Title: Spatiotemporal modeling of vector-borne disease risk
Authors: Gavino Puggioni - University of Rhode Island (United States) [presenting]
Abstract: The occurrence of mosquito-borne tropical diseases, such as Dengue and Zika, have been rising in the last ten years and linked to changes in precipitation, temperature, and urbanization. An illustrative case study features monthly Dengue reports at the municipal level in Puerto Rico from 1990 to 2015, weather variables collected from 34 stations around the island, and satellite data. The first stage of the proposed modeling strategy addresses the difference in spatial support of predictors and response. At the second stage, several space-time CAR specifications are implemented in a Bayesian framework to assess the relative risk of these factors. The model's predictive framework can be used to inform early warning systems for targeted surveillance and outbreak detection.