{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T22:54:15Z","timestamp":1791413655798,"version":"4.3.3"},"reference-count":53,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2017,7,31]],"date-time":"2017-07-31T00:00:00Z","timestamp":1501459200000},"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":[[2018,1,1]]},"abstract":"<jats:title>Summary<\/jats:title><jats:p>We develop a unified theory of designs for controlled experiments that balance baseline covariates a priori (before treatment and before randomization) using the framework of minimax variance and a new method called kernel allocation. We show that any notion of a priori balance must go hand in hand with a notion of structure, since with no structure on the dependence of outcomes on baseline covariates complete randomization (no special covariate balance) is always minimax optimal. Restricting the structure of dependence, either parametrically or non-parametrically, gives rise to certain covariate imbalance metrics and optimal designs. This recovers many popular imbalance metrics and designs previously developed ad hoc, including randomized block designs, pairwise-matched allocation and rerandomization. We develop a new design method called kernel allocation based on the optimal design when structure is expressed by using kernels, which can be parametric or non-parametric. Relying on modern optimization methods, kernel allocation, which ensures nearly perfect covariate balance without biasing estimates under model misspecification, offers sizable advantages in precision and power as demonstrated in a range of real and synthetic examples. We provide strong theoretical guarantees on variance, consistency and rates of convergence and develop special algorithms for design and hypothesis testing.<\/jats:p>","DOI":"10.1111\/rssb.12240","type":"journal-article","created":{"date-parts":[[2017,7,31]],"date-time":"2017-07-31T10:16:42Z","timestamp":1501496202000},"page":"85-112","source":"Crossref","is-referenced-by-count":49,"title":["Optimal<i>A Priori<\/i>Balance in the Design of Controlled Experiments"],"prefix":"10.1093","volume":"80","author":[{"given":"Nathan","family":"Kallus","sequence":"first","affiliation":[{"name":"Cornell University , New York , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2017,7,31]]},"reference":[{"key":"2023022005315002200_","doi-asserted-by":"crossref","DOI":"10.2991\/978-94-91216-83-1","volume-title":"An Introduction to Order Statistics","author":"Ahsanullah","year":"2013"},{"key":"2023022005315002200_","volume-title":"Essays in applied econometrics and education. PhD Thesis","author":"Barrios","year":"2014"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","DOI":"10.4135\/9781483348834","volume-title":"Regression Analysis: a Constructive Critique","author":"Berk","year":"2004"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-9096-9","volume-title":"Reproducing Kernel Hilbert Spaces in Probability and Statistics","author":"Berlinet","year":"2004"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"868","DOI":"10.1287\/opre.2015.1361","article-title":"The power of optimization over randomization in designing experiments involving small samples","volume":"63","author":"Bertsimas","year":"2015","journal-title":"Oper. Res."},{"key":"2023022005315002200_","volume-title":"Introduction to Linear Optimization","author":"Bertsimas","year":"1997"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1002\/rsa.20255","article-title":"Proof of the local REM conjecture for number partitioning: I, Constant energy scales","volume":"34","author":"Borgs","year":"2009","journal-title":"Rand. Struct. Algs"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1002\/rsa.20256","article-title":"Proof of the local REM conjecture for number partitioning: II, Growing energy scales","volume":"34","author":"Borgs","year":"2009","journal-title":"Rand. Struct. Algs"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511804441","volume-title":"Convex Optimization","author":"Boyd","year":"2004"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1093\/biomet\/55.2.365","article-title":"On the efficiency of matched pairs in bernoulli trials","volume":"55","author":"Chase","year":"1968","journal-title":"Biometrika"},{"key":"2023022005315002200_","volume-title":"Experimental Designs","author":"Cochran","year":"1957"},{"key":"2023022005315002200_","volume-title":"Planning of Experiments","author":"Cox","year":"1958"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"449","DOI":"10.4153\/CJM-1965-045-4","article-title":"Paths, trees, and flowers","volume":"17","author":"Edmonds","year":"1965","journal-title":"Can. J. Math."