Approximate Variational Inference for a Model of Social Interactions

18 Pages Posted: 7 Oct 2013

See all articles by Angelo Mele

Angelo Mele

Johns Hopkins University - Carey Business School

Date Written: October 1, 2013


This paper proposes approximate variational inference methods for estimation of a strategic model of social interactions. Players interact in an exogenous network and sequentially choose a binary action. The utility of an action is a function of the choices of neighbors in the network. I prove that the interaction process can be represented as a potential game and it converges to a unique stationary equilibrium distribution. However, exact inference for this model is infeasible because of a computationally intractable likelihood, which cannot be evaluated even when there are few players. To overcome this problem, I propose variational approximations for the likelihood that allow approximate inference. This technique can be applied to any discrete exponential family, and therefore it is a general tool for inference in models with a large number of players. The methodology is illustrated with several simulated datasets and compared with MCMC methods.

Keywords: Bayesian Methods, Microeconometrics

JEL Classification: D85, C13, C73

Suggested Citation

Mele, Angelo, Approximate Variational Inference for a Model of Social Interactions (October 1, 2013). NET Institute Working Paper No. 13-16, Available at SSRN: or

Angelo Mele (Contact Author)

Johns Hopkins University - Carey Business School ( email )

100 International Drive
Baltimore, MD 21202
United States


Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
PlumX Metrics