Summary: We introduce a new family of network models, called hierarchical network models, that allow us to represent in an explicit manner the stochastic dependence among the dyads (random ties) of the network. In particular, each member of this family can be associated with a graphical model defining conditional independence clauses among the dyads of the network, called the dependency graph. Every network model with dyadic independence assumption can be generalized to construct members of this new family. Using this new framework, we generalize the Erdös-Rényi and the \(\beta\) models to create hierarchical Erdös-Rényi and \(\beta\) models. We describe various methods for parameter estimation, as well as simulation studies for models with sparse dependency graphs.
{© 2019 The Authors. Statistica Neerlandica © 2019 VVS.}