@lmumuenchen.bsky.social @jrssa.bsky.social

Making explicit use of the grid-based structure, model estimation can be carried out efficiently with the R package mgcv, allowing for complex model fits over large sets of areas (e.g. continents). We provide a tutorial on how researchers can apply our method for their own work in our paper. [5/5]

We demonstrate how conflict is triggered across cells, over both varying distances and time lags. Diffusion is heavily driven by population structures. Conflict generally breaks out in densely populated areas and from there diffuses, disproportionately affecting less populated areas. [4/5]

We develop a generalized additive model that smooths across the spatio-temporal history of each observation, to capture these diffusion effects. Using conflict data from UCDP & PRIO grid cells across Africa, we analyze diffusion up to 550km in distance and 24 months in the past. [3/5]

Armed conflict exhibits substantial diffusion, i.e., spreading, across space and time. However, existing statistical models do not analyze nor fully capture these complex transmission processes. [2/5]