{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:56:39Z","timestamp":1791392199062,"version":"4.3.3"},"reference-count":63,"publisher":"Institute of Mathematical Statistics","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Ann. Statist."],"published-print":{"date-parts":[[2025,12,1]]},"abstract":"<jats:p>Average treatment effects (ATEs) may be subject to selection bias when they are estimated among only a nonrepresentative subset of the target population. Selection bias can sometimes be eliminated by conditioning on a \u201csufficient adjustment set\u201d of covariates, even for some forms of missingness not at random (MNAR). Without requiring full specification of the causal structure, we consider sufficient adjustment sets to allow nonparametric identification of conditional ATEs in the target population. Covariates in the sufficient set may be collected among only the selected sample. We establish that if a sufficient set exists, then the set consisting of common causes of the outcome and selection, excluding the exposure and its descendants, also suffices. We establish simple graphical criteria for when a sufficient set will not exist, which could help indicate whether this is plausible for a given study. Simulations considering selection due to missing data indicated that sufficiently-adjusted complete-case analysis (CCA) can considerably outperform multiple imputation under MNAR and, if the sample size is not large, sometimes even under missingness at random. Analogous to the common-cause principle for confounding, these sufficiency results clarify when and how selection bias can be eliminated through covariate adjustment.<\/jats:p>","DOI":"10.1214\/24-aos2448","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T06:12:08Z","timestamp":1766470328000},"page":"2303-2328","source":"Crossref","is-referenced-by-count":4,"title":["A common-cause principle for eliminating selection bias in causal estimands through covariate adjustment"],"prefix":"10.1214","volume":"53","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6698-2607","authenticated-orcid":false,"given":"Maya B.","family":"Mathur","sequence":"first","affiliation":[{"name":"Quantitative Sciences Unit, Department of Biomedical Data Sciences, Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tyler J.","family":"VanderWeele","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, Harvard University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilya","family":"Shpitser","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"108","reference":[{"key":"50","unstructured":"<small>ROTNITZKY, A.<\/small> and <small>SMUCLER, E.<\/small> (2020). Efficient adjustment sets for population average causal treatment effect estimation in graphical models. <i>J. Mach. Learn. Res.<\/i> <b>21<\/b> Paper No. 188."},{"key":"25","doi-asserted-by":"crossref","unstructured":"<small>Laird, N. M.<\/small> (1988). Missing data in longitudinal studies. <i>Stat. Med.<\/i> <b>7<\/b> 305\u2013315.","DOI":"10.1002\/sim.4780070131"},{"key":"30","doi-asserted-by":"publisher","unstructured":"<small>Little, R. J. A.<\/small> and <small>Rubin, D. B.