We study rare events data, binary dependent variables with dozens to thousands of times fewer ones (events, such as wars, vetoes, cases of political activism, or epidemiological infections) than zeros (“nonevents”). In many literatures, these variables have proven difficult to explain and predict, a problem that seems to have at least two sources. First, popular statistical procedures, such as logistic regression, can sharply underestimate the probability of rare events. We recommend corrections that outperform existing methods and change the estimates of absolute and relative risks by as much as some estimated effects reported in the literature. Second, commonly used data collection strategies are grossly inefficient for rare events data. The fear of collecting data with too few events has led to data collections with huge numbers of observations but relatively few, and poorly measured, explanatory variables, such as in international conflict data with more than a quarter-million dyads, only a few of which are at war. As it turns out, more efficient sampling designs exist for making valid inferences, such as sampling all available events (e.g., wars) and a tiny fraction of nonevents (peace). This enables scholars to save as much as 99 % of their (nonfixed) data collection costs or to collect much more meaningful explanatory

Some of the most important phenomena in international conflict are coded as "rare events data," binary dependent variables with dozens to thousands of times fewer events, such as wars, coups, etc., than "nonevents". Unfortunately, rare events data are difficult to explain and predict, a problem that seems to have at least two sources. First, and most importantly, the data collection strategies used in international conflict are grossly inefficient. The fear of collecting data with too few events has led to data collections with huge numbers of observations but relatively few, and poorly measured, explanatory variables. As it turns out, more efficient sampling designs exist for making valid inferences, such as sampling all available events (e.g., wars) and a tiny fraction of non-events (peace). This enables scholars to save as much as 99% of their (non-fixed) data collection costs, or to collect much more meaningful explanatory variables. Second, logistic regression, and other commonly ...

Recent empirical International Relations research suggests that democracies, in general, are uniquely pacific. The strongest statistical results, however, have been obtained from datasets that violate the assumptions of the statistical models typically used in estimation. The most widely cited democratic peace studies, moreover, arbitrarily categorize relatively continuous democracy measures and assume that the relationship between democracy and conflict to be identical for all democracy scores (and time invariant). It is difficult, therefore, to know the extent to which democracies in general, or democratic dyads in particular are exceptional in their propensity to avoid militarized conflict.

e address a well-known but inffequently discussed problem in the quantitative study of international conpict: Despite immense data collections, prestigious journals, and sophisticated analyses, empirical findings in the literature on international conflict are often unsatisfying. Many statistical results change ffom article to article and specijication to specijication. Accurate forecasts are nonexistent. In this article we 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, 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. This simple idea has an unexpectedly rich array of observable implications, all consistent with the literature. We directly test our conjecture by formulating a statistical model that includes its critical features. Our approach, a version of a "neural network " model, uncovers some interesting structural features of international conflict and, as one evaluative measure, forecasts substantially better than any previous effort. Moreover, this im~rovement comes at little cost, and it is easv to evaluate whether the model is a statistical improvement over the simpler models commonly used. D espite immense data collections, prestigious

Abstract: Despite increasing attention, we lack the analytic tools necessary to understand international hierarchy and its consequences for politics and policy. This is especially true for the informal hierarchies now found in world affairs. Rooted in a formal-legal tradition, international relationists almost universally assume that the international system is a realm of anarchy. Although the fact of anarchy remains a truism for the system as a whole, it is a fallacy of division to infer that all relationships within that system are anarchic. Building on an alternative view of relational authority and recent research on the practice of sovereignty, a new conception of international hierarchy is developed that varies along two continua defined by security and economic relations. This construct is operationalized and validated, and then tested in a large-n study of the effects of international hierarchy on the defense effort of countries. The principal finding is that states in hierarchical relationships spend significantly less on defense relative to GDP than states not in such relationships. In short, hierarchy matters and subordination pays; states appear to trade some portion of their sovereignty for protection from external security threats. 1

Feel free to cite, but cite for now as "unpublished manuscript" Please check with corresponding author for final text if using direct quotes.

In this paper, we examine the political economy of trade flows among major powers during the twentieth century. In the aftermath of World War II, scale economies motivated an increasing proportion of trade and the size distribution among the major powers became severely skewed. As a result, free trade became a risky strategy for smaller major powers. Reducing this risk required the larger states to make a credible commitment to keep their markets open. Alliances enabled them to do so. As such, military coalitions became especially important determinants of trade flows after World War II. Our empirical analysis supports this argument. We find that alliances exert a strong and sizeable effect on trade throughout the twentieth century. Their impact, however, is larger in the bipolar system than in its multipolar predecessor. Furthermore, relative to their prewar counterparts, post-World War II alliances exert more powerful effects on trade between states of disparate size than on trade between more symmetrical partners. Thus, our empirical analysis suggests that alliances do help resolve the problem of dynamic inconsistency that power asymmetries and scale economies create. The argument and evidence we present suggests that the international political economy resembles other political arenas in which welfare-enhancing outcomes require the nominally dominant power to tie its own hands. In the international system, we argue, an alliance can help a large state to do so, just as merchant guilds enabled medieval rulers to achieve efficient trade levels and a stronger parliament in the seventeenth century helped the English crown to obtain loans at less than prohibitive rates. 1