Quantitative Methods for IR Research

In the course of conducting my substantive research, I have had to research and develop methods used to statistically study of international relations. This entailed thinking about best practices for empirically studying international relations and developing software to assist in this analysis (see my ``Statistics Software" page). Overall, I have made three contributions to the quantitative study of international relations.

First, several of my projects required collecting new data. These data are available here. I collected these data for the same reason that all international relations scholars, going back to Quincy Wright, collected data to study IR: "because they thought that was what was appropriate given the question being asked."

In order to assist scholars in using quantitative data to study international politics, the National Science Foundation funded my collaborative efforts (with Scott Bennett and Allan Stam) to create the NewGene Data Management Software. This software provides a platform for helping scholars of international relations to manage, organize, and merge the various datasets being constantly produced by scholars, public institutions, and private organizations. The software is presently available for both Windows and OsX systems. The software was officially released in July 2017 and I gave a public lecture related to the software, sponsored by the Center for International Social Science Research and the Division of the Social Sciences, to mark its release (this news story describes the public lecture, the NewGene software, and the software's place in the history of quantitative IR research at the University of Chicago). Work to improve and update this software continues.

Second, in a piece published in political analysis, I introduced a new unit of analysis, the k-ad, for scholars to use when studying multilateral events, such as alliance formation and the creation of nonaggression pacts. A k-ad is an observation that captures the characteristics of k number of actors (where k is greater than or equal to 2). This means k can be equal to 2 (a dyad), 3 (a triad), or larger. Creating datasets with k-ads can be computationally intensive, as the datasets can be immensely large. While I introduce sampling methods that reduce the number of k-ads one must produce for a dataset, implementing these procedures can still be tricky. Easing the difficulties scholars face in creating k-adic data was a key part of the proposal to secure the NSF funding leading to the NewGene software (discussed above). Helping scholars to create k-adic data also led me to create a Stata command called kad-create (see here).

Because of this research on k-adic data, I was invited to write a piece in International Studies Quarterly that attempts to discuss the questions and theoretical claims for which dyadic data (perhaps the most commonly used unit of analysis in international relations research) are appropriate. The editors of ISQ then asked several quantitative IR scholars to respond to the points raised by my piece (and pieces by Skylar Cranmer & Bruce Desmaris and by Paul Diehl and Thorin Wright).

Presently, I am working on using a k-adic approach to study war onset. This is part of a broader project I am leading with Erik Gartzke to encourage scholars to empirically test the bargaining model of war, the core model presently used to understand the onset of war. We refer to this initiative as Empirical Implications of Bargaining Theory. In addition to hosting holding a number of workshops on the topic (such as workshop co-host by Kris Ramsay at Princeton University in 2015), we were invited to write a piece detailing this project for the Oxford Encyclopedia of Empirical International Relations Research.

Third, in another piece published in political analysis and co-authored with Walter Mebane, I am encourage quantitative international relations researches to "embrace uncertainty" by adopting variations of Manksi bounds. Whether working with experimental or observation data, scholars must make assumptions (sometimes rather strong assumptions) in order to draw an inference. Manski bounds offer an assumption free approach for defining the plausible range for the effect of a binary variable (e.g. a country being democratic or not; two countries having a territorial dispute or not). I applied this method in a piece on alliance politics published in the journal International Organization.

You are viewing the text version of this site.

To view the full version please install the Adobe Flash Player and ensure your web browser has JavaScript enabled.

Need help? check the requirements page.

Get Flash Player