Strategic Interaction and Interstate Crises: A Fixed-Effects Bayesian Quantal Response Estimator for Incomplete Information Games
Two strategies have been laid out by a growing literature on how to properly test the hypotheses implied by a theory of strategic interaction. The first strategy focuses on conventional comparative statics and the proper specification of standard statistical models (OLS, logit or probit). The second strategy requires deriving a novel likelihood function directly from the model or theory and estimating the parameters with maximum likelihood or Bayesian methods. Both approaches have largely limited their attention to games of perfect information, though many important phenomena are studied using games of incomplete information. This study develops a statistical model for incomplete information games that we term the Fixed Effects Bayesian Quantal Response Model. Our FE-BQRE model, which lies in the domain of the second strategy, offers three advantages over existing efforts: it directly incorporates (i) Bayesian updating and (ii) signaling dynamics, and (iii) it mimics the temporal learning process that we believe takes place in international politics.
Document ID Number