{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T07:22:08Z","timestamp":1772004128813,"version":"3.50.1"},"reference-count":48,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T00:00:00Z","timestamp":1683504000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,2,12]]},"abstract":"<jats:title>Summary<\/jats:title><jats:p>Evaluating the treatment effect has become an important topic for many applications. However, most existing literature focuses mainly on average treatment effects. When the individual effects are heavy tailed or have outlier values, not only may the average effect not be appropriate for summarizing treatment effects, but also the conventional inference for it can be sensitive and possibly invalid due to poor large-sample approximations. In this paper we focus on quantiles of individual treatment effects, which can be more robust in the presence of extreme individual effects. Moreover, our inference for them is purely randomization based, avoiding any distributional assumptions on the units. We first consider inference in stratified randomized experiments, extending the recent work by Caughey et\u00a0al. (2021). We show that the computation of valid p-values for testing null hypotheses on quantiles of individual effects can be transformed into instances of the multiple-choice knapsack problem, which can be efficiently solved exactly or slightly conservatively. We then extend our approach to matched observational studies and propose a sensitivity analysis to investigate to what extent our inference on quantiles of individual effects is robust to unmeasured confounding. The proposed randomization inference and sensitivity analysis are simul- taneously valid for all quantiles of individual effects, noting that the analysis for the maximum or minimum individual effect coincides with the conventional analysis assuming constant treatment effects.<\/jats:p>","DOI":"10.1093\/biomet\/asad030","type":"journal-article","created":{"date-parts":[[2023,5,8]],"date-time":"2023-05-08T13:52:11Z","timestamp":1683553931000},"page":"235-254","source":"Crossref","is-referenced-by-count":10,"title":["Treatment effect quantiles in stratified randomized experiments and matched observational studies"],"prefix":"10.1093","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3248-1024","authenticated-orcid":false,"given":"Yongchang","family":"Su","sequence":"first","affiliation":[{"name":"Department of Statistics, University of Illinois at Urbana-Champaign , 725 S. Wright Street, Champaign, Illinois 61820, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7375-7758","authenticated-orcid":false,"given":"Xinran","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Statistics, University of Illinois at Urbana-Champaign , 725 S. Wright Street, Champaign, Illinois 61820, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,5,8]]},"reference":[{"key":"2024021219285788400_asad030-B1","doi-asserted-by":"crossref","DOI":"10.2307\/j.ctvcm4j72","volume-title":"Mostly Harmless Econometrics","author":"Angrist","year":"2008"},{"key":"2024021219285788400_asad030-B2","volume-title":"Statistics for Experimenters: Design, Innovation, and Discovery","author":"Box","year":"2005"},{"key":"2024021219285788400_asad030-B3","author":"Caughey","year":"2021"},{"key":"2024021219285788400_asad030-B4","doi-asserted-by":"crossref","first-page":"189","DOI":"10.2307\/2531906","article-title":"Locally most powerful tests for detecting treatment effects when only a subset of patients can be expected to \u2018respond\u2019 to treatment","volume":"44","author":"Conover","year":"1988","journal-title":"Biometrics"},{"key":"2024021219285788400_asad030-B5","first-page":"173","article-title":"Smoking and lung cancer: recent evidence and a discussion of some questions","volume":"22","author":"Cornfield","year":"1959","journal-title":"J. Nat. Cancer Inst"},{"key":"2024021219285788400_asad030-B6","first-page":"49","article-title":"The role of significance tests","volume":"4","author":"Cox","year":"1977","journal-title":"Scand. J. Statist"},{"key":"2024021219285788400_asad030-B7","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1097\/EDE.0000000000000457","article-title":"Sensitivity analysis without assumptions","volume":"27","author":"Ding","year":"2016","journal-title":"Epidemiology"},{"key":"2024021219285788400_asad030-B8","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/0377-2217(87)90165-2","article-title":"Exact methods for the knapsack problem and its generalizations","volume":"28","author":"Dudzi\u0144ski","year":"1987","journal-title":"Eur. J. Oper. Res"},{"key":"2024021219285788400_asad030-B9","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/BF02591729","article-title":"An O(n) algorithm for the multiple-choice knapsack linear