1 Spatializing the social networks of cross-boundary civil wars: An exponential random graph model of the First Congo War Steven M. Radil Assistant Professor, Department of Geography, University of Idaho sradil@uidaho.edu Abstract The need to understand how some wars diffuse, or expand over space and time, is a pressing one given the persistence of wars in the international system that involve non-state armed groups and spill beyond the boundaries of a single state. This chapter considers the issues connected with investigating war diffusion in such a context by using the ‘spatializing social networks’ or ‘SSN’ framework which uses the techniques of social network analysis to integrate geographic and political data into a single relational analysis. Although much of the SSN approach to date has been descriptive in nature, data from the First Congo War is used to develop a network-based statistical model called an exponential random graph network (or ERGM) to consider the geographical and political drivers to the war. Data about the participants along with their social and geographic relationships are used to illustrate the application of an ERGM. The results suggest that boundaries are the most salient feature to explain the early spread of the war but that the processes of war diffusion also involved whole-network level properties that cannot be captured by more traditional statistical methods but that can be modeled using an ERGM. This is an author’s copy of a manuscript that has been accepted for inclusion in a forthcoming book on transnational political organizations and boundaries in Africa to be published by Routledge. To cite, please contact the author at sradil@uidaho.edu.