{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T07:20:53Z","timestamp":1791444053157,"version":"4.3.3"},"reference-count":47,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2020,4,15]],"date-time":"2020-04-15T00:00:00Z","timestamp":1586908800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Summary<\/jats:title><jats:p>We consider scenarios in which the likelihood function for a semiparametric regression model factors into separate components, with an efficient estimator of the regression parameter available for each component. An optimal weighted combination of the component estimators, named an ensemble estimator, may be employed as an overall estimate of the regression parameter, and may be fully efficient under uncorrelatedness conditions. This approach is useful when the full likelihood function may be difficult to maximize, but the components are easy to maximize. It covers settings where the nuisance parameter may be estimated at different rates in the component likelihoods. As a motivating example we consider proportional hazards regression with prospective doubly censored data, in which the likelihood factors into a current status data likelihood and a left-truncated right-censored data likelihood. Variable selection is important in such regression modelling, but the applicability of existing techniques is unclear in the ensemble approach. We propose ensemble variable selection using the least squares approximation technique on the unpenalized ensemble estimator, followed by ensemble re-estimation under the selected model. The resulting estimator has the oracle property such that the set of nonzero parameters is successfully recovered and the semiparametric efficiency bound is achieved for this parameter set. Simulations show that the proposed method performs well relative to alternative approaches. Analysis of an AIDS cohort study illustrates the practical utility of the method.<\/jats:p>","DOI":"10.1093\/biomet\/asaa012","type":"journal-article","created":{"date-parts":[[2020,2,25]],"date-time":"2020-02-25T20:15:09Z","timestamp":1582661709000},"source":"Crossref","is-referenced-by-count":1,"title":["Ensemble estimation and variable selection with semiparametric regression models"],"prefix":"10.1093","author":[{"given":"Sunyoung","family":"Shin","sequence":"first","affiliation":[{"name":"Department of Mathematical Sciences, University of Texas at Dallas, 800 W. Campbell Rd., Richardson, Texas 75080, U.S.A. sunyoung.shin@utdallas.edu"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufeng","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Statistics and Operations Research, CB# 3260, University of North Carolina, Chapel Hill, North Carolina 27599, U.S.A. yfliu@email.unc.edu"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen R","family":"Cole","sequence":"first","affiliation":[{"name":"Department of Epidemiology, CB# 7435, University of North Carolina, Chapel Hill, North Carolina 27599, U.S.A. cole@unc.edu"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason P","family":"Fine","sequence":"first","affiliation":[{"name":"Department of Biostatistics, CB# 7420, University of North Carolina, Chapel Hill, North Carolina 27599, U.S.A. jfine@email.unc.edu"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,4,15]]},"reference":[{"key":"2020050505375587200_B1","author":"Andersen,","year":"1997","journal-title":"Statistical Models Based on Counting Processes"},{"key":"2020050505375587200_B2","author":"Bickel,","journal-title":"Efficient and Adaptive Inference in Semiparametric Models"},{"key":"2020050505375587200_B3","doi-asserted-by":"crossref","DOI":"10.1002\/9780470743386","author":"Borenstein,","year":"2009","journal-title":"Introduction to Meta-Analysis"},{"key":"2020050505375587200_B4","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1093\/biomet\/92.2.303","article-title":"Variable selection for multivariate failure time data","volume":"92","author":"Cai,","year":"2005","journal-title":"Biometrika"},{"key":"2020050505375587200_B5","doi-asserted-by":"crossref","first-page":"907","DOI":"10.2105\/AJPH.91.6.907","article-title":"The continuing HIV epidemic among men who have sex with men","volume":"91","author":"Catania,","year":"2001","journal-title":"Am. J. Public Health."},{"key":"2020050505375587200_B6","doi-asserted-by":"crossref","first-page":"1536","DOI":"10.1214\/aos\/1176350608","article-title":"Strong consistency of a nonparametric estimator of the survival function with doubly censored data","volume":"15","author":"Chang,","year":"1987","journal-title":"Ann. Statist."},{"key":"2020050505375587200_B7","doi-asserted-by":"crossref","first-page":"2884","DOI":"10.1214\/10-AOS809","article-title":"Bootstrap consistency for general semiparametric M-estimation","volume":"38","author":"Cheng,","year":"2010","journal-title":"Ann. Statist."},{"key":"2020050505375587200_B8","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1111\/j.2517-6161.1972.tb00899.x","article-title":"Regression models and life tables (with discussion)","volume":"34","author":"Cox,","year":"1972","journal-title":"J. R. Statist. Soc."