EconBase
← All papers

Sharp Minimax Theory for Randomized Experiments

Timothy Sudijono, Edgar Dobriban, Eric Tchetgen Tchetgen

arXiv 13 Aug 2026 · Mathematics — Statistics Theory

arXiv:2608.13822 · PDF · Extracted main text

Abstract

We study minimax-optimal designs and estimators for estimating the sample average treatment effect in finite population randomized experiments, where both design and estimator are unrestricted. For binary potential outcomes, we show this minimax risk is equivalent to the minimax risk $ρ_n^*$ of an estimation problem with $2$ unknown parameters. We leverage this reduction to establish a second-order risk expansion $ρ_n^* = n^{-1} - Cn^{-4/3} + o_n(n^{-4/3})$ for an explicit constant $C$ related to the Airy function. The minimax risk is attained by Bernoulli randomization with a nonlinear shrinkage estimator. Our results show that standard procedures such as complete randomization with difference in means are only minimax optimal up to first order in $n.$ We derive further results on admissibility of these procedures and discuss the practical implications of our results.

Citation extraction

53
references
87
in-text mentions
53
distinct cited
0
self-citations
5,899
main-text words

appendix boundary found by appendix_command · 38% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Imbens, Guido W and Rubin, Donald B (2015) Causal inference in statistics, social, and biomedical sciences1.00053100%
2Ding, Peng (2024) A first course in causal inference0.84333100%
3Kallus, Nathan (2018) Optimal a priori balance in the design of controlled experiments0.8115280%
4Aronow, Peter M and Middleton, Joel A (2013) A class of unbiased estimators of the average treatment effect in randomized experiments0.81142100%
5Aronow, PM and Lopatto, Patrick (2026) Minimax unbiased estimation for finite populations with bounded outcomes0.73732100%
6Kandiros, Vardis and Harshaw, Christopher and Sävje, Fredrik (2026) A Design-Based Minimax Theory for Network Experiments0.69351100%
7Kallus, Nathan (2021) On the optimality of randomization in experimental design: How to randomize for minimax variance and design-based inference0.64441100%
8Bickel, Peter J (1981) Minimax estimation of the mean of a normal distribution when the parameter space is restricted0.64422100%
9Johnstone, Iain M and MacGibbon, K Brenda (1992) Minimax estimation of a constrained Poisson vector0.64422100%
10Levit, B Ya (1981) On asymptotic minimax estimates of the second order0.64422100%

Showing the top 10 of 53 scored citations.