eduzhai > Applied Sciences > Computer Science >

Estimation of Large Network Formation Games

  • Peter
  • (0) Download
  • 20210217
  • Save

... pages left unread,continue reading

Document pages: 107 pages

Abstract: This paper develops estimation methods for network formation models usingobserved data from a single large network. The model allows for utilityexternalities from friends of friends and friends in common, so the expectedutility is nonlinear in the link choices of an agent. We propose a novel methodthat uses the Legendre transform to express the expected utility as a linearfunction of the individual link choices. This implies that the optimal linkdecision is that for an agent who myopically chooses to establish links or notto the other members of the network. The dependence between the agent s linkchoices is through an auxiliary variable. We propose a two-step estimationprocedure that requires weak assumptions on equilibrium selection, is simple tocompute, and has consistent and asymptotically normal estimators for theparameters. Monte Carlo results show that the estimation procedure performswell.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...