Premium
On the optimality of randomization in experimental design: How to randomize for minimax variance and design‐based inference
Author(s) -
Kallus Nathan
Publication year - 2021
Publication title -
journal of the royal statistical society: series b (statistical methodology)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 6.523
H-Index - 137
eISSN - 1467-9868
pISSN - 1369-7412
DOI - 10.1111/rssb.12412
Subject(s) - minimax , resampling , inference , permutation (music) , optimal design , mathematics , partition (number theory) , randomization , mathematical optimization , set (abstract data type) , computer science , algorithm , statistics , artificial intelligence , combinatorics , randomized controlled trial , medicine , physics , surgery , acoustics , programming language
I study the minimax‐optimal design for a two‐arm controlled experiment where conditional mean outcomes vary in a given set and the objective is effect‐estimation precision. When this set is permutation symmetric, the optimal design is shown to be complete randomization. Notably, even when the set has structure (i.e., is not permutation symmetric), being minimax‐optimal for precision still requires randomization beyond a single partition of units, that is, beyond randomizing the identity of treatment. A single partition is not optimal even when conditional means are linear. Since this only targets precision, it may nonetheless not ensure sufficient uniformity for design‐based (i.e., randomization) inference. I therefore propose the inference‐constrained mixed‐strategy optimal design as the minimax‐optimal for precision among designs subject to sufficient‐uniformity constraints.