{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T18:04:04Z","timestamp":1792001044084,"version":"4.4.0"},"reference-count":38,"publisher":"The Econometric Society","issue":"4","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["QE"],"abstract":"<jats:p>We analyze the properties of the Synthetic Control (SC) and related estimators when the pre\u2010treatment fit is imperfect. In this framework, we show that these estimators are generally biased if treatment assignment is correlated with unobserved confounders, even when the number of pre\u2010treatment periods goes to infinity. Still, we show that a demeaned version of the SC method can improve in terms of bias and variance relative to the difference\u2010in\u2010difference estimator. We also derive a specification test for the demeaned SC estimator in this setting with imperfect pre\u2010treatment fit. Given our theoretical results, we provide practical guidance for applied researchers on how to justify the use of such estimators in empirical applications.<\/jats:p>","DOI":"10.3982\/qe1596","type":"journal-article","created":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T05:08:16Z","timestamp":1635484096000},"page":"1197-1221","source":"Crossref","is-referenced-by-count":160,"title":["Synthetic controls with imperfect pretreatment fit"],"prefix":"10.3982","volume":"12","author":[{"given":"Bruno","family":"Ferman","sequence":"first","affiliation":[{"name":"Sao Paulo School of Economics-FGV"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristine","family":"Pinto","sequence":"additional","affiliation":[{"name":"Sao Paulo School of Economics-FGV"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"2359","published-online":{"date-parts":[[2021]]},"reference":[{"key":"quan200157-bib-0001","doi-asserted-by":"crossref","unstructured":"Abadie, A. (2020), \u201cUsing synthetic controls: Feasibility, data requirements, and methodological aspects.\u201d Journal of Economic Literature.","DOI":"10.1257\/jel.20191450"},{"issue":"490","key":"quan200157-bib-0002","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1198\/jasa.2009.ap08746","volume":"105","author":"Abadie","year":"2010","journal-title":"Journal of the American Statiscal Association"},{"issue":"2","key":"quan200157-bib-0003","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1111\/ajps.12116","volume":"59","author":"Abadie","year":"2015","journal-title":"American Journal of Political Science"},{"issue":"1","key":"quan200157-bib-0004","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1257\/000282803321455188","volume":"93","author":"Abadie","year":"2003","journal-title":"American Economic Review"},{"issue":"1","key":"quan200157-bib-0005","first-page":"802","volume":"19","author":"Amjad","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"quan200157-bib-0006","series-title":"Wiley Series in Probability and Statistics\u2014Applied Probability and Statistics Section Series","volume-title":"An Introduction to Multivariate Statistical Analysis","author":"Anderson","year":"1984"},{"key":"quan200157-bib-0007","doi-asserted-by":"crossref","unstructured":"Arkhangelsky, D., S. Athey, D. A. Hirshberg, G. W. Imbens, and S. Wager (2018), \u201cSynthetic difference in differences.\u201d E-prints, December 2018, arXiv:1812.09970.","DOI":"10.3386\/w25532"},{"key":"quan200157-bib-0008","doi-asserted-by":"crossref","unstructured":"Athey, S., M. Bayati, N. Doudchenko, G. Imbens, and K. Khosravi (2018), \u201cMatrix completion methods for causal panel data models.\u201d Working Paper 25132, National Bureau of Economic Research.","DOI":"10.3386\/w25132"},{"key":"quan200157-bib-0009","doi-asserted-by":"crossref","unstructured":"Athey, S. and G. Imbens (2018), \u201cDesign-based analysis in difference-in-differences settings with staggered adoption.