program","volume":"29","author":"Dyer","year":"1984","journal-title":"Math. Program"},{"key":"2024021219285788400_asad030-B10","doi-asserted-by":"crossref","first-page":"931","DOI":"10.1017\/S0266466609990168","article-title":"Sharp bounds on the distribution of treatment effects and their statistical inference","volume":"26","author":"Fan","year":"2010","journal-title":"Economet. Theory"},{"key":"2024021219285788400_asad030-B11","volume-title":"Design of Experiments","author":"Fisher","year":"1935"},{"key":"2024021219285788400_asad030-B12","doi-asserted-by":"crossref","first-page":"1518","DOI":"10.1080\/01621459.2019.1632072","article-title":"Studentized sensitivity analysis for the sample average treatment effect in paired observational studies","volume":"115","author":"Fogarty","year":"2020","journal-title":"J. Am. Statist. Assoc"},{"key":"2024021219285788400_asad030-B13","author":"Fogarty","year":"2020"},{"key":"2024021219285788400_asad030-B14","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1111\/1467-9868.00249","article-title":"Asymptotic separability in sensitivity analysis","volume":"62","author":"Gastwirth","year":"2000","journal-title":"J. R. Statist. Soc. B"},{"key":"2024021219285788400_asad030-B15","volume-title":"Statistical Modeling, Causal Inference, and Social Science","author":"Gelman","year":"2013"},{"key":"2024021219285788400_asad030-B16","author":"Gurobi Optimization, LLC","year":"2022"},{"key":"2024021219285788400_asad030-B17","volume-title":"Theory of Rank Tests","author":"Hajek","year":"1999","edition":"2nd ed"},{"key":"2024021219285788400_asad030-B18","volume-title":"Causal Inference: What If","author":"Hern\u00e1n","year":"2020"},{"key":"2024021219285788400_asad030-B19","first-page":"307","article-title":"Discussion of Paul Rosenbaum\u2019s \u2018Covariance adjustment in randomized experiments and observational studies\u2019","volume":"17","author":"Hill","year":"2002","journal-title":"Statist. Sci."},{"key":"2024021219285788400_asad030-B20","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1111\/biom.13101","article-title":"Constructing a confidence interval for the fraction who benefit from treatment, using randomized trial data","volume":"75","author":"Huang","year":"2019","journal-title":"Biometrics"},{"key":"2024021219285788400_asad030-B21","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139025751","volume-title":"Causal Inference in Statistics, Social, and Biomedical Sciences: An Introduction","author":"Imbens","year":"2015"},{"key":"2024021219285788400_asad030-B22","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1007\/978-3-540-24777-7_11","volume-title":"Knapsack Problems","author":"Kellerer","year":"2004"},{"key":"2024021219285788400_asad030-B23","volume-title":"Nonparametrics: Statistical Methods Based on Ranks","author":"Lehmann","year":"1975"},{"key":"2024021219285788400_asad030-B24","doi-asserted-by":"crossref","first-page":"957","DOI":"10.1002\/sim.6764","article-title":"Exact confidence intervals for the average causal effect on a binary outcome","volume":"35","author":"Li","year":"2016","journal-title":"Statist. Med"},{"key":"2024021219285788400_asad030-B25","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1214\/12-AOAS583","article-title":"Agnostic notes on regression adjustments to experimental data: reexamining Freedman\u2019s critique","volume":"7","author":"Lin","year":"2013","journal-title":"Ann. Appl. Statist"},{"key":"2024021219285788400_asad030-B26","doi-asserted-by":"crossref","first-page":"540","DOI":"10.3102\/1076998618776435","article-title":"Treatment effects on ordinal outcomes: causal estimands and sharp bounds","volume":"43","author":"Lu","year":"2018","journal-title":"J. Educ. Behav. Statist"},{"key":"2024021219285788400_asad030-B27","doi-asserted-by":"crossref","first-page":"664","DOI":"10.1111\/biom.13148","article-title":"Sharp bounds on the relative treatment effect for ordinal outcomes","volume":"76","author":"Lu","year":"2020","journal-title":"Biometrics"},{"key":"2024021219285788400_asad030-B28","first-page":"1","author":"Neyman","year":"1923"},{"key":"2024021219285788400_asad030-B29","author":"R Development Core Team","year":"2024"},{"key":"2024021219285788400_asad030-B30","doi-asserted-by":"crossref","first-page":"924","DOI":"10.1002\/sim.6384","article-title":"Randomization inference for treatment effects on a binary outcome","volume":"34","author":"Rigdon","year":"2015","journal-title":"Statist. Med"},{"key":"2024021219285788400_asad030-B31","doi-asserted-by":"crossref","first-page":"597","DOI":"10.1111\/j.2517-6161.1991.tb01848.x","article-title":"A characterization of optimal designs for observational studies","volume":"53","author":"Rosenbaum","year":"1991","journal-title":"J. R. Statist. Soc. B"},{"key":"2024021219285788400_asad030-B32","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1093\/biomet\/88.1.219","article-title":"Effects attributable to treatment: inference in experiments and observational studies within a discrete pivot","volume":"88","author":"Rosenbaum","year":"2001","journal-title":"Biometrika"},{"key":"2024021219285788400_asad030-B33","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1198\/016214502753479329","article-title":"Attributing effects to treatment in matched observational studies","volume":"97","author":"Rosenbaum","year":"2002","journal-title":"J. Am. Statist. Assoc"},{"key":"2024021219285788400_asad030-B34","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1214\/ss\/1042727942","article-title":"Covariance adjustment in randomized experiments and observational studies","volume":"17","author":"Rosenbaum","year":"2002","journal-title":"Statist. Sci."