{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T18:24:08Z","timestamp":1790101448054,"version":"4.0.1"},"reference-count":60,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T00:00:00Z","timestamp":1664323200000},"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":[],"published-print":{"date-parts":[[2023,2,11]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>The design of any study, whether experimental or observational, that is intended to estimate the causal effects of a treatment condition relative to a control condition refers to those activities that precede any examination of outcome variables. As defined in our 1983 article (Rosenbaum &amp; Rubin, 1983), the propensity score is the unit-level conditional probability of assignment to treatment versus control given the observed covariates; so the propensity score explicitly does not involve any outcome variables, in contrast to other summaries of variables sometimes used in observational studies. Balancing the distributions of covariates in the treatment and control groups by matching or balancing on the propensity score is therefore an aspect of the design of the observational study. In this invited comment on our 1983 article, we review the situation in the early 1980s and recall some apparent paradoxes that propensity scores helped to resolve. We demonstrate that it is possible to balance an enormous number of low-dimensional summaries of a high-dimensional covariate, even though it is generally impossible to match individuals closely for all the components of a high-dimensional covariate. In a sense, there is only one crucial observed covariate, the propensity score, and there is one crucial unobserved covariate, the principal unobserved covariate. The propensity score and the principal unobserved covariate are equal when treatment assignment is strongly ignorable, that is, unconfounded. Controlling for observed covariates is a prelude to the crucial step from association to causation, the step that addresses potential biases from unmeasured covariates. The design of an observational study also prepares for the step to causation: by selecting comparisons to increase the design sensitivity, by seeking opportunities to detect bias, by seeking mutually supportive evidence affected by different biases, by incorporating quasi-experimental devices such as multiple control groups, and by including the economist\u2019s instruments. All of these considerations reflect the formal development of sensitivity analyses that were largely informal prior to the 1980s.<\/jats:p>","DOI":"10.1093\/biomet\/asac054","type":"journal-article","created":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T16:23:29Z","timestamp":1664209409000},"page":"1-13","source":"Crossref","is-referenced-by-count":65,"title":["Propensity scores in the design of observational studies for causal effects"],"prefix":"10.1093","volume":"110","author":[{"given":"P R","family":"Rosenbaum","sequence":"first","affiliation":[{"name":"University of Pennsylvania Department of Statistics and Data Science, The Wharton School, , Philadelphia, Pennsylvania 19104, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D B","family":"Rubin","sequence":"additional","affiliation":[{"name":"One Oxford Street, Cambridge Department of Statistics, Harvard University, , Massachusetts 02138, U.S.A"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2022,9,28]]},"reference":[{"key":"2023021111213812400_B1","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611970630","volume-title":"Some Limit Theorems in Statistics","author":"Bahadur,","year":"1971"},{"key":"2023021111213812400_B2","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1080\/24709360.2021.1913707","article-title":"The importance of having a conceptual stage when reporting non-randomized studies","volume":"5","author":"Bind,","year":"2021","journal-title":"Biostatist. Epidemiol."},{"key":"2023021111213812400_B3","doi-asserted-by":"crossref","first-page":"625","DOI":"10.2307\/1266635","article-title":"Use and abuse of regression","volume":"8","author":"Box,","year":"1966","journal-title":"Technometrics"},{"key":"2023021111213812400_B4","volume-title":"Methodology and Epistemology for Social Science: Selected Papers 1957\u20131986","author":"Campbell,","year":"1988"},{"key":"2023021111213812400_B5","doi-asserted-by":"crossref","DOI":"10.1017\/9781108684606","volume-title":"A Practical Introduction to Regression Discontinuity Designs","author":"Cattaneo,","year":"2019"},{"key":"2023021111213812400_B6","doi-asserted-by":"crossref","first-page":"121","DOI":"10.2307\/3348395","article-title":"Research techniques in the study of human beings","volume":"33","author":"Cochran,","year":"1955","journal-title":"Milbank Memorial Fund Quart."