<\/small> (2002). <i>Statistical Analysis with Missing Data<\/i>, 2nd ed. <i>Wiley Series in Probability and Statistics<\/i>. Wiley, Hoboken, NJ.","DOI":"10.1002\/9781119013563"},{"key":"48","doi-asserted-by":"publisher","unstructured":"<small>Robins, J. M.<\/small>, <small>Rotnitzky, A.<\/small> and <small>Scharfstein, D. O.<\/small> (2000). Sensitivity analysis for selection bias and unmeasured confounding in missing data and causal inference models. In <i>Statistical Models in Epidemiology, the Environment, and Clinical Trials<\/i> (<i>Minneapolis, MN<\/i>, 1997). <i>IMA Vol. Math. Appl.<\/i> <b>116<\/b> 1\u201394. Springer, New York.","DOI":"10.1007\/978-1-4612-1284-3_1"},{"key":"41","doi-asserted-by":"publisher","unstructured":"<small>MOHAN, K.<\/small> and <small>PEARL, J.<\/small> (2021). Graphical models for processing missing data. <i>J. Amer. Statist. Assoc.<\/i> <b>116<\/b> 1023\u20131037.","DOI":"10.1080\/01621459.2021.1874961"},{"key":"9","doi-asserted-by":"crossref","unstructured":"<small>BUUREN, S. V.<\/small> and <small>GROOTHUIS-OUDSHOORN, K.<\/small> (2010). Mice: Multivariate imputation by chained equations in R. <i>J. Stat. Softw.<\/i> 1\u201368.","DOI":"10.18637\/jss.v045.i03"},{"key":"49","doi-asserted-by":"crossref","unstructured":"<small>ROBINS, J. M.<\/small>, <small>ROTNITZKY, A.<\/small> and <small>ZHAO, L. P.<\/small> (1995). Analysis of semiparametric regression models for repeated outcomes in the presence of missing data. <i>J. Amer. Statist. Assoc.<\/i> <b>90<\/b> 106\u2013121.","DOI":"10.1080\/01621459.1995.10476493"},{"key":"60","doi-asserted-by":"crossref","unstructured":"<small>VAN BUUREN, S.<\/small> (2018). <i>Flexible Imputation of Missing Data<\/i>. CRC Press, Boca Raton.","DOI":"10.1201\/9780429492259"},{"key":"59","doi-asserted-by":"publisher","unstructured":"<small>VANDERWEELE, T. J.<\/small> and <small>SHPITSER, I.<\/small> (2011). A new criterion for confounder selection. <i>Biometrics<\/i> <b>67<\/b> 1406\u20131413.","DOI":"10.1111\/j.1541-0420.2011.01619.x"},{"key":"51","doi-asserted-by":"publisher","unstructured":"<small>Rubin, D. B.<\/small> (1976). Inference and missing data. <i>Biometrika<\/i> <b>63<\/b> 581\u2013592.","DOI":"10.1093\/biomet\/63.3.581"},{"key":"45","doi-asserted-by":"publisher","unstructured":"<small>Pearl, J.<\/small> (2009). <i>Causality<\/i>: <i>Models, Reasoning, and Inference<\/i>, 2nd ed. Cambridge Univ. Press, Cambridge.","DOI":"10.1017\/CBO9780511803161"},{"key":"56","unstructured":"<small>VanderWeele, T.<\/small> (2015). <i>Explanation in Causal Inference<\/i>: <i>Methods for Mediation and Interaction<\/i>. Oxford Univ. Press, London."},{"key":"15","doi-asserted-by":"publisher","unstructured":"<small>DIDELEZ, V.<\/small>, <small>KREINER, S.<\/small> and <small>KEIDING, N.<\/small> (2010). Graphical models for inference under outcome-dependent sampling. <i>Statist. Sci.<\/i> <b>25<\/b> 368\u2013387.","DOI":"10.1214\/10-STS340"},{"key":"16","doi-asserted-by":"publisher","unstructured":"<small>GRAHAM, J. W.<\/small>, <small>OLCHOWSKI, A. E.<\/small> and <small>GILREATH, T. D.<\/small> (2007). How many imputations are really needed? Some practical clarifications of multiple imputation theory. <i>Prev. Sci.