},{"key":"2020050505375587200_B9","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1214\/lnms\/1215090068","article-title":"Some remarks on likelihood factorization","author":"Cox,","year":"2001","journal-title":"State of the Art in Probability and Statistics: Festschrift for Willem R. van Zwet"},{"key":"2020050505375587200_B10","doi-asserted-by":"crossref","first-page":"2092","DOI":"10.1214\/09-AOS780","article-title":"Penalized variable selection procedure for Cox models with semiparametric relative risk","volume":"38","author":"Du,","year":"2010","journal-title":"Ann. Statist."},{"key":"2020050505375587200_B11","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1214\/009053604000000067","article-title":"Least angle regression","volume":"32","author":"Efron,","year":"2004","journal-title":"Ann. Statist."},{"key":"2020050505375587200_B12","doi-asserted-by":"crossref","first-page":"1525","DOI":"10.1097\/00002030-199908200-00013","article-title":"Gay men report high rates of unprotected anal sex with partners of unknown or discordant HIV status","volume":"13","author":"Ekstrand,","year":"1999","journal-title":"AIDS"},{"key":"2020050505375587200_B13","doi-asserted-by":"crossref","first-page":"1348","DOI":"10.1198\/016214501753382273","article-title":"Variable selection via nonconcave penalized likelihood and its oracle properties","volume":"96","author":"Fan,","year":"2001","journal-title":"J. Am. Statist. Assoc."},{"key":"2020050505375587200_B14","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1214\/aos\/1015362185","article-title":"Variable selection for Cox\u2019s proportional hazards model and frailty model","volume":"30","author":"Fan,","year":"2002","journal-title":"Ann. Statist."},{"key":"2020050505375587200_B15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-0348-8621-5","author":"Groeneboom,","year":"1992","journal-title":"Information Bounds and Nonparametric Maximum Likelihood Estimation"},{"key":"2020050505375587200_B16","doi-asserted-by":"crossref","first-page":"540","DOI":"10.1214\/aos\/1032894452","article-title":"Efficient estimation for the proportional hazards model with interval censoring","volume":"24","author":"Huang,","year":"1996","journal-title":"Ann. Statist."},{"key":"2020050505375587200_B17","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1093\/aje\/126.2.310","article-title":"The Multicenter AIDS Cohort Study: rationale, organization, and selected characteristics of the participants","volume":"126","author":"Kaslow,","year":"1987","journal-title":"Am. J. Epidemiol."},{"key":"2020050505375587200_B18","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1214\/lnms\/1196285392","article-title":"Combining correlated unbiased estimators of the mean of a normal distribution","author":"Keller,","year":"2004","journal-title":"A Festschrift for Herman Rubin"},{"key":"2020050505375587200_B19","doi-asserted-by":"crossref","first-page":"1339","DOI":"10.1016\/j.jmva.2010.01.010","article-title":"Asymptotic properties of the maximum likelihood estimator for the proportional hazards model with doubly censored data","volume":"101","author":"Kim,","year":"2010","journal-title":"J. Mult. Anal."},{"key":"2020050505375587200_B20","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.csda.2012.06.001","article-title":"An EM algorithm for the proportional hazards model with doubly censored data","volume":"57","author":"Kim,","year":"2013","journal-title":"Comp. Statist. Data Anal."},{"key":"2020050505375587200_B21","doi-asserted-by":"crossref","DOI":"10.1007\/b97377","author":"Klein,","year":"2003","journal-title":"Survival Analysis: Techniques for Censored and Truncated Data"},{"key":"2020050505375587200_B22","author":"Kosorok,","year":"2007","journal-title":"Introduction to Empirical Processes and Semiparametric Inference"},{"key":"2020050505375587200_B23","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1093\/biomet\/asz030","article-title":"Generalized meta-analysis for multiple regression models across studies with disparate covariate information","volume":"106","author":"Kundu,","year":"2019","journal-title":"Biometrika"},{"key":"2020050505375587200_B24","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1214\/aos\/1176348110","article-title":"Rank regression methods for left-truncated and right-censored data","volume":"19","author":"Lai,","year":"1991","journal-title":"Ann. Statist."},{"key":"2020050505375587200_B25","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1093\/biomet\/asq006","article-title":"On the relative efficiency of using summary statistics versus individual-level data in meta-analysis","volume":"97","author":"Lin,","year":"2010","journal-title":"Biometrika"},{"key":"2020050505375587200_B26","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1080\/01621459.2014.899235","article-title":"Multivariate meta-analysis of heterogeneous studies using only summary statistics: efficiency and robustness","volume":"110","author":"Liu,","year":"2015","journal-title":"J. Am. Statist. Assoc."},{"key":"2020050505375587200_B27","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1093\/biomet\/ast029","article-title":"Variable selection in semiparametric transformation models for right-censored data","volume":"100","author":"Liu,","year":"2013","journal-title":"Biometrika"},{"key":"2020050505375587200_B28","doi-asserted-by":"crossref","first-page":"717","DOI":"10.1093\/biomet\/ass027","article-title":"On the robustness of the adaptive lasso to model misspecification","volume":"99","author":"Lu,","year":"2012","journal-title":"Biometrika"},{"key":"2020050505375587200_B29","doi-asserted-by":"crossref","first-page":"381","DOI":"10.2307\/3318710","article-title":"Observed information in semiparametric models","volume":"5","author":"Murphy,","year":"1999","journal-title":"Bernoulli"},{"key":"2020050505375587200_B30","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1080\/01621459.2000.10474219","article-title":"On profile likelihood","volume":"95","author":"Murphy,","year":"2000","journal-title":"J. Am. Statist. Assoc."