\u201d arXiv:1808.05293. Working Paper.","DOI":"10.3386\/w24963"},{"issue":"2","key":"quan200157-bib-0010","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1257\/jep.31.2.3","volume":"31","author":"Athey","year":"2017","journal-title":"Journal of Economic Perspectives"},{"issue":"1","key":"quan200157-bib-0011","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1111\/1468-0262.00392","volume":"71","author":"Bai","year":"2003","journal-title":"Econometrica"},{"issue":"4","key":"quan200157-bib-0012","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.3982\/ECTA6135","volume":"77","author":"Bai","year":"2009","journal-title":"Econometrica"},{"issue":"1","key":"quan200157-bib-0013","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1111\/1468-0262.00273","volume":"70","author":"Bai","year":"2002","journal-title":"Econometrica"},{"key":"quan200157-bib-0014","unstructured":"Ben-Michael, E., A. Feller, and J. Rothstein (2018), \u201cThe augmented synthetic control method.\u201d arXiv:1811.04170. Working Paper."},{"key":"quan200157-bib-0015","doi-asserted-by":"crossref","unstructured":"Botosaru, I. and B. Ferman (2019), \u201cOn the role of covariates in the synthetic control method.\u201d Econometrics Journal, 1.","DOI":"10.1093\/ectj\/utz001"},{"key":"quan200157-bib-0016","doi-asserted-by":"crossref","unstructured":"Callaway, B. and P. H. C. Sant'Anna (2018), \u201cDifference-in-differences with multiple time periods and an application on the minimum wage and employment.\u201d arXiv:1803.09015. Working Paper.","DOI":"10.2139\/ssrn.3148250"},{"key":"quan200157-bib-0017","unstructured":"Carvalho, C. V., R. Masini, and M. C. Medeiros (2018), \u201cArCo: An artificial counterfactual approach for aggregate data.\u201d Journal of Econometrics. (Forthcoming)."},{"key":"quan200157-bib-0018","doi-asserted-by":"crossref","unstructured":"Chernozhukov, V., K. Wuthrich, and Y. Zhu (2017), \u201cAn exact and robust conformal inference method for counterfactual and synthetic controls.\u201d E-prints, December 2017, arXiv:1712.09089.","DOI":"10.1920\/wp.cem.2017.6217"},{"key":"quan200157-bib-0019","doi-asserted-by":"crossref","unstructured":"Carvalho, C. V., R. Masini, and M. Cunha Medeiros (2016), \u201cThe perils of counterfactual analysis with integrated processes.\u201d Textos para discuss\u00e3o 654, PUC-Rio (Brazil), Department of Economics.","DOI":"10.2139\/ssrn.2894065"},{"issue":"9","key":"quan200157-bib-0020","doi-asserted-by":"crossref","first-page":"2964","DOI":"10.1257\/aer.20181169","volume":"110","author":"Chaisemartin","year":"2020","journal-title":"American Economic Review"},{"issue":"4","key":"quan200157-bib-0021","doi-asserted-by":"crossref","first-page":"1057","DOI":"10.2307\/1912517","volume":"49","author":"Dickey","year":"1981","journal-title":"Econometrica"},{"key":"quan200157-bib-0022","doi-asserted-by":"crossref","unstructured":"Doudchenko, N. and G. W. Imbens (2016), \u201cBalancing, regression, difference-in-differences and synthetic control methods: A synthesis.\u201d Working Paper 22791, National Bureau of Economic Research.","DOI":"10.3386\/w22791"},{"key":"quan200157-bib-0023","unstructured":"Ferman, B. (2019), \u201cOn the properties of the synthetic control estimator with many periods and many controls.\u201d E-prints, June 2019, arXiv:1906.06665."},{"key":"quan200157-bib-0024","unstructured":"Ferman, B. and C. Pinto (2019), \u201cSynthetic controls with imperfect pre-treatment fit.\u201d arXiv:1911.08521. version from November 19th, 2019."},{"key":"quan200157-bib-0025","doi-asserted-by":"crossref","unstructured":"Ferman, B., C. Pinto (2021), \u201cSupplement to \u2018Synthetic controls with imperfect pretreatment fit\u2019.