Improving Quantitative Studies of International Conflict: A Conjecture

Résumé 0

In this article, the authors address a well-known but infrequently discussed problem in the quantitative study of international conflict: despite immense data collections, prestigious journals, and sophisticated analyses, empirical findings in the literature on international conflict are often unsatisfying. Many statistical results change from article to article and specification to specification. Accurate forecasts are nonexistent. The authors offer a conjecture about one source of this problem: the causes of conflict, theorized to be important but often found to be small or ephemeral in prior research, are indeed tiny for the vast majority of dyads, but they are large, stable, and replicable wherever the ex ante probability of conflict is large. The authors provide a direct test of their conjecture by formulating a statistical model that includes its critical features. The approach, a version of a "neural network" model, uncovers some structural features of international conflict and also functions as an evaluative measure by forecasting. Moreover, it is easy to evaluate whether the neural network model is a statistical improvement over the simpler models commonly used.