What Are the Neighbors Doing?
Michael D. Ward, University of Washington, Seattle
Civil conflict and civil war are clustered in time and space. I explore new ways to model spatial dependencies in the context of the complexity of civil conflict. Using methods adapted from the social relations model, it is possible to represent social dependencies and clustering among states in a way that incorporates country level as well as dyadic covariates. This clustering can recapture the often-observed clustering of societies that is observed in many empirical data sets on civil war. I describe this approach in the framework of familiar regression models and explore implications for civil war studies of adopting this approach.