},{"key":"2024021219285788400_asad030-B35","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3692-2","volume-title":"Observational Studies","author":"Rosenbaum","year":"2002","edition":"2nd ed"},{"key":"2024021219285788400_asad030-B36","doi-asserted-by":"crossref","first-page":"1164","DOI":"10.1111\/j.1541-0420.2007.00783.x","article-title":"Confidence intervals for uncommon but dramatic responses to treatment","volume":"63","author":"Rosenbaum","year":"2007","journal-title":"Biometrics"},{"key":"2024021219285788400_asad030-B37","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-1213-8","volume-title":"Design of Observational Studies","author":"Rosenbaum","year":"2010"},{"key":"2024021219285788400_asad030-B38","doi-asserted-by":"crossref","first-page":"1017","DOI":"10.1111\/j.1541-0420.2010.01535.x","article-title":"A new u-statistic with superior design sensitivity in matched observational studies","volume":"67","author":"Rosenbaum","year":"2011","journal-title":"Biometrics"},{"key":"2024021219285788400_asad030-B39","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1080\/01621459.2013.879261","article-title":"Weighted m-statistics with superior design sensitivity in matched observational studies with multiple controls","volume":"109","author":"Rosenbaum","year":"2014","journal-title":"J. Am. Statist. Assoc"},{"key":"2024021219285788400_asad030-B40","doi-asserted-by":"crossref","DOI":"10.4159\/9780674982697","volume-title":"Observation and Experiment: An Introduction to Causal Inference","author":"Rosenbaum","year":"2017"},{"key":"2024021219285788400_asad030-B41","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":"2024021219285788400_asad030-B42","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":"2024021219285788400_asad030-B43","doi-asserted-by":"crossref","first-page":"1669","DOI":"10.1080\/03610928508829003","article-title":"Two sample nonparametric tests based on subsamples","volume":"14","author":"Stephenson","year":"1985","journal-title":"Commun. Statist. A"},{"key":"2024021219285788400_asad030-B44","first-page":"351","article-title":"On the combination of independent two sample tests of Wilcoxon","volume":"37","author":"Van Elteren","year":"1960","journal-title":"Bull. Inst. Int. Statist"},{"key":"2024021219285788400_asad030-B45","author":"Yu","year":"2020"},{"key":"2024021219285788400_asad030-B46","doi-asserted-by":"crossref","first-page":"1380","DOI":"10.1111\/biom.13098","article-title":"Directional penalties for optimal matching in observational studies","volume":"75","author":"Yu","year":"2019","journal-title":"Biometrics"},{"key":"2024021219285788400_asad030-B47","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/0020-0190(84)90014-0","article-title":"An O(n) algorithm for the linear multiple choice knapsack problem and related problems","volume":"18","author":"Zemel","year":"1984","journal-title":"Info. Process. Lett"},{"key":"2024021219285788400_asad030-B48","doi-asserted-by":"crossref","first-page":"735","DOI":"10.1111\/rssb.12327","article-title":"Sensitivity analysis for inverse probability weighting estimators via the percentile bootstrap","volume":"81","author":"Zhao","year":"2019","journal-title":"J. R. Statist. Soc. B"}],"container-title":["Biometrika"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biomet\/advance-article-pdf\/doi\/10.1093\/biomet\/asad030\/50795734\/asad030.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/111\/1\/235\/56665766\/asad030.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biomet\/article-pdf\/111\/1\/235\/56665766\/asad030.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:01:06Z","timestamp":1729382466000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biomet\/article\/111\/1\/235\/7156839"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,8]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,5,8]]},"published-print":{"date-parts":[[2024,2,12]]}},"URL":"https:\/\/doi.org\/10.1093\/biomet\/asad030","relation":{},"ISSN":["0006-3444","1464-3510"],"issn-type":[{"value":"0006-3444","type":"print"},{"value":"1464-3510","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,3,1]]},"published":{"date-parts":[[2023,5,8]]}}}