Endogenous clustering and analogy-based expectation equilibrium

TL;DR

This paper introduces a novel equilibrium concept in two-player games where players group strategies into analogy classes to reduce prediction errors, leading to new insights on belief heterogeneity and multiple equilibria.

Contribution

It develops the Clustered Analogy-Based Expectation Equilibrium framework, distinguishing environments with self-repelling and self-attractive partitions, and explores their implications.

Findings

Environment-dependent analogy partitions influence equilibrium multiplicity.

Self-repelling partitions require mixing over classes.

Self-attractive partitions allow multiple equilibrium outcomes.

Abstract

Normal-form two-player games are categorized by players into K analogy classes so as to minimize the prediction error about the behavior of the opponent. This results in Clustered Analogy-Based Expectation Equilibria in which strategies are analogy-based expectation equilibria given the analogy partitions and analogy partitions minimize the prediction errors given the strategies. We distinguish between environments with self-repelling analogy partitions in which some mixing over partitions is required and environments with self-attractive partitions in which several analogy partitions can arise, thereby suggesting new channels of belief heterogeneity and equilibrium multiplicity. Various economic applications are discussed.