},{"key":"2023021111213812400_B7","doi-asserted-by":"crossref","first-page":"261","DOI":"10.2307\/2527916","article-title":"Analysis of covariance: Its nature and uses","volume":"13","author":"Cochran,","year":"1957","journal-title":"Biometrics"},{"key":"2023021111213812400_B8","doi-asserted-by":"crossref","first-page":"234","DOI":"10.2307\/2344179","article-title":"The planning of observational studies of human populations (with Discussion)","volume":"128","author":"Cochran,","year":"1965","journal-title":"J. R. Statist. Soc. A"},{"key":"2023021111213812400_B9","doi-asserted-by":"crossref","first-page":"295","DOI":"10.2307\/2528036","article-title":"The effectiveness of adjustment by subclassification in removing bias in observational studies","volume":"24","author":"Cochran,","year":"1968","journal-title":"Biometrics"},{"key":"2023021111213812400_B10","first-page":"417","article-title":"Controlling bias in observational studies: A review","volume":"35","author":"Cochran,","year":"1973","journal-title":"Sankhy\u0101 A"},{"key":"2023021111213812400_B11","doi-asserted-by":"crossref","first-page":"1175","DOI":"10.1093\/ije\/dyp289","article-title":"Smoking and lung cancer: Recent evidence and a discussion of some questions","volume":"38","author":"Cornfield,","year":"1959, 2009","journal-title":"Int. J. Epidemiol."},{"key":"2023021111213812400_B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1214\/07-AOAS113","article-title":"Applied statistics: A review","volume":"1","author":"Cox,","year":"2007","journal-title":"Ann. Appl. Statist."},{"key":"2023021111213812400_B13","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1093\/ije\/dyp290","article-title":"Commentary: Smoking and lung cancer: Reflections on a pioneering paper","volume":"38","author":"Cox,","year":"2009","journal-title":"Int. J. Epidemiol."},{"key":"2023021111213812400_B14","doi-asserted-by":"crossref","DOI":"10.1201\/9781420035834","volume-title":"The Theory of the Design of Experiments","author":"Cox,","year":"2000"},{"key":"2023021111213812400_B15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.2517-6161.1979.tb01052.x","article-title":"Conditional independence in statistical theory","volume":"41","author":"Dawid,","year":"1979","journal-title":"J. R. Statist. Soc. B"},{"key":"2023021111213812400_B16","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1080\/01621459.2017.1305275","article-title":"Quantitative evaluation of the trade-off of strengthened instruments and sample size in observational studies","volume":"113","author":"Ertefaie,","year":"2018","journal-title":"J. Am. Statist. Assoc."},{"key":"2023021111213812400_B17","volume-title":"Statistical Methods for Research Workers","author":"Fisher,","year":"1925"},{"key":"2023021111213812400_B18","volume-title":"Design of Experiments","author":"Fisher,","year":"1935"},{"key":"2023021111213812400_B19","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1080\/01621459.2015.1112802","article-title":"Discrete optimization for interpretable study populations and randomization inference in an observational study of severe sepsis mortality","volume":"111","author":"Fogarty,","year":"2016","journal-title":"J. Am. Statist. Assoc."},{"key":"2023021111213812400_B20","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":"2023021111213812400_B21","doi-asserted-by":"crossref","first-page":"1199","DOI":"10.1093\/ije\/dyp299","article-title":"Commentary: Cornfield, epidemiology and causality","volume":"38","author":"Greenhouse,","year":"2009","journal-title":"Int. J. Epidemiol."},{"key":"2023021111213812400_B22","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1111\/1468-0262.00183","article-title":"Identification and estimation of treatment effects with a regression-discontinuity design","volume":"69","author":"Hahn,","year":"2001","journal-title":"Econometrica"},{"key":"2023021111213812400_B23","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1111\/rssa.12559","article-title":"Finding the strength in a weak instrument in a study of cognitive outcomes produced by Catholic high schools","volume":"183","author":"Heng,","year":"2020","journal-title":"J. R. Statist. Soc."},{"key":"2023021111213812400_B24","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1080\/01621459.1963.10500830","article-title":"Probability inequalities for sums of bounded random variables","volume":"58","author":"Hoeffding,","year":"1963","journal-title":"J. Am. Statist. Assoc."},{"key":"2023021111213812400_B25","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1080\/00031305.1981.10479311","article-title":"The practice of statistics: The real world is an idea whose time has come","volume":"35","author":"Hunter,","year":"1981","journal-title":"Am. Statistician"},{"key":"2023021111213812400_B26","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139025751","volume-title":"Causal Inference in Statistics, Social, and Biomedical Sciences","author":"Imbens,","year":"2015"},{"key":"2023021111213812400_B27","doi-asserted-by":"crossref","first-page":"e124","DOI":"10.1371\/journal.pmed.0020124","article-title":"Why most published research findings are false","volume":"2","author":"Ioannidis,","year":"2005","journal-title":"PLoS Med."