{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T11:09:08Z","timestamp":1791976148648,"version":"4.4.0"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2019,11,12]],"date-time":"2019-11-12T00:00:00Z","timestamp":1573516800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SES 1357561"],"award-info":[{"award-number":["SES 1357561"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SES 1459931"],"award-info":[{"award-number":["SES 1459931"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5,1]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>Modern empirical work in regression discontinuity (RD) designs often employs local polynomial estimation and inference with a mean square error (MSE) optimal bandwidth choice. This bandwidth yields an MSE-optimal RD treatment effect estimator, but is by construction invalid for inference. Robust bias-corrected (RBC) inference methods are valid when using the MSE-optimal bandwidth, but we show that they yield suboptimal confidence intervals in terms of coverage error. We establish valid coverage error expansions for RBC confidence interval estimators and use these results to propose new inference-optimal bandwidth choices for forming these intervals. We find that the standard MSE-optimal bandwidth for the RD point estimator is too large when the goal is to construct RBC confidence intervals with the smaller coverage error rate. We further optimize the constant terms behind the coverage error to derive new optimal choices for the auxiliary bandwidth required for RBC inference. Our expansions also establish that RBC inference yields higher-order refinements (relative to traditional undersmoothing) in the context of RD designs. Our main results cover sharp and sharp kink RD designs under conditional heteroskedasticity, and we discuss extensions to fuzzy and other RD designs, clustered sampling, and pre-intervention covariates adjustments. The theoretical findings are illustrated with a Monte Carlo experiment and an empirical application, and the main methodological results are available in R and Stata packages.<\/jats:p>","DOI":"10.1093\/ectj\/utz022","type":"journal-article","created":{"date-parts":[[2019,11,13]],"date-time":"2019-11-13T16:34:40Z","timestamp":1573662880000},"page":"192-210","source":"Crossref","is-referenced-by-count":419,"title":["Optimal bandwidth choice for robust bias-corrected inference in regression discontinuity designs"],"prefix":"10.1093","volume":"23","author":[{"given":"Sebastian","family":"Calonico","sequence":"first","affiliation":[{"name":"Columbia University, Department of Health Policy and Management, 722 West 168th Street, Office R482 New York, NY 10032, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matias D","family":"Cattaneo","sequence":"additional","affiliation":[{"name":"Princeton University, Department of Operations Research and Financial Engineering, 98 Charlton St, Sherred Hall 227, Princeton NJ 08540, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Max H","family":"Farrell","sequence":"additional","affiliation":[{"name":"University of Chicago, Booth School of Business, 5807 South Woodlawn Ave, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2019,11,12]]},"reference":[{"key":"2021051409485623300_bib1","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1146\/annurev-economics-080217-053402","article-title":"Econometric methods for program evaluation","volume":"10","author":"Abadie","year":"2018","journal-title":"Annual Review of Economics"},{"key":"2021051409485623300_bib2","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.econlet.2016.01.024","article-title":"Optimal bandwidth selection for the fuzzy regression discontinuity estimator","volume":"141","author":"Arai","year":"2016","journal-title":"Economic Letters"},{"key":"2021051409485623300_bib3","doi-asserted-by":"crossref","first-page":"441","DOI":"10.3982\/QE590","article-title":"Simultaneous selection of optimal bandwidths for the sharp regression discontinuity estimator","volume":"9","author":"Arai","year":"2018","journal-title":"Quantitative Economics"},{"key":"2021051409485623300_bib4","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1108\/S0731-905320170000038017","article-title":"Regression discontinuity designs with clustered data","volume-title":"Regression Discontinuity Designs: Theory and Applications (Advances in Econometrics, Vol. 38)","author":"Bartalotti","year":"2017"},{"key":"2021051409485623300_bib5","doi-asserted-by":"crossref","first-page":"767","DOI":"10.1080\/01621459.2017.1285776","article-title":"On the effect of bias estimation on coverage accuracy in nonparametric inference","volume":"113","author":"Calonico","year":"2018","journal-title":"Journal of the American Statistical Association"},{"key":"2021051409485623300_bib6","article-title":"Coverage error optimal confidence intervals for local polynomial regression","author":"Calonico","year":"2019"},{"key":"2021051409485623300_bib7","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1177\/1536867X1701700208","article-title":"rdrobust: Software for regression discontinuity designs","volume":"17","author":"Calonico","year":"2017","journal-title":"Stata