Adaptive Treatment Assignment in Experiments for Policy Choice

28 Pages Posted: 9 Aug 2019

See all articles by Maximilian Kasy

Maximilian Kasy

University of California, Berkeley

Anja Sautmann

Massachusetts Institute of Technology; Brown University - Department of Economics

Date Written: 2019


The goal of many experiments is to inform the choice between different policies. However, standard experimental designs are geared toward point estimation and hypothesis testing. We consider the problem of treatment assignment in an experiment with several non-overlapping waves, where the goal is to choose among a set of possible policies (treatments) for large-scale implementation. The optimal experimental design learns from earlier waves and assigns more experimental units to the better-performing treatments in later waves. We propose a computationally tractable approximation of the optimal design that we call "exploration sampling," where assignment probabilities are an increasing concave function of the posterior probabilities that each treatment is optimal. Theoretical results and calibrated simulations demonstrate improvements in welfare, relative to both non-adaptive designs as well as bandit algorithms. An application to selecting between different recruitment strategies for an agricultural extension service in Odisha, India demonstrates practical feasibility.

Keywords: experimental design, field experiments, optimal policy

Suggested Citation

Kasy, Maximilian and Sautmann, Anja, Adaptive Treatment Assignment in Experiments for Policy Choice (2019). CESifo Working Paper No. 7778, Available at SSRN: or

Maximilian Kasy (Contact Author)

University of California, Berkeley ( email )

310 Barrows Hall
Berkeley, CA 94720
United States

Anja Sautmann

Massachusetts Institute of Technology ( email )

77 Massachusetts Avenue
50 Memorial Drive
Cambridge, MA 02139-4307
United States

Brown University - Department of Economics ( email )

64 Waterman Street
Providence, RI 02912
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics