Explaining Recruitment to Extremism: A Bayesian Contaminated Case Control Approach

Who joins extremist movements? Answering this question poses considerable methodological challenges. Survey techniques are practically infeasible and selective samples provide no counterfactual. Assigning recruits to contextual units provides one solution, but is vulnerable to problems of ecological inference. In this article, we take inspiration from epidemiology and the protest literature and elaborate a technique to combine survey and ecological approaches. The rare events, multilevel Bayesian contaminated case-control design we propose accounts for individual-level and contextual factors, as well as spatial autocorrelation in the incidence of recruitment. We validate our approach by matching a sample of Islamic State (ISIS) fighters from nine Muslim-majority countries with representative population surveys enumerated shortly before recruits joined the movement. We find that high status individuals in their early twenties who had university education were more likely to join ISIS. We find more mixed evidence for relative deprivation.