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1093\/biomet\/58.3.403","article-title":"Forcing a sequential experiment to be balanced","volume":"58","author":"Efron","year":"1971","journal-title":"Biometrika"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1214\/009053604000000067","article-title":"Least angle regression","volume":"32","author":"Efron","year":"2004","journal-title":"Ann. Statist."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4899-4541-9","volume-title":"An Introduction to the Bootstrap","author":"Efron","year":"1993"},{"key":"2023022005315002200_","volume-title":"The Design of Experiments","author":"Fisher","year":"1935"},{"key":"2023022005315002200_","volume-title":"Statistical Inference and Analysis: Selected Correspondence of R. A. Fisher","author":"Fisher","year":"1990"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1006\/aama.1996.0501","article-title":"From association to causation via regression","volume":"18","author":"Freedman","year":"1997","journal-title":"Adv. Appl. Math."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.aam.2006.12.003","article-title":"On regression adjustments to experimental data","volume":"40","author":"Freedman","year":"2008","journal-title":"Adv. Appl. Math."},{"key":"2023022005315002200_","volume-title":"Computers and Intractability","author":"Garey","year":"1979"},{"key":"2023022005315002200_","volume-title":"Permutation, Parametric and Bootstrap Tests of Hypotheses","author":"Good","year":"2005"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1093\/biostatistics\/5.2.263","article-title":"Optimal multivariate matching before randomization","volume":"5","author":"Greevy","year":"2004","journal-title":"Biostatistics"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1080\/10618600.1993.10474623","article-title":"Comparison of multivariate matching methods: structures, distances, and algorithms","volume":"2","author":"Gu","year":"1993","journal-title":"J. Computnl Graph. Statist."},{"key":"2023022005315002200_","volume-title":"Gurobi Optimizer Reference Manual","author":"Gurobi Optimization","year":"2015"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1111\/j.1751-5823.2007.00024.x","article-title":"Econometric causality","volume":"76","author":"Heckman","year":"2008","journal-title":"Int. Statist. Rev."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","DOI":"10.1142\/4319","volume-title":"Applied Analysis","author":"Hunter","year":"2001"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/0378-3758(90)90080-E","article-title":"Randomization in a bayesian perspective","volume":"25","author":"Kadane","year":"1990","journal-title":"J. Statist. Planng Inf."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1111\/biom.12148","article-title":"Matching on-the-fly: sequential allocation with higher power and efficiency","volume":"70","author":"Kapelner","year":"2014","journal-title":"Biometrics"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1214\/aoms\/1177697089","article-title":"A correspondence between bayesian estimation on stochastic processes and smoothing by splines","volume":"41","author":"Kimeldorf","year":"1970","journal-title":"Ann. Math. Statist."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1214\/aoms\/1177698877","article-title":"Series representations of distributions of quadratic forms in normal variables: I, central case","volume":"38","author":"Kotz","year":"1967","journal-title":"Ann. Math. Statist."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-20212-4","volume-title":"Probability in Banach Spaces: Isoperimetry and Processes","author":"Ledoux","year":"1991"},{"key":"2023022005315002200_","volume-title":"Theory of Point Estimation","author":"Lehmann","year":"1998"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1214\/12-AOAS583","article-title":"Agnostic notes on regression adjustments to experimental data: reexamining Freedmans critique","volume":"7","author":"Lin","year":"2013","journal-title":"Ann. Appl. Statist."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/S0024-3795(98)10032-0","article-title":"Applications of second-order cone programming","volume":"284","author":"Lobo","year":"1998","journal-title":"Lin. Alg. Appl."