What We Know and What We Don’t Know about Violent Extremism in the United States

• In Event: Radicalization to Violent Extremism: What We Don't Know

Abstract

While the empirical study of terrorism has grown dramatically in the past decade and a half to incorporate more sophisticated statistical and econometric methods, data validity is still an open, first order question. To illustrate strengths and weaknesses of current empirical research on violent extremism I draw on the Profiles of Individual Radicalization in the United States (PIRUS) dataset. In recent research, my colleagues and I test whether variables derived from prominent criminological theories are helpful in distinguishing between violent and non-violent extremists. Our results show that four variables are significantly related to violent radicalization: lack of a stable employment history, prior criminal record, membership in a radical clique, and a history of mental illness. The relationships are robust across multiple techniques for imputing missing data. However, in related research we also show that point estimates of basic conditional probabilities can vary dramatically depending on the amount of missing data in certain variables and the methods used to address this issue. We conclude by advocating for continuing efforts to improve the quality of our research but also being transparent about the assumptions we make on the limitations of our data and the implications for analysis and interpretation.

Author

• Gary LaFree, University of Maryland