A Bayesian mixture modeling approach for public health surveillance.

摘要: Spatial monitoring of trends in health data plays an important part public surveillance. Most commonly, it is used to understand the etiology a issue, assess impact intervention, or provide detection unusual behavior. In this article, we present Bayesian mixture model for surveillance, which able estimates disease risk space and time, also detect areas with The designed deal range spatial temporal patterns data, time series different lengths. We carry out simulation study performance under scenarios, compare against recently proposed short series. Finally, surveillance road traffic accidents England over years 2005-2015.