{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T03:17:29Z","timestamp":1789528649409,"version":"build-2803163510"},"reference-count":59,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"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":[[2026,5,9]]},"abstract":"<jats:title>SUMMARY<\/jats:title>\n                  <jats:p>This study considers the practically important case of nonparametrically estimating heterogeneous average treatment effects that vary with a limited number of discrete and continuous covariates in a selection-on-observables framework where the number of possible confounders is very large. We propose a two-step estimator for which the first step is estimated by machine learning. We show that this estimator has desirable statistical properties such as consistency, asymptotic normality, and rate double robustness. In particular, we derive the coupled convergence conditions between the nonparametric and the machine-learning steps. We also show that estimating population average treatment effects by averaging the estimated heterogeneous effects is semiparametrically efficient. The resulting estimators are compared to other suggestions in the literature in Monte Carlo experiments that are inspired by real data. They are found to perform relatively better in most settings. The new estimators are applied to the empirical example of the effects of mothers\u2019 smoking during pregnancy on the birthweight of their babies.<\/jats:p>","DOI":"10.1093\/ectj\/utaf026","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T12:31:45Z","timestamp":1764592305000},"page":"290-319","source":"Crossref","is-referenced-by-count":1,"title":["Nonparametric estimation of conditional average treatment effects under high-dimensional confounding"],"prefix":"10.1093","volume":"29","author":[{"given":"Michael","family":"Zimmert","sequence":"first","affiliation":[{"name":"Swiss National Bank , B\u00f6rsenstrasse 15, 8001 Z\u00fcrich , CH"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Lechner","sequence":"additional","affiliation":[{"name":"University of St. Gallen, Schweizerisches Institut f\u00fcr Empirische Wirtschaftsforschung , Rosenbergstrasse 22, 9000 St. Gallen , CH"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"2026050901264352900_bib1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/0034-6527.00321","article-title":"Semiparametric difference-in-differences estimators","volume":"72","author":"Abadie","year":"2005","journal-title":"Review of Economic Studies"},{"key":"2026050901264352900_bib2","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1002\/jae.851","article-title":"Estimating the effect of smoking on birth outcomes using a matched panel data approach","volume":"21","author":"Abrevaya","year":"2006","journal-title":"Journal of Applied Econometrics"},{"key":"2026050901264352900_bib3","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1080\/07350015.2014.975555","article-title":"Estimating conditional average treatment effects","volume":"33","author":"Abrevaya","year":"2015","journal-title":"Journal of Business and Economic Statistics"},{"key":"2026050901264352900_bib4","first-page":"1031","article-title":"The costs of low birth weight","volume":"120","author":"Almond","year":"2005","journal-title":"The Quarterly Journal of Economics"},{"issue":"2","key":"2026050901264352900_bib5","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1257\/jep.31.2.3","article-title":"The state of applied econometrics: causality and policy evaluation","volume":"31","author":"Athey","year":"2017","journal-title":"Journal of Economic Perspectives"},{"key":"2026050901264352900_bib6","first-page":"685","article-title":"Machine learning methods economists should know about","volume-title":"Annual Review of Economics","author":"Athey","year":"2019"},{"key":"2026050901264352900_bib7","doi-asserted-by":"crossref","first-page":"1148","DOI":"10.1214\/18-AOS1709","article-title":"Generalized random forests","volume":"47","author":"Athey","year":"2019","journal-title":"Annals of Statistics"},{"key":"2026050901264352900_bib8","doi-asserted-by":"crossref","first-page":"1430","DOI":"10.1111\/j.1468-0297.2010.02382.x","article-title":"A caseworker like me\u2013does the similarity between the unemployed and their caseworkers increase job placements?","volume":"120","author":"Behncke","year":"2010","journal-title":"The Economic Journal"},{"key":"2026050901264352900_bib9","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1111\/j.1467-985X.2009.00600.x","article-title":"Unemployed and their caseworkers: should they be friends or foes?","volume":"173","author":"Behncke","year":"2010","journal-title":"Journal of the Royal Statistical Society: