Similarity Nash Equilibria in Statistical Games

• 成果类型: Article
• 署名作者: Argenziano, Rossella; Gilboa, Itzhak
• 署名单位: University of Essex; Hautes Etudes Commerciales (HEC) Paris; Tel Aviv University
• 刊物名称: AMERICAN ECONOMIC JOURNAL-MICROECONOMICS
• ISSN/ISSBN: 1945-7669
• DOI: 10.1257/mic.20220049
• 发表日期: 2023
• 页码: 354-386
• 关键词: context theory; CLASSIFICATION; RECOGNITION; MODEL

摘要

A statistical game is a game in which strategic interaction is mediated via a binary outcome y, coupled with a prediction problem where a characteristic x of the gamx, y). In Similarity Nash Equilibria, players combine statistical and strategic reasoning, using an estimate of y as a coordination device. They predict y by its similarity-weighted frequency and learn the optimal notion of similarity from the data. We prove that the model captures the importance of precedents and the endogenous formation of sunspots.