},{"key":"2023021111213812400_B28","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1093\/biomet\/asz003","article-title":"Integrating the evidence from evidence factors in observational studies","volume":"106","author":"Karmakar,","year":"2019","journal-title":"Biometrika"},{"key":"2023021111213812400_B29","volume-title":"Design and Analysis of Experiments","author":"Kempthorne,","year":"1952"},{"key":"2023021111213812400_B30","volume-title":"A System of Logic","author":"Mill,","year":"1872"},{"key":"2023021111213812400_B31","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1214\/12-AOS1008","article-title":"Rerandomization to improve covariate balance in experiments","volume":"40","author":"Morgan,","year":"2012","journal-title":"Ann. Statist."},{"key":"2023021111213812400_B32","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1080\/01621459.2014.997879","article-title":"Large, sparse optimal matching with refined covariate balance in an observational study of the health outcomes produced by new surgeons","volume":"110","author":"Pimentel,","year":"2015","journal-title":"J. Am. Statist. Assoc."},{"key":"2023021111213812400_B33","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1093\/biomet\/74.1.13","article-title":"Sensitivity analysis for certain permutation inferences in matched observational studies","volume":"74","author":"Rosenbaum,","year":"1987","journal-title":"Biometrika"},{"key":"2023021111213812400_B34","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3692-2","volume-title":"Observational Studies","author":"Rosenbaum,","year":"2002","edition":"2nd ed"},{"key":"2023021111213812400_B35","doi-asserted-by":"crossref","first-page":"153","DOI":"10.1093\/biomet\/91.1.153","article-title":"Design sensitivity in observational studies","volume":"91","author":"Rosenbaum,","year":"2004","journal-title":"Biometrika"},{"key":"2023021111213812400_B36","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1198\/000313005X42831","article-title":"Heterogeneity and causality: Unit heterogeneity and design sensitivity in observational studies","volume":"59","author":"Rosenbaum,","year":"2005","journal-title":"Am. Statistician"},{"key":"2023021111213812400_B37","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1080\/01621459.2014.960968","article-title":"Bahadur efficiency of sensitivity analyses in observational studies","volume":"110","author":"Rosenbaum,","year":"2015","journal-title":"J. Am. Statist. Assoc."},{"key":"2023021111213812400_B38","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1080\/01621459.2015.1054489","article-title":"Some counterclaims undermine themselves in observational studies","volume":"110","author":"Rosenbaum,","year":"2015","journal-title":"J. Am. Statist. Assoc."},{"key":"2023021111213812400_B39","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-46405-9","volume-title":"Design of Observational Studies","author":"Rosenbaum,","year":"2020","edition":"2nd ed"},{"key":"2023021111213812400_B40","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1146\/annurev-statistics-031219-041058","article-title":"Modern algorithms for matching in observational studies","volume":"7","author":"Rosenbaum,","year":"2020","journal-title":"Ann. Rev. Statist. Appl."},{"key":"2023021111213812400_B41","doi-asserted-by":"crossref","DOI":"10.1201\/9781003039648","volume-title":"Replication and Evidence Factors in Observational Studies","author":"Rosenbaum,","year":"2021"},{"key":"2023021111213812400_B42","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1093\/biomet\/70.1.41","article-title":"The central role of the propensity score in observational studies for causal effects","volume":"70","author":"Rosenbaum,","year":"1983","journal-title":"Biometrika"},{"key":"2023021111213812400_B43","doi-asserted-by":"crossref","first-page":"516","DOI":"10.1080\/01621459.1984.10478078","article-title":"Reducing bias in observational studies using subclassification on the propensity score","volume":"79","author":"Rosenbaum,","year":"1984","journal-title":"J. Am. Statist. Assoc."},{"key":"2023021111213812400_B44","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1080\/00031305.1985.10479383","article-title":"Constructing a control group using multivariate matched sampling methods that incorporate the propensity score","volume":"39","author":"Rosenbaum,","year":"1985","journal-title":"Am. Statistician"},{"key":"2023021111213812400_B45","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1037\/h0037350","article-title":"Estimating causal effects of treatments in randomized and nonrandomized studies","volume":"66","author":"Rubin,","year":"1974","journal-title":"J. Educ. Psychol."