Series A (Statistics in Society)"},{"key":"2026050901264352900_bib10","first-page":"521","article-title":"Least squares after model selection in high-dimensional sparse models","volume":"19","author":"Belloni","year":"2013","journal-title":"Bernouille"},{"key":"2026050901264352900_bib11","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1093\/restud\/rdt044","article-title":"Inference on treatment effects after selection among high-dimensional controls","volume":"81","author":"Belloni","year":"2014","journal-title":"Review of Economic Studies"},{"key":"2026050901264352900_bib12","volume-title":"Efficient and Adaptive Estimation for Semiparametric Models","author":"Bickel","year":"1993","edition":"(1 ed.)"},{"key":"2026050901264352900_bib13","first-page":"381","article-title":"Estimating integrated squared density derivatives: sharp best order of convergence estimates","author":"Bickel","year":"1988","journal-title":"Sankhy\u0101: The Indian Journal of Statistics, Series A"},{"key":"2026050901264352900_bib14","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1162\/REST_a_00431","article-title":"New evidence on the finite sample properties of propensity score reweighting and matching estimators","volume":"96","author":"Busso","year":"2014","journal-title":"Review of Economics and Statistics"},{"key":"2026050901264352900_bib15","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1016\/j.jeconom.2009.09.023","article-title":"Efficient semiparametric estimation of multi-valued treatment effects under ignorability","volume":"155","author":"Cattaneo","year":"2010","journal-title":"Journal of Econometrics"},{"key":"2026050901264352900_bib16","doi-asserted-by":"crossref","first-page":"C1","DOI":"10.1111\/ectj.12097","article-title":"Double\/debiased machine learning for treatment and structural parameters","volume":"21","author":"Chernozhukov","year":"2018","journal-title":"The Econometrics Journal"},{"key":"2026050901264352900_bib17","doi-asserted-by":"crossref","first-page":"1911","DOI":"10.3982\/ECTA14415","article-title":"The sorted effects method: discovering heterogeneous effects beyond their averages","volume":"86","author":"Chernozhukov","year":"2018","journal-title":"Econometrica"},{"key":"2026050901264352900_bib18","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1007\/s10995-007-0238-8","article-title":"Maternal smoking during pregnancy and birthweight: a propensity score matching approach","volume":"12","author":"da\u00a0Veiga","year":"2008","journal-title":"Maternal and Child Health Journal"},{"key":"2026050901264352900_bib19","first-page":"1","article-title":"Estimation of conditional average treatment effects with high-dimensional data","volume":"40","author":"Fan","year":"2020","journal-title":"Journal of Business & Economic Statistics"},{"key":"2026050901264352900_bib20","first-page":"181","article-title":"Deep neural networks for estimation and inference","volume-title":"Econometrica","author":"Farrell","year":"2021"},{"key":"2026050901264352900_bib21","first-page":"879","article-title":"Orthogonal statistical learning","volume-title":"The Annals of Statistics","author":"Foster","year":"2023"},{"key":"2026050901264352900_bib22","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1162\/003465304323023697","article-title":"Finite-sample properties of propensity-score matching and weighting estimators","volume":"86","author":"Fr\u00f6lich","year":"2004","journal-title":"Review of Economics and Statistics"},{"key":"2026050901264352900_bib23","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1081\/ETC-120039608","article-title":"A note on the role of the propensity score for estimating average treatment effects","volume":"23","author":"Fr\u00f6lich","year":"2004","journal-title":"Econometric Reviews"},{"key":"2026050901264352900_bib24","doi-asserted-by":"crossref","first-page":"315","DOI":"10.2307\/2998560","article-title":"On the role of the propensity score in efficient semiparametric estimation of average treatment effects","volume":"66","author":"Hahn","year":"1998","journal-title":"Econometrica"},{"key":"2026050901264352900_bib25","doi-asserted-by":"crossref","first-page":"315","DOI":"10.3982\/ECTA9609","article-title":"Asymptotic variance of semiparametric estimators with generated regressors","volume":"81","author":"Hahn","year":"2013","journal-title":"Econometrica"},{"key":"2026050901264352900_bib26","doi-asserted-by":"crossref","first-page":"784","DOI":"10.1162\/rest.89.4.784","article-title":"Nonparametric estimation of regression functions in the presence of irrelevant regressors","volume":"89","author":"Hall","year":"2007","journal-title":"Review of Economics and