A Poisson cokriging method for bivariate count data

Abstract

Bivariate spatially correlated count data appear naturally in several domains such as ecology, economy and epidemiology. Current methods for analysing such data lack simplicity, interpretability and computational awareness. This paper introduces Poisson cokriging, a bivariate geostatistical technique to model and predict spatially correlated count variables. Our method exploits classical geostatistical theory and the bivariate Poisson distribution to propose an adaptation of cokriging when the underlying process follows a bivariate Poisson structure. A simulation study and a real data application using counts from two mosquito-borne diseases in Colombia showed that our model successfully performs spatial predictions at unobserved locations under different settings. We demonstrate the competitive convenience of Poisson cokriging in filtering rates and modelling highly variant population sizes against traditional geostatistical methods. We conclude that Poisson cokriging improves prediction accuracy and reduces variance prediction errors in comparison with ordinary cokriging.