Measuring Violence Risk in Space and Time using Kernel Density Estimation

Abstract

Being able to assess conflict risk at local level is crucial for preventing political violence or mitigating its consequences. This paper develops a new methodological approach for measuring violence risk across space and time that improves the prediction of future conflict events. Violence is modeled as a stochastic process with an unknown underlying distribution. Each conflict event observed on the ground is interpreted as a random realization of this process and its underlying distribution is estimated using kernel density estimation methods in a three-dimensional space. The optimal smoothing parameters are estimated to maximize the likelihood of future conflict events. An illustration of the practical gains (in terms of out-ofsample forecasting performance) of this new methodology compared to standard space-time autoregressive models is shown using data from Ivory Coast.