},{"key":"2020050505375587200_B31","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1002\/jae.3950050202","article-title":"Semiparametric efficiency bounds","volume":"5","author":"Newey,","year":"1990","journal-title":"J. Appl. Economet."},{"key":"2020050505375587200_B32","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1080\/10618600.1999.10474804","article-title":"Extending the iterative convex minorant algorithm to the Cox model for interval-censored data","volume":"8","author":"Pan,","year":"1999","journal-title":"J. Comp. Graph. Statist."},{"key":"2020050505375587200_B33","article-title":"R: A Language and Environment for Statistical Computing","year":"2020"},{"key":"2020050505375587200_B34","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.c221","article-title":"Meta-analysis of individual participant data: rationale, conduct, and reporting","volume":"340","author":"Riley,","year":"2010","journal-title":"Br. Med. J."},{"key":"2020050505375587200_B35","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1080\/01621459.2000.10474276","article-title":"Linear regression with current status data","volume":"95","author":"Shen,","year":"2000","journal-title":"J. Am. Statist. Assoc."},{"key":"2020050505375587200_B36","doi-asserted-by":"crossref","first-page":"1591","DOI":"10.1001\/archinternmed.2012.4508","article-title":"The influence of sex, race\/ethnicity, and educational attainment on human immunodeficiency virus death rates among adults, 1993\u20132007","volume":"172","author":"Simard,","year":"2012","journal-title":"Arch. Internal Med."},{"key":"2020050505375587200_B37","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1080\/24754269.2018.1530903","article-title":"Combining estimators of a common parameter across samples","volume":"2","author":"Slud,","year":"2018","journal-title":"Statist. Theory Rel. Fields"},{"key":"2020050505375587200_B38","doi-asserted-by":"crossref","first-page":"1298","DOI":"10.1214\/15-AOS1406","article-title":"Semiparametric efficient estimation for shared-frailty models with doubly-censored clustered data","volume":"44","author":"Su,","year":"2016","journal-title":"Ann. Statist."},{"key":"2020050505375587200_B39","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.1097\/QAD.0b013e32832baa34","article-title":"Estimating the proportion of HIV transmissions from main sex partners among men who have sex with men in five US cities","volume":"23","author":"Sullivan,","year":"2009","journal-title":"AIDS"},{"key":"2020050505375587200_B40","author":"Sun,","year":"2007","journal-title":"The Statistical Analysis of Interval-Censored Failure Time Data"},{"key":"2020050505375587200_B41","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","article-title":"Regression shrinkage and selection via the lasso","volume":"58","author":"Tibshirani,","year":"1996","journal-title":"J. R. Statist. Soc. B"},{"key":"2020050505375587200_B42","doi-asserted-by":"crossref","first-page":"385","DOI":"10.1002\/(SICI)1097-0258(19970228)16:4<385::AID-SIM380>3.0.CO;2-3","article-title":"The lasso method for variable selection in the Cox model","volume":"16","author":"Tibshirani,","year":"1997","journal-title":"Statist. Med."},{"key":"2020050505375587200_B43","author":"van der Vaart,","year":"2000","journal-title":"Asymptotic Statistics"},{"key":"2020050505375587200_B44","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1198\/016214507000000509","article-title":"Unified LASSO estimation by least squares approximation","volume":"102","author":"Wang,","year":"2007","journal-title":"J. Am. Statist. Assoc."},{"key":"2020050505375587200_B45","doi-asserted-by":"crossref","first-page":"507","DOI":"10.1111\/j.1369-7412.2007.00606.x","article-title":"Maximum likelihood estimation in semiparametric regression models with censored data (with discussion)","volume":"69","author":"Zeng,","year":"2007","journal-title":"J. R. Statist. Soc. B"},{"key":"2020050505375587200_B46","doi-asserted-by":"crossref","first-page":"3191","DOI":"10.1080\/03610926.2011.621578","article-title":"Efficient estimation for linear transformation models with current status data (with discussion)","volume":"42","author":"Zhang,","year":"2013","journal-title":"Commun. Statist. B"},{"key":"2020050505375587200_B47","doi-asserted-by":"crossref","first-page":"1418","DOI":"10.1198\/016214506000000735","article-title":"The adaptive lasso and its oracle properties","volume":"101","author":"Zou,","year":"2006","journal-title":"J. Am. Statist. Assoc."}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asaa012\/33166211\/asaa012.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asaa012\/33166211\/asaa012.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T03:19:14Z","timestamp":1722482354000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article\/doi\/10.1093\/biomet\/asaa012\/5820551"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,15]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1093\/biomet\/asaa012","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,4,15]]},"article-number":"asaa012"}}