Statistics"},{"key":"2026050901264352900_bib27","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.1198\/016214504000000548","article-title":"Cross-validation and the estimation of conditional probability densities","volume":"99","author":"Hall","year":"2004","journal-title":"Journal of the American Statistical Association"},{"key":"2026050901264352900_bib28","doi-asserted-by":"crossref","first-page":"1161","DOI":"10.1111\/1468-0262.00442","article-title":"Efficient estimation of average treatment effects using the estimated propensity score","volume":"71","author":"Hirano","year":"2003","journal-title":"Econometrica"},{"key":"2026050901264352900_bib29","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1162\/REST_a_00632","article-title":"Why do tougher caseworkers increase employment? The role of program assignment as a causal mechanism","volume":"99","author":"Huber","year":"2017","journal-title":"Review of Economics and Statistics"},{"key":"2026050901264352900_bib30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jeconom.2012.11.006","article-title":"The performance of estimators based on the propensity score","volume":"175","author":"Huber","year":"2013","journal-title":"Journal of Econometrics"},{"key":"2026050901264352900_bib31","first-page":"3008","article-title":"Towards optimal doubly robust estimation of heterogeneous causal effects","volume-title":"Electronic Journal of Statistics","author":"Kennedy","year":"2023"},{"key":"2026050901264352900_bib32","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1111\/rssb.12212","article-title":"Non-parametric methods for doubly robust estimation of continuous treatment effects","volume":"79","author":"Kennedy","year":"2017","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2026050901264352900_bib33","first-page":"602","article-title":"Double machine learning based program evaluation under unconfoundedness","volume-title":"The Econometrics Journal","author":"Knaus","year":"2022"},{"key":"2026050901264352900_bib35","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1093\/ectj\/utaa014","article-title":"Machine learning estimation of heterogeneous causal effects: Empirical Monte Carlo evidence","volume":"24","author":"Knaus","year":"2021","journal-title":"The Econometrics Journal"},{"key":"2026050901264352900_bib34","doi-asserted-by":"crossref","first-page":"597","DOI":"10.3368\/jhr.57.2.0718-9615R1","article-title":"Heterogeneous employment effects of job search programmes: a machine learning approach","volume":"57","author":"Knaus","year":"2022","journal-title":"Journal of Human Resources"},{"key":"2026050901264352900_bib36","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.5242195","article-title":"Modified Causal Forests for estimating heterogeneous causal effects","volume-title":"arXiv preprint arXiv:1812.09487","author":"Lechner","year":"2018"},{"key":"2026050901264352900_bib37","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1002\/jae.2574","article-title":"Doubly robust uniform confidence band for the conditional average treatment effect function","volume":"32","author":"Lee","year":"2016","journal-title":"Journal of Applied Econometrics"},{"key":"2026050901264352900_bib38","volume-title":"Nonparametric Econometrics: Theory and Practice","author":"Li","year":"2007"},{"key":"2026050901264352900_bib39","doi-asserted-by":"crossref","first-page":"2937","DOI":"10.1002\/sim.1903","article-title":"Stratification and weighting via the propensity score in estimation of causal treatment effects: a comparative study","volume":"23","author":"Lunceford","year":"2004","journal-title":"Statistics in Medicine"},{"key":"2026050901264352900_bib40","first-page":"1","article-title":"High-dimensional L2-boosting: Rate of Convergence","volume-title":"Journal of Machine Learning Research","author":"Luo","year":"2025"},{"key":"2026050901264352900_bib41","doi-asserted-by":"crossref","first-page":"1132","DOI":"10.1214\/12-AOS995","article-title":"Nonparametric regression with nonparametrically generated covariates","volume":"40","author":"Mammen","year":"2012","journal-title":"Annals of Statistics"},{"key":"2026050901264352900_bib42","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1111\/j.1467-9892.1996.tb00294.x","article-title":"Multivariate local polynomial regression for time series: uniform strong consistency and rates","volume":"17","author":"Masry","year":"1996","journal-title":"Journal of Time Series Analysis"},{"key":"2026050901264352900_bib43","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.2307\/2951752","article-title":"The asymptotic variance of semiparametric estimators","volume":"62","author":"Newey","year":"1994","journal-title":"Econometrica"},{"key":"2026050901264352900_bib44","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1017\/S0266466600008409","article-title":"Kernel estimation of partial means and a general variance estimator","volume":"10","author":"Newey","year":"1994","journal-title":"Econometric Theory"},{"key":"2026050901264352900_bib45","first-page":"299","article-title":"Quasi-oracle estimation of heterogeneous treatment effects","volume-title":"Biometrika","author":"Nie","year":"2021"},{"key":"2026050901264352900_bib46","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511612503","volume-title":"Nonparametric Econometrics","author":"Pagan","year":"1999","edition":"(1 ed.)"