Multiple randomization designs: estimation and inference with interference

• 成果类型: Article
• 署名作者: Masoero, Lorenzo; Vijaykumar, Suhas; Richardson, Thomas S.; McQueen, James; Rosen, Ido; Burdick, Brian; Bajari, Pat; Imbens, Guido
• 署名单位: Amazon.com; University of Washington; University of Washington Seattle; Stanford University; Stanford University
• 刊物名称: JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-STATISTICAL METHODOLOGY
• ISSN/ISSBN: 1369-7412; 1467-9868
• DOI: 10.1093/jrsssb/qkaf073
• 发表日期: 2026-07
• 页码: 958-977
• 关键词: Experimental design; Marketplaces; randomization inference; spillovers; Causal Inference; units

摘要

Completely randomized experiments, originally developed by Fisher and Neyman in the 1930s, are still widely used in practice, even in online experimentation. However, such designs are of limited value for answering standard questions in marketplaces, where multiple populations of agents interact strategically, leading to complex patterns of spillover effects. In this article, we derive the finite-sample properties of tractable estimators for 'Simple Multiple Randomization Designs', a new class of experimental designs which account for complex spillover effects in randomized experiments. Our derivations are obtained under a natural and general form of cross-unit interference, which we call 'local interference'. We discuss the estimation of main effects, direct effects, and spillovers, and present associated central limit theorems.