Journal"},{"key":"2021051409485623300_bib8","doi-asserted-by":"crossref","first-page":"442","DOI":"10.1162\/rest_a_00760","article-title":"Regression discontinuity designs using covariates","volume":"101","author":"Calonico","year":"2019","journal-title":"Review of Economics and Statistics"},{"key":"2021051409485623300_bib9","doi-asserted-by":"crossref","first-page":"2295","DOI":"10.3982\/ECTA11757","article-title":"Robust nonparametric confidence intervals for regression-discontinuity designs","volume":"82","author":"Calonico","year":"2014","journal-title":"Econometrica"},{"key":"2021051409485623300_bib10","doi-asserted-by":"crossref","first-page":"1753","DOI":"10.1080\/01621459.2015.1017578","article-title":"Optimal data-driven regression discontinuity plots","volume":"110","author":"Calonico","year":"2015","journal-title":"Journal of the American Statistical Association"},{"key":"2021051409485623300_bib11","doi-asserted-by":"crossref","first-page":"2453","DOI":"10.3982\/ECTA11224","article-title":"Inference on causal effects in a generalized regression kink design","volume":"83","author":"Card","year":"2015","journal-title":"Econometrica"},{"key":"2021051409485623300_bib12","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1108\/S0731-905320170000038016","article-title":"Regression kink design: Theory and practice","volume-title":"Regression Discontinuity Designs: Theory and Applications (Advances in Econometrics, Vol. 38)","author":"Card","year":"2017"},{"key":"2021051409485623300_bib13","doi-asserted-by":"crossref","DOI":"10.1108\/S0731-9053201738","volume-title":"Regression Discontinuity Designs: Theory and Applications (Advances in Econometrics, Vol. 38)","author":"Cattaneo","year":"2017"},{"key":"2021051409485623300_bib14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1515\/jci-2013-0010","article-title":"Randomization inference in the regression discontinuity design: An application to party advantages in the U.S. senate","volume":"3","author":"Cattaneo","year":"2015","journal-title":"Journal of Causal Inference"},{"key":"2021051409485623300_bib15","doi-asserted-by":"crossref","DOI":"10.1017\/9781108684606","article-title":"A Practical Introduction to Regression Discontinuity Designs: Foundations","volume-title":"Cambridge Elements: Quantitative and Computational Methods for Social Science","author":"Cattaneo","year":"2019"},{"key":"2021051409485623300_bib16","article-title":"A Practical Introduction to Regression Discontinuity Designs: Extensions","volume-title":"Cambridge Elements: Quantitative and Computational Methods for Social Science","author":"Cattaneo","year":"2020"},{"key":"2021051409485623300_bib17","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1086\/686802","article-title":"Interpreting regression discontinuity designs with multiple cutoffs","volume":"78","author":"Cattaneo","year":"2016","journal-title":"Journal of Politics"},{"key":"2021051409485623300_bib18","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1002\/pam.21985","article-title":"Comparing inference approaches for RD designs: A reexamination of the effect of head start on child mortality","volume":"36","author":"Cattaneo","year":"2017","journal-title":"Journal of Policy Analysis and Management"},{"key":"2021051409485623300_bib19","first-page":"134","article-title":"The choice of neighborhood in regression discontinuity designs","volume":"2","author":"Cattaneo","year":"2016","journal-title":"Observational Studies"},{"key":"2021051409485623300_bib20","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1108\/S0731-905320170000038013","article-title":"Testing stability of regression discontinuity models","volume-title":"Regression Discontinuity Designs: Theory and Applications (Advances in Econometrics, Vol. 38)","author":"Cerulli","year":"2017"},{"key":"2021051409485623300_bib21","doi-asserted-by":"crossref","first-page":"1691","DOI":"10.1214\/aos\/1031594737","article-title":"On automatic boundary corrections","volume":"25","author":"Cheng","year":"1997","journal-title":"Annals of Statistics"},{"key":"2021051409485623300_bib22","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/j.jeconom.2019.03.006","article-title":"Robust uniform inference for quantile treatment effects in regression discontinuity designs","volume":"211","author":"Chiang","year":"2019","journal-title":"Journal of Econometrics"},{"key":"2021051409485623300_bib23","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1080\/07350015.2017.1302880","article-title":"Regression discontinuity designs with sample selection","volume":"37","author":"Dong","year":"2019","journal-title":"Journal of Business and Economic Statistics"},{"key":"2021051409485623300_bib24","article-title":"Regression discontinuity designs with a continuous treatment","author":"Dong","year":"2019"},{"key":"2021051409485623300_bib25","doi-asserted-by":"crossref","first-page":"1081","DOI":"10.1162\/REST_a_00510","article-title":"Identifying the effect of changing the policy threshold in regression discontinuity models","volume":"97","author":"Dong","year":"2015","journal-title":"Review of Economics and Statistics"},{"key":"2021051409485623300_bib26","volume-title":"Local Polynomial Modelling and