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 strategies via the requirements that categories contain a sufficient amount of observations and exhibit sufficient within-category similarity, in line with the bias-variance trade-off. We apply our framework to classic games including the chainstore game and adverse selection games, thereby suggesting novel predictions for these applications.