{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T22:31:07Z","timestamp":1790375467214,"version":"4.1.0"},"reference-count":33,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2014,10,15]],"date-time":"2014-10-15T00:00:00Z","timestamp":1413331200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2015,9,1]],"date-time":"2015-09-01T00:00:00Z","timestamp":1441065600000},"content-version":"tdm","delay-in-days":321,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01-AI073127"],"award-info":[{"award-number":["R01-AI073127"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["wiley.com"],"crossmark-restriction":true},"short-container-title":["Statistics in Medicine"],"published-print":{"date-parts":[[2015,1,15]]},"abstract":"<jats:p>Inverse probability weights used to fit marginal structural models are typically estimated using logistic regression. However, a data\u2010adaptive procedure may be able to better exploit information available in measured covariates. By combining predictions from multiple algorithms, ensemble learning offers an alternative to logistic regression modeling to further reduce bias in estimated marginal structural model parameters. We describe the application of two ensemble learning approaches to estimating stabilized weights: super learning (SL), an ensemble machine learning approach that relies on<jats:italic>V<\/jats:italic>\u2010fold cross validation, and an ensemble learner (EL) that creates a single partition of the data into training and validation sets. Longitudinal data from two multicenter cohort studies in Spain (CoRIS and CoRIS\u2010MD) were analyzed to estimate the mortality hazard ratio for initiation versus no initiation of combined antiretroviral therapy among HIV positive subjects. Both ensemble approaches produced hazard ratio estimates further away from the null, and with tighter confidence intervals, than logistic regression modeling. Computation time for EL was less than half that of SL. We conclude that ensemble learning using a library of diverse candidate algorithms offers an alternative to parametric modeling of inverse probability weights when fitting marginal structural models. With large datasets, EL provides a rich search over the solution space in less time than SL with comparable results. Copyright \u00a9 2014 John Wiley &amp; Sons, Ltd.<\/jats:p>","DOI":"10.1002\/sim.6322","type":"journal-article","created":{"date-parts":[[2014,10,15]],"date-time":"2014-10-15T09:06:30Z","timestamp":1413363990000},"page":"106-117","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":51,"title":["Ensemble learning of inverse probability weights for marginal structural modeling in large observational datasets"],"prefix":"10.1002","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0127-0099","authenticated-orcid":false,"given":"Susan","family":"Gruber","sequence":"first","affiliation":[{"name":"Department of Epidemiology Harvard School of Public Health Boston MA U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roger W.","family":"Logan","sequence":"additional","affiliation":[{"name":"Department of Epidemiology Harvard School of Public Health Boston MA U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Inmaculada","family":"Jarr\u00edn","sequence":"additional","affiliation":[{"name":"National Center of Epidemiology Instituto de Salud Carlos III Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Susana","family":"Monge","sequence":"additional","affiliation":[{"name":"National Center of Epidemiology Instituto de Salud Carlos III Madrid Spain"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Miguel A.","family":"Hern\u00e1n","sequence":"additional","affiliation":[{"name":"Department of Epidemiology Harvard School of Public Health Boston MA U.S.A."},{"name":"Department of Biostatistics Harvard School of Public Health Boston MA U.S.A."},{"name":"Harvard\u2010MIT Division of Health Sciences and Technology Boston MA U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2014,10,15]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1097\/00001648-200009000-00012"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2013.01.016"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1515\/jci-2012-0003"},{"issue":"25","key":"e_1_2_8_5_1","first-page":"1","article-title":"Super learner","volume":"6","author":"Laan M","year":"2007","journal-title":"Statistical Applications in Genetics and Molecular Biology"},{"key":"e_1_2_8_6_1","unstructured":"PolleyE van derLaanM.Super learner in prediction Technical Report Division of Biostatistics University of CaliforniaBerkeley 2010."