Its Applications","author":"Fan","year":"1996"},{"key":"2021051409485623300_bib27","doi-asserted-by":"crossref","first-page":"494","DOI":"10.1080\/01621459.2017.1328356","article-title":"A permutation test for the regression kink design","volume":"113","author":"Ganong","year":"2018","journal-title":"Journal of the American Statistical Association"},{"key":"2021051409485623300_bib28","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1080\/07350015.2017.1366909","article-title":"Why high-order polynomials should not be used in regression discontinuity designs","volume":"37","author":"Gelman","year":"2019","journal-title":"Journal of Business and Economic Statistics"},{"key":"2021051409485623300_bib29","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":"2021051409485623300_bib30","article-title":"Wild bootstrap for fuzzy regression discontinuity designs: Obtaining robust bias-corrected confidence intervals","author":"He","year":"2019","journal-title":"Working paper, Iowa State University"},{"key":"2021051409485623300_bib31","doi-asserted-by":"crossref","first-page":"1019","DOI":"10.3982\/QE864","article-title":"When does regression discontinuity design work? Evidence from random election outcomes","volume":"9","author":"Hyytinen","year":"2018","journal-title":"Quantitative Economics"},{"key":"2021051409485623300_bib32","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1016\/j.jeconom.2007.05.001","article-title":"Regression discontinuity designs: A guide to practice","volume":"142","author":"Imbens","year":"2008","journal-title":"Journal of Econometrics"},{"key":"2021051409485623300_bib33","doi-asserted-by":"crossref","first-page":"933","DOI":"10.1093\/restud\/rdr043","article-title":"Optimal bandwidth choice for the regression discontinuity estimator","volume":"79","author":"Imbens","year":"2012","journal-title":"Review of Economic Studies"},{"key":"2021051409485623300_bib34","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139025751","volume-title":"Causal Inference in Statistics, Social, and Biomedical Sciences","author":"Imbens","year":"2015"},{"key":"2021051409485623300_bib35","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1093\/pan\/mpu014","article-title":"Geographic boundaries as regression discontinuities","volume":"23","author":"Keele","year":"2015","journal-title":"Political Analysis"},{"key":"2021051409485623300_bib36","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1016\/j.jeconom.2007.05.003","article-title":"Regression discontinuity inference with specification error","volume":"142","author":"Lee","year":"2008","journal-title":"Journal of Econometrics"},{"key":"2021051409485623300_bib37","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1257\/jel.48.2.281","article-title":"Regression discontinuity designs in economics","volume":"48","author":"Lee","year":"2010","journal-title":"Journal of Economic Literature"},{"key":"2021051409485623300_bib38","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1162\/qjec.122.1.159","article-title":"Does Head Start improve children\u2019s life chances? Evidence from a regression discontinuity design","volume":"122","author":"Ludwig","year":"2007","journal-title":"Quarterly Journal of Economics"},{"key":"2021051409485623300_bib39","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1016\/j.jeconom.2010.12.008","article-title":"Extending the regression-discontinuity approach to multiple assignment variables","volume":"161","author":"Papay","year":"2011","journal-title":"Journal of Econometrics"},{"key":"2021051409485623300_bib40","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1108\/S0731-905320170000038001","article-title":"On interpreting the regression discontinuity design as a local experiment","volume-title":"Regression Discontinuity Designs: Theory and Applications (Advances in Econometrics, Vol. 38)","author":"Sekhon","year":"2017"},{"key":"2021051409485623300_bib41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jeconom.2017.07.004","article-title":"Regression discontinuity with categorical outcomes","volume":"201","author":"Xu","year":"2017","journal-title":"Journal of Econometrics"}],"container-title":["The Econometrics Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/ectj\/advance-article-pdf\/doi\/10.1093\/ectj\/utz022\/30700026\/utz022.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/ectj\/article-pdf\/23\/2\/192\/37933834\/utz022.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/ectj\/article-pdf\/23\/2\/192\/37933834\/utz022.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,14]],"date-time":"2021-05-14T05:49:35Z","timestamp":1620971375000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ectj\/article\/23\/2\/192\/5625071"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,11,12]]},"references-count":41,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2019,11,12]]},"published-print":{"date-parts":[[2020,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/ectj\/utz022","relation":{},"ISSN":["1368-4221","1368-423X"],"issn-type":[{"value":"1368-4221","type":"print"},{"value":"1368-423X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,5]]},"published":{"date-parts":[[2019,11,12]]}}}