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"217","DOI":"10.2307\/2530821","article-title":"Post-stratification in the randomized clinical trial","volume":"39","author":"McHugh","year":"1983","journal-title":"Biometrics"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/S0304-3975(01)00153-0","article-title":"A physicist\u2019s approach to number partitioning","volume":"265","author":"Mertens","year":"2001","journal-title":"Theoret. Comput. Sci."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1214\/12-AOS1008","article-title":"Rerandomization to improve covariate balance in experiments","volume":"40","author":"Morgan","year":"2012","journal-title":"Ann. Statist."},{"key":"2023022005315002200_","volume-title":"MOSEK Fusion API for Python Manual, Version 7.0","author":"MOSEK","year":"2015"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"103","DOI":"10.2307\/2529712","article-title":"Sequential treatment assignment with balancing for prognostic factors in the controlled clinical trial","volume":"31","author":"Pocock","year":"1975","journal-title":"Biometrics"},{"key":"2023022005315002200_","volume-title":"Gaussian Processes for Machine Learning","author":"Rasmussen","year":"2006"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"2379","DOI":"10.1080\/03610929408831393","article-title":"Correcting for non-compliance in randomized trials using structural nested mean models","volume":"23","author":"Robins","year":"1994","journal-title":"Communs Statist. Theory Meth."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1007\/978-1-4419-9076-1_11","volume-title":"Proc. 2nd Seattle Symp. Biostatistics","author":"Robins","year":"2004"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1198\/016214506000001112","article-title":"Interference between units in randomized experiments","volume":"102","author":"Rosenbaum","year":"2007","journal-title":"J. Am. Statist. Ass."},{"key":"2023022005315002200_","volume-title":"Real Analysis","author":"Royden","year":"1988"},{"key":"2023022005315002200_","first-page":"961","article-title":"Which ifs have causal answers","volume":"81","author":"Rubin","year":"1986","journal-title":"J. Am. Statist. Ass."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1198\/016214508000001011","article-title":"The design and analysis of gold standard randomized experiments","volume":"103","author":"Rubin","year":"2008","journal-title":"J. Am. Statist. Ass."},{"key":"2023022005315002200_","first-page":"173","volume-title":"Studies in Subjective Probability","author":"Savage","year":"1964"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1002\/sim.4780130305","article-title":"Fisher\u2019s game with the devil","volume":"13","author":"Senn","year":"1994","journal-title":"Statist. Med."},{"key":"2023022005315002200_","first-page":"2389","article-title":"Universality, characteristic kernels and RKHS embedding of measures","volume":"12","author":"Sriperumbudur","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"4635","DOI":"10.1109\/TIT.2006.881713","article-title":"An explicit description of the reproducing kernel Hilbert spaces of Gaussian RBF kernels","volume":"52","author":"Steinwart","year":"2006","journal-title":"IEEE Trans. Inform. Theory"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"363","DOI":"10.2307\/2332011","article-title":"Comparison between balanced and random arrangements of field plots","volume":"29","author":"Student","year":"1938","journal-title":"Biometrika"},{"key":"2023022005315002200_","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1109\/4235.585893","article-title":"No free lunch theorems for optimization.","volume":"1","author":"Wolpert","year":"1997","journal-title":"IEEE Trans. Evoln. Computn"}],"container-title":["Journal of the Royal Statistical Society Series B: Statistical Methodology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Frssb.12240","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/80\/1\/85\/49271374\/jrsssb_80_1_85.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssb\/article-pdf\/80\/1\/85\/49271374\/jrsssb_80_1_85.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T18:56:47Z","timestamp":1750791407000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssb\/article\/80\/1\/85\/7048414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,7,31]]},"references-count":53,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2017,7,31]]},"published-print":{"date-parts":[[2018,1,1]]}},"URL":"https:\/\/doi.org\/10.1111\/rssb.12240","relation":{},"ISSN":["1369-7412","1467-9868"],"issn-type":[{"value":"1369-7412","type":"print"},{"value":"1467-9868","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,1]]},"published":{"date-parts":[[2017,7,31]]}}}