<\/i> <b>8<\/b> 206\u2013213.","DOI":"10.1007\/s11121-007-0070-9"},{"key":"61","doi-asserted-by":"publisher","unstructured":"<small>WHITE, I. R.<\/small> and <small>CARLIN, J. B.<\/small> (2010). Bias and efficiency of multiple imputation compared with complete-case analysis for missing covariate values. <i>Stat. Med.<\/i> <b>29<\/b> 2920\u20132931.","DOI":"10.1002\/sim.3944"},{"key":"29","unstructured":"<small>LITTLE, R. J.<\/small>, <small>D\u2019AGOSTINO, R.<\/small>, <small>COHEN, M. L.<\/small>, <small>DICKERSIN, K.<\/small>, <small>EMERSON, S. S.<\/small>, <small>FARRAR, J. T.<\/small>, <small>FRANGAKIS, C.<\/small>, <small>HOGAN, J. W.<\/small>, <small>MOLENBERGHS, G.<\/small> et al. (2012). The prevention and treatment of missing data in clinical trials. <i>N. Engl. J. Med.<\/i> <b>367<\/b> 1355\u20131360."},{"key":"1","doi-asserted-by":"crossref","unstructured":"<small>ALLISON, P. D.<\/small> (2000). Multiple imputation for missing data: A cautionary tale. <i>Sociol. Methods Res.<\/i> <b>28<\/b> 301\u2013309.","DOI":"10.1177\/0049124100028003003"},{"key":"2","doi-asserted-by":"crossref","unstructured":"<small>ANDRIDGE, R. R.<\/small> and <small>LITTLE, R. J.<\/small> (2010). A review of hot deck imputation for survey non-response. <i>Int. Stat. Rev.<\/i> <b>78<\/b> 40\u201364.","DOI":"10.1111\/j.1751-5823.2010.00103.x"},{"key":"3","doi-asserted-by":"crossref","unstructured":"<small>BANACK, H. R.<\/small> and <small>KAUFMAN, J. S.<\/small> (2014). The obesity paradox: Understanding the effect of obesity on mortality among individuals with cardiovascular disease. <i>Prev. Med.<\/i> <b>62<\/b> 96\u2013102.","DOI":"10.1016\/j.ypmed.2014.02.003"},{"key":"4","unstructured":"<small>BAREINBOIM, E.<\/small> and <small>PEARL, J.<\/small> (2012). Controlling selection bias in causal inference. In <i>Artificial Intelligence and Statistics<\/i> 100\u2013108. PMLR."},{"key":"5","doi-asserted-by":"crossref","unstructured":"<small>BAREINBOIM, E.<\/small> and <small>TIAN, J.<\/small> (2015). Recovering causal effects from selection bias. In <i>Proceedings of the AAAI Conference on Artificial Intelligence<\/i> <b>29<\/b>.","DOI":"10.1609\/aaai.v29i1.9679"},{"key":"6","doi-asserted-by":"crossref","unstructured":"<small>BAREINBOIM, E.<\/small>, <small>TIAN, J.<\/small> and <small>PEARL, J.<\/small> (2022). Recovering from selection bias in causal and statistical inference. In <i>Probabilistic and Causal Inference<\/i>: <i>The Works of Judea Pearl<\/i> 433\u2013450.","DOI":"10.1145\/3501714.3501740"},{"key":"7","doi-asserted-by":"crossref","unstructured":"<small>BARTLETT, J. W.<\/small>, <small>CARPENTER, J. R.<\/small>, <small>TILLING, K.<\/small> and <small>VANSTEELANDT, S.<\/small> (2014). Improving upon the efficiency of complete case analysis when covariates are MNAR. <i>Biostatistics<\/i> <b>15<\/b> 719\u2013730.","DOI":"10.1093\/biostatistics\/kxu023"},{"key":"8","doi-asserted-by":"crossref","unstructured":"<small>BARTLETT, J. W.<\/small>, <small>HAREL, O.<\/small> and <small>CARPENTER, J. R.<\/small> (2015). Asymptotically unbiased estimation of exposure odds ratios in complete records logistic regression. <i>Amer. J. Epidemiol.<\/i> <b>182<\/b> 730\u2013736.","DOI":"10.1093\/aje\/kwv114"},{"key":"10","doi-asserted-by":"publisher","unstructured":"<small>CARPENTER, J. R.