This study demonstrated that spatial and temporal factors related to crime patterns are generally confounded, requiring analyses to take both into account, and it proposes a spatio-temporal self-exciting point process model that incorporates spatial features, near repeat and retaliation effects, and triggering.
Crime has both varying patterns in space - related to features of the environment, economy and policing - and patterns in time arising from criminal behavior, such as retaliation. Serious crimes may also be preceded by minor crimes of disorder. The current study developed inference methods and diagnostic tools, such as residual maps, for the proposed model; and through extensive simulation and crime data obtained from Pittsburgh, Pennsylvania, demonstrated its properties and usefulness. (publisher abstracts modified)