},{"key":"e_1_2_8_7_1","first-page":"23:31","article-title":"Spanish cohort of naive HIV\u2010infected patients (CoRIS): rationale, organization and initial results","volume":"25","author":"Caro\u2010Murillo AM","year":"2007","journal-title":"Enfermedades Infecciosas Y Microbiologia Clinica"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1097\/QAD.0b013e3283324283"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4780091214"},{"key":"e_1_2_8_10_1","first-page":"553","volume-title":"Advances in Longitudinal Data Analysis","author":"Robins JM","year":"2009"},{"key":"e_1_2_8_11_1","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1002\/sim.3782","article-title":"Improved propensity score weighting using machine learning","volume":"29","author":"Lee B","year":"2009","journal-title":"Statistics in Medicine"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1037\/1082-989X.9.4.403"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.2776"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1214\/09-SS054"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.594"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80023-1"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00117832"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21706-2"},{"key":"e_1_2_8_19_1","series-title":"The Wadsworth statistics\/probability series","volume-title":"Classification and Regression Trees","author":"Breiman L","year":"1984"},{"key":"e_1_2_8_20_1","volume-title":"Toolkit for Weighting and Analysis of Nonequivalent Groups: A Tutorial for the Twang Package","author":"Ridgeway G","year":"2013"},{"key":"e_1_2_8_21_1","volume-title":"Toolkit for Weighting and Analysis of Nonequivalent Groups: A Tutorial for the Twang SAS Macro","author":"McCaffrey D","year":"2014"},{"key":"e_1_2_8_22_1","series-title":"Springer Series in Statistics","volume-title":"The Elements of Statistical Learning","author":"Hastie T","year":"2002"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1524\/stnd.2006.24.3.351"},{"key":"e_1_2_8_24_1","volume-title":"R: A Language and Environment for Statistical Computing","author":"Development Core Team, R","year":"2012"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"PolleyE.SuperLearner: super learner prediction 2012. URLhttp:\/\/CRAN.R\u2010project.org\/package=SuperLearner R package version 2.0\u20109. [Accessed on 15 October 2013].","DOI":"10.32614\/CRAN.package.SuperLearner"},{"key":"e_1_2_8_26_1","unstructured":"ArlotS LerasleM.V\u2010fold cross\u2010validation and V\u2010fold penalization in least\u2010squares density estimation 2012. eprint arXiv:1210.5830."},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(03)13802-0"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(03)14570-9"},{"key":"e_1_2_8_29_1","unstructured":"van derLaanM DudoitS.Unified cross\u2010validation methodology for selection among estimators and a general cross\u2010validated adaptive epsilon\u2010net estimator: Finite sample oracle inequalities and examples Division of Biostatistics University of California Berkeley November2003."},{"key":"e_1_2_8_30_1","unstructured":"ImaiK RatkovicM.Robust estimation of inverse probability weights for marginal structural models Princeton University URLhttp:\/\/imai.princeton.edu\/research\/MSM.html[Accessed on 15 October 2013] May2013."},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2014.958155"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1541-0420.2012.01830.x"},{"issue":"1","key":"e_1_2_8_33_1","first-page":"1","article-title":"Collaborative double robust penalized targeted maximum likelihood estimation","volume":"6","author":"Laan M","year":"2010","journal-title":"The International Journal of Biostatistics"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.2202\/1557-4679.1182"}],"container-title":["Statistics in Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fsim.6322","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/sim.6322","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T04:31:58Z","timestamp":1746419518000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/sim.6322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,10,15]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,1,15]]}},"alternative-id":["10.1002\/sim.6322"],"URL":"https:\/\/doi.org\/10.1002\/sim.6322","archive":["Portico"],"relation":{},"ISSN":["0277-6715","1097-0258"],"issn-type":[{"value":"0277-6715","type":"print"},{"value":"1097-0258","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,10,15]]},"assertion":[{"value":"2014-12-10","name":"published_online","label":"Published Online","group":{"name":"publication_history","label":"Publication History"}}]}}