The paper “Sequential data assimilation of the 1D self-exciting process with application to urban crime data“, co-authored by Naratip Santitissadeekorn, Martin Short (Georgia Tech), and David Lloyd, has been accepted for publication in Computational Statistics and Data Analysis.  The paper develops a novel Bayesian sequential data assimilation algorithm for joint state-parameter estimation by deriving an approximating Poisson-Gamma ‘Kalman’ filter, that allows for uncertainty quantification for inhomogeneous Poisson data. The theory is applied to synthetic and real Los Angles gang crime data.  A link to the final form preprint is here. The university has issued a press release about the work and the link is here.