Distinguished Lectures and Public Lectures: Statistical Analysis of Spatiotemporal Point Process Data
18 May 2017 16:00 in CG93
A spatiotemporal point process, P, is a stochastic model for generating a countable set of points (x(i), t(i)) ∈ IR2 × IR+, where each x(i) denotes the location, and t(i) the time, of an event of interest. A typical data-set is a partial realisation of P restricted to a specified spatial region A and time-interval [0,T], possibly supplemented by covariate information on location, time or the events themselves. In this talk, I will first give examples of different interpretations of this scenario according to whether only one or both of the sets of locations and times are stochastically generated. I will then discuss in more detail methods for analysing spatiotemporal point process data based on two very different modelling approaches, log-Gaussian Cox process models; and conditional intensity models, and describe applications of each in the context of human and veterinary epidemiology.
Contact firstname.lastname@example.org for more information