University , Belgium"},{"name":"Harvard School of Public Health , Boston , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2008,9,16]]},"reference":[{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1126\/science.187.4175.398","article-title":"Sex bias in graduate admissions: data from Berkeley","volume":"187","author":"Bickel","year":"1975","journal-title":"Science"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1093\/ije\/31.1.163","article-title":"Fallibility in estimating direct effects","volume":"31","author":"Cole","year":"2002","journal-title":"Int. J. Epidem."},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1093\/humrep\/dem151","article-title":"Should we adjust for gestational age when analysing birth weights?: the use of z-scores revisited","volume":"22","author":"Delbaere","year":"2007","journal-title":"Hum. Reprodn"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"2633","DOI":"10.1093\/humrep\/del247","article-title":"Birthweight of singletons after assisted reproduction is higher after single- than after double-embryo transfer","volume":"21","author":"De Sutter","year":"2006","journal-title":"Hum. Reprodn"},{"key":"2023040707570422600_","first-page":"138","volume-title":"Proc. 22nd A. Conf. Uncertainty in Artifical Intelligence","author":"Didelez","year":"2006"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1111\/j.0006-341X.2002.00021.x","article-title":"Principal stratification in causal inference","volume":"58","author":"Frangakis","year":"2002","journal-title":"Biometrics"},{"key":"2023040707570422600_","volume-title":"Direct effect models","author":"Van Der Laan","year":"2005"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-21700-0","volume-title":"Unified Methods for Censored Longitudinal Data and Causality","author":"Van Der Laan","year":"2003"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1191\/0962280204sm362ra","article-title":"A perspective on surrogate endpoints in controlled clinical trials","volume":"13","author":"Molenberghs","year":"2004","journal-title":"Statist. Meth. Med. Res."},{"key":"2023040707570422600_","volume-title":"Causality: Models, Reasoning, and Inference","author":"Pearl","year":"2000"},{"key":"2023040707570422600_","first-page":"411","volume-title":"Proc. 17th Conf. Uncertainty in Artificial Intelligence","author":"Pearl","year":"2001"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"276","DOI":"10.1097\/01.ede.0000208475.99429.2d","article-title":"Estimation of direct causal effects","volume":"17","author":"Petersen","year":"2006","journal-title":"Epidemiology"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"1393","DOI":"10.1016\/0270-0255(86)90088-6","article-title":"A new approach to causal inference in mortality studies with sustained exposure periods\u2014application to control of the healthy worker survivor effect","volume":"7","author":"Robins","year":"1986","journal-title":"Math. Modllng"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"2379","DOI":"10.1080\/03610929408831393","article-title":"Correcting for non-compliance in randomized trials using structural nested mean models","volume":"23","author":"Robins","year":"1994","journal-title":"Communs Statist. Theory Meth."},{"key":"2023040707570422600_","first-page":"349","volume-title":"Computation, Causation, and Discovery","author":"Robins","year":"1999"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1097\/00001648-199203000-00013","article-title":"Identifiability and exchangeability for direct and indirect effects","volume":"3","author":"Robins","year":"1992","journal-title":"Epidemiology"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"479","DOI":"10.2307\/2532304","article-title":"Estimating exposure effects by modelling the expectation of exposure conditional on confounders","volume":"48","author":"Robins","year":"1992","journal-title":"Biometrics"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1111\/j.1541-0420.2007.00847_2.x","article-title":"Discussion of \u2018Principal stratification designs to estimate input data missing due to death\u2019, by C. E. Frangakis, D. B. Rubin, M.-W. An and E. MacKenzie.","volume":"63","author":"Robins","year":"2007","journal-title":"Biometrics"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"544","DOI":"10.1214\/07-STS227D","article-title":"Performance of double-robust estimators when inverse probability weights are highly variable","volume":"22","author":"Robins","year":"2007","journal-title":"Statist. Sci."},{"key":"2023040707570422600_","volume-title":"Double-robust and efficient methods for estimating the average causal effect of a binary treatment","author":"Robins","year":"2008"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"656","DOI":"10.2307\/2981697","article-title":"The consequences of adjustment for a concomitant variable that has been affected by the treatment","volume":"147","author":"Rosenbaum","year":"1984","journal-title":"J. R. Statist. Soc. A"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1111\/j.1467-9469.2004.02-123.x","article-title":"Direct and indirect causal effects via potential outcomes","volume":"31","author":"Rubin","year":"2004","journal-title":"Scand. J. Statist."},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"1619","DOI":"10.1198\/016214506000000023","article-title":"A distributional approach for causal inference using propensity scores","volume":"101","author":"Tan","year":"2006","journal-title":"J. Am. Statist. Ass."},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"1102","DOI":"10.1111\/j.1541-0420.2005.00380.x","article-title":"Counterfactual links to the proportion of treatment effect explained by a surrogate marker","volume":"61","author":"Taylor","year":"2005","journal-title":"Biometrics"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"926","DOI":"10.1111\/j.1541-0420.2007.00766.x","article-title":"Causal mediation analyses with rank preserving models","volume":"63","author":"Ten Have","year":"2007","journal-title":"Biometrics"},{"key":"2023040707570422600_","doi-asserted-by":"crossref","first-page":"1173","DOI":"10.1136\/bmj.38625.685706.AE","article-title":"Preterm birth in twins following subfertility treatment: a population-based cohort study","volume":"331","author":"Verstraelen","year":"2005","journal-title":"Br. Med. J."},{"key":"2023040707570422600_","volume-title":"Diagnosing bias in the inverse probability of treatment weighted estimator resulting from violation of experimental treatment assignment","author":"Wang","year":"2006"}],"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%2Fj.1467-9868.2008.00673.x","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/70\/5\/1049\/49796075\/jrsssb_70_5_1049.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/70\/5\/1049\/49796075\/jrsssb_70_5_1049.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T19:43:16Z","timestamp":1684525396000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/70\/5\/1049\/7109483"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,9,16]]},"references-count":27,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2008,9,16]]},"published-print":{"date-parts":[[2008,11,1]]}},"URL":"https:\/\/doi.org\/10.1111\/j.1467-9868.2008.00673.x","relation":{"has-review":[{"id-type":"doi","id":"10.3410\/f.1138948.596049","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":[[2008,11]]},"published":{"date-parts":[[2008,9,16]]}}}