<\/small> and <small>SMUK, M.<\/small> (2021). Missing data: A statistical framework for practice. <i>Biom. J.<\/i> <b>63<\/b> 915\u2013947.","DOI":"10.1002\/bimj.202000196"},{"key":"11","doi-asserted-by":"crossref","unstructured":"<small>CORREA, J.<\/small> and <small>BAREINBOIM, E.<\/small> (2017). Causal effect identification by adjustment under confounding and selection biases. In <i>Proceedings of the AAAI Conference on Artificial Intelligence<\/i> <b>31<\/b>.","DOI":"10.1609\/aaai.v31i1.11060"},{"key":"12","doi-asserted-by":"crossref","unstructured":"<small>CORREA, J.<\/small>, <small>TIAN, J.<\/small> and <small>BAREINBOIM, E.<\/small> (2018). Generalized adjustment under confounding and selection biases. In <i>Proceedings of the AAAI Conference on Artificial Intelligence<\/i> <b>32<\/b>.","DOI":"10.1609\/aaai.v32i1.12125"},{"key":"13","doi-asserted-by":"crossref","unstructured":"<small>CORREA, J. D.<\/small>, <small>TIAN, J.<\/small> and <small>BAREINBOIM, E.<\/small> (2019). Identification of causal effects in the presence of selection bias. In <i>Proceedings of the AAAI Conference on Artificial Intelligence<\/i> <b>33<\/b> 2744\u20132751.","DOI":"10.1609\/aaai.v33i01.33012744"},{"key":"14","doi-asserted-by":"publisher","unstructured":"<small>DANIEL, R. M.<\/small>, <small>KENWARD, M. G.<\/small>, <small>COUSENS, S. N.<\/small> and <small>DE STAVOLA, B. L.<\/small> (2012). Using causal diagrams to guide analysis in missing data problems. <i>Stat. Methods Med. Res.<\/i> <b>21<\/b> 243\u2013256.","DOI":"10.1177\/0962280210394469"},{"key":"17","doi-asserted-by":"crossref","unstructured":"<small>GREENLAND, S.<\/small>, <small>PEARL, J.<\/small> and <small>ROBINS, J. M.<\/small> (1999). Causal diagrams for epidemiologic research. <i>Epidemiology<\/i> <b>10<\/b> 37\u201348.","DOI":"10.1097\/00001648-199901000-00008"},{"key":"18","doi-asserted-by":"crossref","unstructured":"<small>HENCKEL, L.<\/small>, <small>PERKOVI\u0106, E.<\/small> and <small>MAATHUIS, M. H.<\/small> (2022). Graphical criteria for efficient total effect estimation via adjustment in causal linear models. <i>J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> <b>84<\/b> 579\u2013599.","DOI":"10.1111\/rssb.12451"},{"key":"19","doi-asserted-by":"crossref","unstructured":"<small>HERN\u00c1N, M. A.<\/small>, <small>HERN\u00c1NDEZ-D\u00cdAZ, S.<\/small> and <small>ROBINS, J. M.<\/small> (2004). A structural approach to selection bias. <i>Epidemiology<\/i> <b>15<\/b> 615\u2013625.","DOI":"10.1097\/01.ede.0000135174.63482.43"},{"key":"20","unstructured":"<small>HERN\u00c1N, M. A.<\/small> and <small>ROBINS, J. M.<\/small> (2020). <i>Causal Inference<\/i>: <i>What If<\/i>. CRC Press, CRC, Boca Raton, FL."},{"key":"21","unstructured":"<small>HOWARD, B. V.<\/small>, <small>ROMAN, M. J.<\/small>, <small>DEVEREUX, R. B.<\/small>, <small>FLEG, J. L.<\/small>, <small>GALLOWAY, J. M.<\/small>, <small>HENDERSON, J. A.<\/small>, <small>HOWARD, W. J.<\/small>, <small>LEE, E. T.<\/small>, <small>METE, M.<\/small> et al. (2008). Effect of lower targets for blood pressure and LDL cholesterol on atherosclerosis in diabetes: The SANDS randomized trial. <i>J. Amer. Med. Assoc.