Optimal Decision Rules When Payoffs are Partially Identified

• 成果类型: Article; Early Access
• 署名作者: Christensen, Timothy; Moon, Hyungsik Roger; Schorfheide, Frank
• 署名单位: Yale University; University of Southern California; University of Pennsylvania
• 刊物名称: REVIEW OF ECONOMIC STUDIES
• ISSN/ISSBN: 0034-6527
• DOI: 10.1093/restud/rdag017
• 发表日期: 2026
• 关键词: regret treatment choice; instrumental variables; inference; utility; bounds; asymptotics; average; models

摘要

We derive asymptotically optimal statistical decision rules for discrete choice problems when payoffs depend on a partially-identified parameter theta and the decision maker can use a point-identified parameter mu to deduce restrictions on theta. Examples include treatment choice under partial identification and pricing with rich unobserved heterogeneity. Our notion of optimality combines a minimax approach to handle the ambiguity from partial identification of theta given mu with an average risk minimization approach for mu. We show how to implement optimal decision rules using the bootstrap and (quasi-)Bayesian methods in both parametric and semiparametric settings. We provide detailed applications to treatment choice and optimal pricing. Our asymptotic approach is well suited for realistic empirical settings in which the derivation of finite-sample optimal rules is intractable.