Empirical analyses of international relations data have become one of the principal methods by which researchers evaluate theories of trade, conflict, and other interactions among countries. Although the data used in these analyses are longitudinal and reflect network patterns, involving measured relations among nations over time, very seldom is the temporal nature of the data accounted for in these statistical modeling efforts, and even more frequently, the network effects are ignored. Furthermore, rarely is there any attempt to gauge the validity of the obtained model-fitting results by comparison to unfolding events, despite the fact that many of the core approaches in scientifically oriented studies of international politics spring from strong policy concerns. To address these issues, the project will develop and implement statistical models for relational data that take into account both (a) the evolution of international relations over time, and (b) the complex dependencies inherent to relational, social network data. This will be done by extending regression and latent factor models for network data to the time domain, allowing for the analysis of complicated longitudinal relational data using tools that are familiar to social science researchers.
Although networks are important in international affairs, network effects and their dynamics are often ignored. The methodology developed in this project will improve upon the standard methods for evaluating international relations by accounting for underlying network patterns as well as the dynamic character of the observed data. With such an approach, it will be possible to accurately identify and distinguish stable from dynamic network effects in international relations and thereby provide a more complete picture of the evolution of the political and economic relationships among nations. This award was supported as part of the fiscal year 2006 Mathematical Sciences priority area special competition on Mathematical Social and Behavioral Sciences (MSBS).