<\/i> <b>299<\/b> 1678\u20131689."},{"key":"22","doi-asserted-by":"crossref","unstructured":"<small>HUGHES, R. A.<\/small>, <small>HERON, J.<\/small>, <small>STERNE, J. A.<\/small> and <small>TILLING, K.<\/small> (2019). Accounting for missing data in statistical analyses: Multiple imputation is not always the answer. <i>Int. J. Epidemiol.<\/i> <b>48<\/b> 1294\u20131304.","DOI":"10.1093\/ije\/dyz032"},{"key":"23","unstructured":"<small>INTERNATIONAL COUNCIL FOR HARMONISATION OF TECHNICAL REQUIREMENTS FOR PHARMACEUTICALS IN HUMAN USE<\/small> (2019). Addendum on estimands and sensitivity analysis in clinical trials: to the guideline on statistical principles for clinical trials. <a href=\"https:\/\/database.ich.org\/sites\/default\/files\/E9-R1_Step4_Guideline_2019_1203.pdf\">https:\/\/database.ich.org\/sites\/default\/files\/E9-R1_Step4_Guideline_2019_1203.pdf<\/a>. Accessed 2023-09-28."},{"key":"24","doi-asserted-by":"crossref","unstructured":"<small>KENAH, E.<\/small> (2023). A potential outcomes approach to selection bias. <i>Epidemiology<\/i> <b>34<\/b> 865\u2013972.","DOI":"10.1097\/EDE.0000000000001660"},{"key":"26","unstructured":"<small>LASH, T. L.<\/small> (2021). Chapter 29, Bias analysis. In <i>Modern Epidemiology<\/i> 711\u2013748 4th ed. Wolters Kluwer, Philadelphia, PA."},{"key":"27","doi-asserted-by":"crossref","unstructured":"<small>LEE, K. J.<\/small> and <small>CARLIN, J. B.<\/small> (2012). Recovery of information from multiple imputation: A simulation study. <i>Emerg. Themes Epidemiol.<\/i> <b>9<\/b> 1\u201310.","DOI":"10.1186\/1742-7622-9-3"},{"key":"28","doi-asserted-by":"crossref","unstructured":"<small>LI, P.<\/small>, <small>STUART, E. A.<\/small> and <small>ALLISON, D. B.<\/small> (2015). Multiple imputation: A flexible tool for handling missing data. <i>J. Amer. Med. Assoc.<\/i> <b>314<\/b> 1966\u20131967.","DOI":"10.1001\/jama.2015.15281"},{"key":"31","doi-asserted-by":"crossref","unstructured":"<small>LU, H.<\/small>, <small>COLE, S. R.<\/small>, <small>HOWE, C. J.<\/small> and <small>WESTREICH, D.<\/small> (2022). Toward a clearer definition of selection bias when estimating causal effects. <i>Epidemiology<\/i> <b>33<\/b> 699\u2013706.","DOI":"10.1097\/EDE.0000000000001516"},{"key":"32","unstructured":"<small>MALINSKY, D.<\/small>, <small>SHPITSER, I.<\/small> and <small>RICHARDSON, T.<\/small> (2019). A potential outcomes calculus for identifying conditional path-specific effects. In <i>The<\/i> 22<i>nd International Conference on Artificial Intelligence and Statistics<\/i> 3080\u20133088. PMLR."},{"key":"33","doi-asserted-by":"crossref","unstructured":"<small>MARSHALL, A.<\/small>, <small>ALTMAN, D. G.<\/small>, <small>ROYSTON, P.<\/small> and <small>HOLDER, R. L.<\/small> (2010). Comparison of techniques for handling missing covariate data within prognostic modelling studies: A simulation study. <i>BMC Med. Res. Methodol.<\/i> <b>10<\/b> 1\u201316.","DOI":"10.1186\/1471-2288-10-7"},{"key":"34","doi-asserted-by":"crossref","unstructured":"<small>MATHUR, M. B.<\/small> (2023). The M-value: A simple sensitivity analysis for bias due to missing data in treatment effect estimates. <i>Amer. J. Epidemiol<\/i> <b>194<\/b> 612-620.","DOI":"10.1093\/aje\/kwac207"},{"key":"35","doi-asserted-by":"crossref","unstructured":"<small>MATHUR, M. B.