Small network data such as team, family, or personal networks, is common in many fields that study social networks. Although the analysis of small networks may appear simplistic relative to the difficulties posed by "big" datasets, there are at least two key challenges: (1) fitting statistical models to explain the network structure in small groups, and (2) testing if structural properties of small networks are associated with group-level outcomes; for example, team performance. In this presentation, we introduce two new statistical methods that use a revisited version of Exponential Random Graph Models (ERGMs) in the context of small networks. Using exhaustive enumeration of networks in the support, we are able to calculate exact likelihood functions for ERGMs, which allows us to obtain maximum likelihood estimates directly (without using simulations), avoiding common problems that arise from methods that rely on approximations instead.
As an invitation from Prof. Noshir Contractor, I gave this talk at Northwestern University’s SONIC Lab followed by a workshop on the tools that we have been developing for implemting the methods described in it. The lab was kind enough to record my talk as well as advertise it here
This is joint work with Prof. Kayla de la Haye (USC).