A1712
Title: Optimal treatment assignment rules under capacity constraints
Authors: Keita Sunada - University of Rochester (United States) [presenting]
Kohei Izumi - University of Rochester (United States)
Abstract: Treatment assignment under supply constraints is studied when a planner aims to maximize social welfare by assigning treatments based on observable covariates. Such constraints are common when treatments are scarce and costly, but they complicate the analysis of optimal assignment rules because assignment probabilities must be coordinated across the entire covariate distribution. A new approach reformulates the planner's problem as an optimal transport problem, which makes the constraints analytically tractable. Using a limits of experiments framework, local asymptotic optimality results are established for two canonical decision rules: the plug-in rule and the Bayesian rule. The latter rule can dominate the former rule, with simulations demonstrating sizable risk reductions. An empirical illustration using school voucher program data demonstrates how the two rules differ in practice.