<\/small>, <small>PEACOCK, J. R.<\/small>, <small>ROBINSON, T. N.<\/small> and <small>GARDNER, C. D.<\/small> (2021). Effectiveness of a theory-informed documentary to reduce consumption of meat and animal products: Three randomized controlled experiments. <i>Nutrients<\/i> <b>13<\/b> 4555.","DOI":"10.3390\/nu13124555"},{"key":"36","doi-asserted-by":"crossref","unstructured":"<small>MATHUR, M.B.<\/small> and <small>SHPITSER, I.<\/small> (2025). Imputation without nightMARs: Graphical criteria for valid imputation of missing data. Preprint. Available at <a href=\"https:\/\/osf.io\/preprints\/osf\/zqne9_v2\">https:\/\/osf.io\/preprints\/osf\/zqne9_v2<\/a>.","DOI":"10.31219\/osf.io\/zqne9_v2"},{"key":"37","doi-asserted-by":"crossref","unstructured":"<small>MATHUR, M. B.<\/small> and <small>SHPITSER, I.<\/small> (2025). Simple graphical criteria for selection bias in general-population and selected-sample treatment effects. <i>Amer. J. Epidemiol.<\/i> <b>194<\/b> 267\u2013277.","DOI":"10.1093\/aje\/kwae145"},{"key":"38","unstructured":"<small>MATHUR, M. B.<\/small>, <small>SHPITSER, I.<\/small>, and <small>VANDERWEELE, T. J.<\/small>, (2025). Resurrecting complete-case analysis: A defense. <i>Amer. J. Epidemiol.<\/i> To appear. Available at <a href=\"https:\/\/osf.io\/preprints\/osf\/f9jvz_v2\/\">https:\/\/osf.io\/preprints\/osf\/f9jvz_v2\/<\/a>."},{"key":"39","doi-asserted-by":"crossref","unstructured":"<small>MATHUR, M. B.<\/small>, <small>VANDERWEELE, T. J.<\/small> and <small>SHPITSER, I.<\/small> (2025). Supplement to \u201cA common-cause principle for eliminating selection bias in causal estimands through covariate adjustment.\u201d <a href=\"https:\/\/doi.org\/10.1214\/24-AOS2448SUPP\">https:\/\/doi.org\/10.1214\/24-AOS2448SUPP<\/a>","DOI":"10.1214\/24-AOS2448SUPP"},{"key":"40","doi-asserted-by":"publisher","unstructured":"<small>MEALLI, F.<\/small> and <small>RUBIN, D. B.<\/small> (2015). Clarifying missing at random and related definitions, and implications when coupled with exchangeability. <i>Biometrika<\/i> <b>102<\/b> 995\u20131000.","DOI":"10.1093\/biomet\/asv035"},{"key":"42","doi-asserted-by":"crossref","unstructured":"<small>MOLENBERGHS, G.<\/small> and <small>KENWARD, M.<\/small> (2007). <i>Missing Data in Clinical Studies<\/i>. Wiley, New York.","DOI":"10.1002\/9780470510445"},{"key":"43","doi-asserted-by":"crossref","unstructured":"<small>MOONS, K. G.<\/small>, <small>DONDERS, R. A.<\/small>, <small>STIJNEN, T.<\/small> and <small>HARRELL JR, F. E.<\/small> (2006). Using the outcome for imputation of missing predictor values was preferred. <i>J. Clin. Epidemiol.<\/i> <b>59<\/b> 1092\u20131101.","DOI":"10.1016\/j.jclinepi.2006.01.009"},{"key":"44","unstructured":"<small>NABI, R.<\/small>, <small>BHATTACHARYA, R.<\/small>, <small>SHPITSER, I.<\/small> and <small>ROBINS, J.<\/small> (2022). Causal and counterfactual views of missing data models. Preprint. Available at <a href=\"https:\/\/arxiv.org\/abs\/2210.05558\">https:\/\/arxiv.org\/abs\/2210.05558<\/a>."},{"key":"46","doi-asserted-by":"crossref","unstructured":"<small>PIGOTT, T. D.