Here is the poster we are using to advertise the data suite at PSS(I).
Category: Blog Posts
You Don’t Need to Analyze International Conflict by Just Confrontation Onsets, or Confrontation Summaries
From Steve Miller | Dyad-year models of conflict onset and conflict escalation are the most common way for researchers to explore the causes of conflict between states. Using some data set of dyad years in the Correlates of War state system (e.g. politically relevant, contiguous, universal), a researcher can explore the determinants of the onset of a new conflict episode in a given dyad-year. Selecting on conflict onsets, researchers can look for what correlates with particularly “severe” conflicts involving the […]
Current Projects
We are currently involved in two NSF-funded projects. Miller and Gibler are finishing an issues-based data collection (NSF#1729300), that collects information on all issues of contention in confrontations from 1816 to 2014. Three levels of data are being collected: overall issue data, issue changes data over time, and demands made over each issue. This data is intended to be used in connection with the MIC events data to better understand international bargaining through conflict. The second ongoing project, headed by […]
Do Not Use CoWMID for Robustness Checks with Our Data
We use the same coding rules for confrontations as CoWMID does for disputes: Jones, Bremer, and Singer (1996). We also use the same population of states in the international system. Thus, on paper, our datasets should be equivalent, but they are not. We have been devout about applying CoWMID coding rules consistently over time with primary source information, with only a few modifications for clarity and informational purposes. Meanwhile, CoWMID has just accepted their pre-1993 cases as gifts from some […]
Read More from Do Not Use CoWMID for Robustness Checks with Our Data
The reciprocation variable: It’s not measuring what you think
Many studies, including a couple of my own, use the variable <recip> or reciprocation as a dependent variable in their analyses of, for example, audience costs. I’m not going to list the studies because the authors, including myself, were naive about what the variable represented, but <recip> does not theoretically or empirically capture audience costs inferences well. The logic of reciprocation as a proxy for audience costs is straightforward. One country initiates a militarized incident. If the target state does […]
Read More from The reciprocation variable: It’s not measuring what you think
Do Not Select on Fatal Conflicts!
A convention that has developed over the last couple of decades has quantitative researchers sampling only the Correlates of War Militarized Interstate Disputes (CoWMIDs) that had military fatalities. Most recognize the heterogeneity in the data set—that there are some “weird” cases—and want to analyze only those cases that truly have a chance to escalate to war. We have found this selection method to be both theoretically and empirically fraught. Here’s why. First, ever hear of the following conflicts?: Iran Hostage Crisis of […]