A Decomposition Approach to Counterfactual Analysis in Game-Theoretic Models (2010.08868v7)

Abstract: Decomposition methods are often used for producing counterfactual predictions in non-strategic settings. When the outcome of interest arises from a game-theoretic setting where agents are better off by deviating from their strategies after a new policy, such predictions, despite their practical simplicity, are hard to justify. We present conditions in Bayesian games under which the decomposition-based predictions coincide with the equilibrium-based ones. In many games, such coincidence follows from an invariance condition for equilibrium selection rules. To illustrate our message, we revisit an empirical analysis in Ciliberto and Tamer (2009) on firms' entry decisions in the airline industry.