<\/small> (2001). A review of methods for missing data. <i>Educ. Res. Eval.<\/i> <b>7<\/b> 353\u2013383.","DOI":"10.1076\/edre.7.4.353.8937"},{"key":"47","unstructured":"<small>RICHARDSON, T. S.<\/small> and <small>ROBINS, J. M.<\/small> (2013). Single world intervention graphs (SWIGs): a unification of the counterfactual and graphical approaches to causality. Center for the Statistics and the Social Sciences, University of Washington Series. Working Paper 128."},{"key":"52","unstructured":"<small>RUBIN, D. B.<\/small> (2004). <i>Multiple Imputation for Nonresponse in Surveys<\/i>. <i>Wiley Classics Library<\/i>. Wiley, Hoboken, NJ."},{"key":"53","unstructured":"<small>SHPITSER, I.<\/small> and <small>PEARL, J.<\/small> (2006). Identification of joint interventional distributions in recursive semi-Markovian causal models. In <i>Proceedings of the National Conference on Artificial Intelligence<\/i> <b>21<\/b> 1219. MIT Press, Menlo Park, CA."},{"key":"54","doi-asserted-by":"crossref","unstructured":"<small>SMITH, L. H.<\/small> (2020). Selection mechanisms and their consequences: Understanding and addressing selection bias. <i>Curr. Epidemiol. Rep.<\/i> <b>7<\/b> 179\u2013189.","DOI":"10.1007\/s40471-020-00241-6"},{"key":"55","doi-asserted-by":"crossref","unstructured":"<small>SMITH, L. H.<\/small> and <small>VANDERWEELE, T. J.<\/small> (2019). Bounding bias due to selection. <i>Epidemiology<\/i> <b>30<\/b> 509.","DOI":"10.1097\/EDE.0000000000001032"},{"key":"57","doi-asserted-by":"crossref","unstructured":"<small>VANDERWEELE, T. J.<\/small> (2012). Confounding and effect modification: Distribution and measure. <i>Epidemiol. Methods<\/i> <b>1<\/b> 55\u201382.","DOI":"10.1515\/2161-962X.1004"},{"key":"58","unstructured":"<small>VANDERWEELE, T. J.<\/small>, <small>ROTHMAN, K. J.<\/small> and <small>LASH, T. L.<\/small> (2021). Chapter 12, confounding and confounders. In <i>Modern Epidemiology<\/i> 263\u2013286 4th ed. Wolters Kluwer, Philadelphia, PA."},{"key":"62","doi-asserted-by":"crossref","unstructured":"<small>WHITTEMORE, A. S.<\/small> (1978). Collapsibility of multidimensional contingency tables. <i>J. Roy. Statist. Soc. Ser. B, Methodol.<\/i> <b>40<\/b> 328\u2013340.","DOI":"10.1111\/j.2517-6161.1978.tb01046.x"},{"key":"63","doi-asserted-by":"publisher","unstructured":"<small>WOOLDRIDGE, J. M.<\/small> (2007). Inverse probability weighted estimation for general missing data problems. <i>J. Econometrics<\/i> <b>141<\/b> 1281\u20131301.","DOI":"10.1016\/j.jeconom.2007.02.002"}],"container-title":["The Annals of Statistics"],"original-title":[],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:22:36Z","timestamp":1791390156000},"score":1,"resource":{"primary":{"URL":"https:\/\/projecteuclid.org\/journals\/annals-of-statistics\/volume-53\/issue-6\/A-common-cause-principle-for-eliminating-selection-bias-in-causal\/10.1214\/24-AOS2448.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":63,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,12,1]]}},"URL":"https:\/\/doi.org\/10.1214\/24-aos2448","relation":{},"ISSN":["0090-5364","2168-8966"],"issn-type":[{"value":"0090-5364","type":"print"},{"value":"2168-8966","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,1]]}}}