{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T20:24:35Z","timestamp":1778099075646,"version":"3.51.4"},"reference-count":44,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2017,1,24]],"date-time":"2017-01-24T00:00:00Z","timestamp":1485216000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Evaluation Clinical Practice"],"published-print":{"date-parts":[[2017,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Rationale, aims and objectives<\/jats:title><jats:p>When a randomized controlled trial is not feasible, health researchers typically use observational data and rely on statistical methods to adjust for confounding when estimating treatment effects. These methods generally fall into 3 categories: (1) estimators based on a model for the outcome using conventional regression adjustment; (2) weighted estimators based on the propensity score (ie, a model for the treatment assignment); and (3) \u201cdoubly robust\u201d (DR) estimators that model both the outcome and propensity score within the same framework. In this paper, we introduce a new DR estimator that utilizes marginal mean weighting through stratification (MMWS) as the basis for weighted adjustment. This estimator may prove more accurate than treatment effect estimators because MMWS has been shown to be more accurate than other models when the propensity score is misspecified. We therefore compare the performance of this new estimator to other commonly used treatment effects estimators.<\/jats:p><\/jats:sec><jats:sec><jats:title>Method<\/jats:title><jats:p>Monte Carlo simulation is used to compare the DR\u2010MMWS estimator to regression adjustment, 2 weighted estimators based on the propensity score and 2 other DR methods. To assess performance under varied conditions, we vary the level of misspecification of the propensity score model as well as misspecify the outcome model.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Overall, DR estimators generally outperform methods that model one or the other components (eg, propensity score or outcome). The DR\u2010MMWS estimator outperforms all other estimators when both the propensity score and outcome models are misspecified and performs equally as well as other DR estimators when only the propensity score is misspecified.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Health researchers should consider using DR\u2010MMWS as the principal evaluation strategy in observational studies, as this estimator appears to outperform other estimators in its class.<\/jats:p><\/jats:sec>","DOI":"10.1111\/jep.12714","type":"journal-article","created":{"date-parts":[[2017,1,24]],"date-time":"2017-01-24T06:43:10Z","timestamp":1485240190000},"page":"697-702","source":"Crossref","is-referenced-by-count":41,"title":["Improving causal inference with a doubly robust estimator that combines propensity score stratification and weighting"],"prefix":"10.1111","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0755-2313","authenticated-orcid":false,"given":"Ariel","family":"Linden","sequence":"first","affiliation":[{"name":"Linden Consulting Group, LLC  Ann Arbor MI USA"},{"name":"Division of General Medicine Medical School, University of Michigan  Ann Arbor MI USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2017,1,24]]},"reference":[{"key":"e_1_2_6_2_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1996.10476902"},{"key":"e_1_2_6_3_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2753.2006.00615.x"},{"key":"e_1_2_6_4_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/70.1.41"},{"key":"e_1_2_6_5_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1987.10478441"},{"key":"e_1_2_6_6_1","doi-asserted-by":"publisher","DOI":"10.1097\/00001648-200009000-00011"},{"key":"e_1_2_6_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2753.2009.01219.x"},{"key":"e_1_2_6_8_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2753.2009.01361.x"},{"key":"e_1_2_6_9_1","doi-asserted-by":"publisher","DOI":"10.1089\/dis.2004.7.180"},{"key":"e_1_2_6_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.5705"},{"key":"e_1_2_6_11_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1005285815569"},{"key":"e_1_2_6_12_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1999.10473862"},{"key":"e_1_2_6_13_1","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwj047"},{"key":"e_1_2_6_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/pds.969"},{"key":"e_1_2_6_15_1","unstructured":"RobinsJM.Robust estimation in sequentially ignorable missing data and causal inference models.Proceedings of the American Statistical Association Section on Bayesian Statistical Science1999; 6\u201310."},{"key":"e_1_2_6_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1994.10476818"},{"key":"e_1_2_6_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1541-0420.2005.00377.x"},{"key":"e_1_2_6_18_1","doi-asserted-by":"publisher","DOI":"10.3102\/1076998609359785"},{"key":"e_1_2_6_19_1","doi-asserted-by":"publisher","DOI":"10.1037\/a0024918"},{"key":"e_1_2_6_20_1","doi-asserted-by":"publisher","DOI":"10.1111\/jep.12254"},{"key":"e_1_2_6_21_1","doi-asserted-by":"publisher","DOI":"10.1111\/jep.12701"},{"key":"e_1_2_6_22_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1475-6773.2005.00352.x"},{"key":"e_1_2_6_23_1","doi-asserted-by":"publisher","DOI":"10.2307\/2528036"},{"key":"e_1_2_6_24_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1984.10478078"},{"key":"e_1_2_6_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jeconom.2007.02.002"},{"key":"e_1_2_6_26_1","volume-title":"Econometric Analysis of Cross Section and Panel Data","author":"Wooldridge JM","year":"2010"},{"key":"e_1_2_6_27_1","doi-asserted-by":"publisher","DOI":"10.2165\/00115677-200513030-00002"},{"key":"e_1_2_6_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.1903"},{"key":"e_1_2_6_29_1","unstructured":"LindenA.MMWS: stata module for implementing mean marginal weighting through stratification. Statistical Software Components s457886 Boston College Department of Economics 2014. Downloadable fromhttp:\/\/ideas.repec.org\/c\/boc\/bocode\/s457886.html[Accessed on December 28 2016]."},{"key":"e_1_2_6_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.3854"},{"key":"e_1_2_6_31_1","doi-asserted-by":"publisher","DOI":"10.1214\/07-STS227"},{"key":"e_1_2_6_32_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asq035"},{"key":"e_1_2_6_33_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6768"},{"key":"e_1_2_6_34_1","doi-asserted-by":"publisher","DOI":"10.1214\/07-STS227D"},{"key":"e_1_2_6_35_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2753.2005.00612.x"},{"key":"e_1_2_6_36_1","doi-asserted-by":"publisher","DOI":"10.1037\/1082-989X.9.4.403"},{"key":"e_1_2_6_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/pds.1555"},{"key":"e_1_2_6_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.3782"},{"key":"e_1_2_6_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2009.11.020"},{"key":"e_1_2_6_40_1","doi-asserted-by":"publisher","DOI":"10.1515\/ijb-2015-0028"},{"key":"e_1_2_6_41_1","doi-asserted-by":"publisher","DOI":"10.1111\/jep.12515"},{"key":"e_1_2_6_42_1","doi-asserted-by":"publisher","DOI":"10.1089\/dis.2004.7.275"},{"key":"e_1_2_6_43_1","doi-asserted-by":"publisher","DOI":"10.1089\/dis.2006.9.73"},{"key":"e_1_2_6_44_1","volume-title":"Data Mining: Practical Machine Learning Tools and Techniques","author":"Witten IH","year":"2011"},{"key":"e_1_2_6_45_1","first-page":"38","article-title":"The generalizability of disease management program results: getting from here to there","volume":"17","author":"Linden A","year":"2004","journal-title":"Manag Care Interface"}],"container-title":["Journal of Evaluation in Clinical Practice"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Fjep.12714","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jep.12714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T20:17:35Z","timestamp":1696277855000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/jep.12714"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,24]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,8]]}},"alternative-id":["10.1111\/jep.12714"],"URL":"https:\/\/doi.org\/10.1111\/jep.12714","archive":["Portico"],"relation":{},"ISSN":["1356-1294","1365-2753"],"issn-type":[{"value":"1356-1294","type":"print"},{"value":"1365-2753","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,1,24]]}}}