Tractability and Phase Transitions in Endogenous Network Formation

The dynamics of network formation are generally very complex, making the study of distributions over the space of networks often intractable. Under a condition called conservativeness, I show that the stationary distribution of a network formation process can be found in closed form, and is given by a Gibbs measure. For conservative processes, the stationary distribution of a certain class of models can be characterized for an arbitrarily large number of players. In this limit, the statistical properties of the model can exhibit phase transitions: discontinuous changes as a response to continuous changes in model parameters.