Group items tagged

Statistical validation of results, as Shaffer described it, simply involves testing the null hypothesis: that the pattern you detect in your data occurs at random. If you can reject the null hypothesis—and science and medicine have settled on rejecting it when there's only a five percent or less chance that it occurred at random—then you accept that your actual finding is significant. The problem now is that we're rapidly expanding our ability to do tests. Various speakers pointed to data sources as diverse as gene expression chips and the Sloan Digital Sky Survey, which provide tens of thousands of individual data points to analyze. At the same time, the growth of computing power has meant that we can ask many questions of these large data sets at once, and each one of these tests increases the prospects than an error will occur in a study; as Shaffer put it, "every decision increases your error prospects." She pointed out that dividing data into subgroups, which can often identify susceptible subpopulations, is also a decision, and increases the chances of a spurious error. Smaller populations are also more prone to random associations. In the end, Young noted, by the time you reach 61 tests, there's a 95 percent chance that you'll get a significant result at random. And, let's face it—researchers want to see a significant result, so there's a strong, unintentional bias towards trying different tests until something pops out. Young went on to describe a study, published in JAMA, that was a multiple testing train wreck: exposures to 275 chemicals were considered, 32 health outcomes were tracked, and 10 demographic variables were used as controls. That was about 8,800 different tests, and as many as 9 million ways of looking at the data once the demographics were considered.

Trade's effect on military conflict is one of the most important issues in international relations. The last decade has seen research and debate into the role of trade intensify; Liberals argue that trade brings peace, neo-realists and neo-Marxists reason that trade brings conflict, and classical realists contend that trade has no impact. This debate is not just academic: some key U.S. policymakers (Senator McCain and former President Clinton for instance) believe that trade brings peace, a view that contributes to their support for free trade. Economists developed bilateral trade models in isolation from models of interstate conflict, which were the work of political scientists. These two types of models handle distance between nations differently. Bilateral trade takes its cue from Isaac Newton's formula for the gravitational attraction between two objects: the larger the objects' masses and the shorter the distance between them, the larger the attraction. So the larger the trade partners' economies and the closer they are to one another, the greater their trade. However, conflict models instead incorporate shared borders by land or close distance over water (contiguity) - stressing the role of border disputes in sparking interstate conflict. Distance is included in conflict equations based on the idea that an army gets weaker the farther it strays from its base, but what point in a nation to pick for the trade and conflict equation is unclear. Often theorists use the distance between capital cities, which is problematic: wars generally happen around borders where armies are often based, and capitals have historically changed without this altering the likelihood of war between the nation and its neighbours. The authors suggest that the trade data set plugged into trade and conflict equations is critical. This type of data often contains gaps - there are a number of reasons why data from a particular nation might be unavailable, inevitably leaving researchers to make assumptions. The majority of trade and conflict studies define conflict to include all types of militarised interstate disputes (MIDs). But Keshk, Reuveny, and Pollins question the results generated when different conflict definitions are chosen. For instance, a conflict such as a threat to use nuclear weapons would not cause fatalities, but may still have some impact on trade and vice versa. In fact, by altering the data treatment and assumptions in the equation, the authors generated a variety of results, which supported several different theoretical viewpoints. The authors suggest that future research should investigate questions of missing bilateral trade data, and attempt a more subtle use of the meaning of "military conflict". Researchers might also develop distance and contiguity measures at a more sophisticated level. "Any signal that trade brings peace remains weak and inconsistent, regardless of the way proximity is modelled in the conflict equation. The signal that conflict reduces trade, in contrast, is strong and consistent," say the authors. "Any study of the effect of trade on conflict that ignores the reverse fact is practically guaranteed to produce estimates that contain simultaneity bias." Studies of the relationship between international trade and military conflict can be traced back many centuries, particularly in the works of luminaries such as de Montesquieu, Immanuel Kant, John Hobson, Vladimir Lenin, Henry Morgenthau, Kenneth Waltz, Frederic List, and Albert Hirschman. This latest study emphasises that international politics are affecting trade between nation pairs, while it is far less obvious whether trade systematically affects politics. "To our colleagues from the liberal camp we would like to say that we still believe there are limited circumstances in which more trade may help lead countries to more peaceful resolutions of their differences, particularly if they are already at peace," the authors state. "However, it is past time for academics and policymakers to look beyond the naive claim that the cultivation of trade ties will always and everywhere produce a more peaceful world."