Categorization in Games: A Bias-Variance Perspective - Paris-Jourdan Sciences Économiques Access content directly
Preprints, Working Papers, ... Year : 2023

Categorization in Games: A Bias-Variance Perspective


We develop a framework for categorization in games, applicable both to multistage games of complete information and static games of incomplete information. Players use categories to form coarse beliefs about their opponents' behavior. Players best-respond given these beliefs, as in analogy-based expectations equilibria. Categories are related to previously used strategies via the requirements that categories contain a sufficient amount of observations and exhibit sufficient withincategory similarity, in line with the bias-variance trade-off. When applied to classic games including the chainstore game and adverse selection games our framework yields less unintuitive predictions than those arising with standard solution concepts.
Fichier principal
Vignette du fichier
wp_202322_.pdf (659.45 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

halshs-04154272 , version 1 (06-07-2023)


  • HAL Id : halshs-04154272 , version 1


Philippe Jehiel, Erik Mohlin. Categorization in Games: A Bias-Variance Perspective. 2023. ⟨halshs-04154272⟩
18 View
11 Download


Gmail Facebook Twitter LinkedIn More