},{"key":"2023021111213812400_B46","doi-asserted-by":"crossref","first-page":"109","DOI":"10.2307\/2529342","article-title":"Multivariate matching methods that are equal percent bias reducing, I: Some examples","volume":"32","author":"Rubin,","year":"1976","journal-title":"Biometrics"},{"key":"2023021111213812400_B47","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3102\/10769986002001001","article-title":"Assignment to treatment group on the basis of a covariate","volume":"2","author":"Rubin,","year":"1977","journal-title":"J. Educ. Statist."},{"key":"2023021111213812400_B48","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1002\/sim.2739","article-title":"The design versus the analysis of observational studies for causal effects: Parallels with the design of randomized trials","volume":"26","author":"Rubin,","year":"2007","journal-title":"Statist. Med."},{"key":"2023021111213812400_B49","doi-asserted-by":"crossref","first-page":"808","DOI":"10.1214\/08-AOAS187","article-title":"For objective causal inference, design trumps analysis","volume":"2","author":"Rubin,","year":"2008","journal-title":"Ann. Appl. Statist."},{"key":"2023021111213812400_B50","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1097\/EDE.0b013e3182782468","article-title":"Should epidemiologists be more sensitive to design sensitivity?","volume":"24","author":"Stuart,","year":"2013","journal-title":"Epidemiol."},{"key":"2023021111213812400_B51","doi-asserted-by":"crossref","first-page":"279","DOI":"10.3102\/1076998607306078","article-title":"Matching with multiple control groups with adjustment for group differences","volume":"33","author":"Stuart,","year":"2008","journal-title":"J. Educ. Behav. Statist."},{"key":"2023021111213812400_B52","doi-asserted-by":"crossref","first-page":"155","DOI":"10.4135\/9781412995627.d14","article-title":"Best practices in quasi-experimental designs","volume-title":"Best Practices in Quantitative Methods","author":"Stuart,","year":"2008"},{"key":"2023021111213812400_B53","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1037\/h0044319","article-title":"Regression-discontinuity analysis","volume":"51","author":"Thistlethwaite,","year":"1960","journal-title":"J. Educ. Psychol."},{"key":"2023021111213812400_B54","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1080\/00031305.1980.10482706","article-title":"We need both exploratory and confirmatory","volume":"34","author":"Tukey,","year":"1980","journal-title":"Am. Statistician"},{"key":"2023021111213812400_B55","doi-asserted-by":"crossref","first-page":"72","DOI":"10.1080\/00031305.1986.10475361","article-title":"Sunset salvo","volume":"40","author":"Tukey,","year":"1986","journal-title":"Am. Statistician"},{"key":"2023021111213812400_B56","doi-asserted-by":"crossref","first-page":"1276","DOI":"10.1111\/biom.13374","article-title":"Evaluating and improving a matched comparison of antidepressants and bone density","volume":"77","author":"Yu,","year":"2021","journal-title":"Biometrics"},{"key":"2023021111213812400_B57","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1080\/01621459.2018.1429277","article-title":"On sensitivity value of pair-matched observational studies","volume":"114","author":"Zhao,","year":"2019","journal-title":"J. Am. Statist. Assoc."},{"key":"2023021111213812400_B58","doi-asserted-by":"crossref","first-page":"1360","DOI":"10.1080\/01621459.2012.703874","article-title":"Using mixed integer programming for matching in an observational study of kidney failure after surgery","volume":"107","author":"Zubizarreta,","year":"2012","journal-title":"J. Am. Statist. Assoc."},{"key":"2023021111213812400_B59","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1097\/EDE.0b013e318277367e","article-title":"Effect of the 2010 Chilean earthquake on posttraumatic stress: Reducing sensitivity to unmeasured bias through study design","volume":"24","author":"Zubizarreta,","year":"2013","journal-title":"Epidemiol."},{"key":"2023021111213812400_B60","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1214\/13-AOAS713","article-title":"Matching for balance, pairing for heterogeneity in an observational study of the effectiveness of for-profit and not-for-profit high schools in Chile","volume":"8","author":"Zubizarreta,","year":"2014","journal-title":"Ann. Appl. Statist."}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asac054\/47013579\/asac054.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/110\/1\/1\/49160167\/asac054.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/110\/1\/1\/49160167\/asac054.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,4]],"date-time":"2024-10-04T14:27:56Z","timestamp":1728052076000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/110\/1\/1\/6726181"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,28]]},"references-count":60,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2022,9,28]]},"published-print":{"date-parts":[[2023,2,11]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asac054","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,3,1]]},"published":{"date-parts":[[2022,9,28]]}}}