\u201d Quantitative Economics Supplemental Material, 12, https:\/\/doi.org\/10.3982\/QE1596.","DOI":"10.3982\/QE1596"},{"issue":"2","key":"quan200157-bib-0026","doi-asserted-by":"crossref","first-page":"510","DOI":"10.1002\/pam.22206","volume":"39","author":"Ferman","year":"2020","journal-title":"Journal of Policy Analysis and Management"},{"issue":"3","key":"quan200157-bib-0027","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1162\/REST_a_00537","volume":"98","author":"Gobillon","year":"2016","journal-title":"The Review of Economics and Statistics"},{"key":"quan200157-bib-0028","doi-asserted-by":"crossref","unstructured":"Goodman-Bacon, A. (2018), \u201cDifference-in-differences with variation in treatment timing.\u201d Working Paper 25018, National Bureau of Economic Research.","DOI":"10.3386\/w25018"},{"issue":"5","key":"quan200157-bib-0029","doi-asserted-by":"crossref","first-page":"705","DOI":"10.1002\/jae.1230","volume":"27","author":"Hsiao","year":"2012","journal-title":"Journal of Applied Econometrics"},{"issue":"3","key":"quan200157-bib-0030","first-page":"1","volume":"26","author":"Hyndman","year":"2008","journal-title":"Journal of Statistical Software"},{"key":"quan200157-bib-0031","unstructured":"Kaul, A., S. Kl\u00f6bner, G. Pfeifer, and M. Schieler (2015), \u201cSynthetic control methods: Never use all pre-intervention outcomes as economic predictors.\u201d Available at www.oekonometrie.uni-saarland.de\/papers\/SCM_Predictors.pdf."},{"issue":"1","key":"quan200157-bib-0032","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.jeconom.2016.01.011","volume":"197","author":"Li","year":"2017","journal-title":"Journal of Econometrics"},{"key":"quan200157-bib-0033","doi-asserted-by":"crossref","unstructured":"Masini, R. and M. C. Medeiros (2019), \u201cCounterfactual analysis with artificial controls: Inference, high dimensions and nonstationarity.\u201d Available at SSRN https:\/\/ssrn.com\/abstract=3303308.","DOI":"10.2139\/ssrn.3303308"},{"issue":"4","key":"quan200157-bib-0034","doi-asserted-by":"crossref","first-page":"1543","DOI":"10.3982\/ECTA9382","volume":"83","author":"Moon","year":"2015","journal-title":"Econometrica"},{"issue":"6","key":"quan200157-bib-0035","doi-asserted-by":"crossref","first-page":"1519","DOI":"10.1111\/1468-0262.00256","volume":"69","author":"Ng","year":"2001","journal-title":"Econometrica"},{"key":"quan200157-bib-0036","doi-asserted-by":"crossref","unstructured":"Powell, D. (2018), \u201cImperfect synthetic controls: Did the Massachusetts health care reform save lives?\u201d Available at SSRN https:\/\/ssrn.com\/abstract=3192710.","DOI":"10.2139\/ssrn.3192710"},{"key":"quan200157-bib-0037","unstructured":"Ruggles, S., K. Genadek, R. Goeken, J. Grover, and M. Sobek (2015), \u201cIntegrated public use microdata series: Version 6.0 [Machine-readable database].\u201d"},{"issue":"2","key":"quan200157-bib-0038","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1017\/pan.2016.2","volume":"25","author":"Xu","year":"2017","journal-title":"Political Analysis"}],"container-title":["Quantitative Economics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.3982\/QE1596","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,29]],"date-time":"2021-10-29T05:10:54Z","timestamp":1635484254000},"score":1,"resource":{"primary":{"URL":"http:\/\/qeconomics.org\/ojs\/index.php\/qe\/article\/view\/QE1596"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":38,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021]]}},"alternative-id":["10.3982\/QE1596"],"URL":"https:\/\/doi.org\/10.3982\/qe1596","relation":{},"ISSN":["1759-7323"],"issn-type":[{"value":"1759-7323","type":"print"}],"subject":[],"published":{"date-parts":[[2021]]}}}