Social interactions under incomplete information with heterogeneous expectations

We analyze social interactions where the conditional expectations about group members' behaviors are heterogeneous with individual features as well as asymmetric private information, under the framework of a simultaneous move game with incomplete information. A functional contraction mapping is used to establish the existence of a unique Bayesian Nash equilibrium. The method of nested fixed point maximum likelihood estimation performs well for both linear and binary choice models. If heterogeneity is assumed away, estimates will be biased. For the 2011 National Youth Tobacco Survey data, significant peer effects on juvenile tobacco use are found.