},{"key":"2026050901264352900_bib47","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1214\/193940307000000527","article-title":"Higher order influence functions and minimax estimation of nonlinear functionals","volume-title":"Probability and Statistics: Essays in Honor of David A. Freedman","author":"Robins","year":"2008"},{"key":"2026050901264352900_bib48","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1080\/01621459.1994.10476818","article-title":"Estimation of regression coefficients when some regressors are not always observed","volume":"89","author":"Robins","year":"1994","journal-title":"Journal of the American Statistical Association"},{"key":"2026050901264352900_bib49","doi-asserted-by":"crossref","first-page":"931","DOI":"10.2307\/1912705","article-title":"Root-n-consistent semiparametric regression","volume":"56","author":"Robinson","year":"1988","journal-title":"Econometrica"},{"key":"2026050901264352900_bib50","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":"Biometrica"},{"key":"2026050901264352900_bib51","doi-asserted-by":"crossref","first-page":"4","DOI":"10.2202\/1557-4679.1052","article-title":"A doubly robust censoring unbiased transformation","volume":"3","author":"Rubin","year":"2007","journal-title":"International Journal of Biostatistics"},{"key":"2026050901264352900_bib52","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":"Journal of Educational Psychology"},{"key":"2026050901264352900_bib53","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1093\/ectj\/utaa027","article-title":"Debiased machine learning of conditional average treatment effects and other causal functions","volume":"24","author":"Semenova","year":"2021","journal-title":"The Econometrics Journal"},{"key":"2026050901264352900_bib54","unstructured":"StataCorp (2013). Excerpt from Cattaneo (2010) Journal of Econometrics 155: 138-154 (2013). Datasets for Stata Treatment-Effects Manual, Release 13. http:\/\/www.stata-press.com\/data\/r13\/cattaneo2.dta.Accessed October 3, 2025."},{"key":"2026050901264352900_bib55","article-title":"Unemployment insurance databases (AVAM, ASAL) and social security records (AHV)","author":"Swiss Administrative Data","year":"2003"},{"key":"2026050901264352900_bib56","volume-title":"Semiparametric Theory and Missing Data","author":"Tsiatis","year":"2006","edition":"(1 ed.)"},{"key":"2026050901264352900_bib57","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1080\/01621459.2017.1319839","article-title":"Estimation and inference of heterogeneous treatment effects using random forests","volume":"113","author":"Wager","year":"2018","journal-title":"Journal of the American Statistical Association"},{"key":"2026050901264352900_bib58","article-title":"Adaptive concentration of regression trees, with application to random forests","volume-title":"arXiv preprint arXiv:1503.06388","author":"Wager","year":"2015"},{"key":"2026050901264352900_bib59","doi-asserted-by":"crossref","first-page":"892","DOI":"10.1002\/j.2325-8012.2009.tb00936.x","article-title":"Teen smoking and birth outcomes","volume":"75","author":"Walker","year":"2009","journal-title":"Southern Economic Journal"}],"container-title":["Econometrics Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ectj\/advance-article-pdf\/doi\/10.1093\/ectj\/utaf026\/65671359\/utaf026.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ectj\/article-pdf\/29\/2\/290\/65671359\/utaf026.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ectj\/article-pdf\/29\/2\/290\/65671359\/utaf026.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T05:26:59Z","timestamp":1778304419000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ectj\/article\/29\/2\/290\/8362711"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":59,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,12,2]]},"published-print":{"date-parts":[[2026,5,9]]}},"URL":"https:\/\/doi.org\/10.1093\/ectj\/utaf026","relation":{},"ISSN":["1368-4221","1368-423X"],"issn-type":[{"value":"1368-4221","type":"print"},{"value":"1368-423X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2025,12,2]]}}}