Network mechanisms and network models
Christoph Stadtfeld, Viviana Amati
Abstract
This chapter introduces the concept of network mechanisms and compares it to the notion of social mechanisms in Analytical Sociology. It discusses how statistical network models and empirically calibrated simulation models are applied to investigate network mechanisms. Different statistical network models are reviewed and compared, in particular conditional uniform graph (CUG) tests, quadratic assignment procedure (QAP) regressions, exponential random graph models (ERGMs), stochastic actor-oriented models (SAOMs) and relational event models (REM and DyNAM). The chapter further highlights that several of these models can be used as agent-based simulation frameworks to study micro-macro links in complex social systems.