Sahu, Sujit K. (2005) Spatio-Temporal Modelling and Forecasting of Fine Particulate Matter. In: S.I.S. 2005 - Statistica e Ambiente, 21-23 Settembre 2005, Messina, Italy.
Studies indicate that even short-term exposure to high concentrations of fine atmospheric particulate matter (PM2.5) can lead to long-term health effects. Data are typically observed at fixed monitoring stations throughout a study region of interest at different time points. The study region may contain both rural and urban areas. Statistical spatio-temporal models are appropriate for modelling these data.In this talk I will summarise my recent work on modelling and short-term forecasting of PM2.5 levels. I will talk about a a random effects model developed in Sahu et al. (2004) and briefly mention a Bayesian Kriged-Kalman filtering model detailed in Sahu and Mardia (2005). In the first approach we introduce two random effects components, one for rural or background levels and the other as a supplement for urban areas. These are specified in the form of spatio-temporal processes. Weighting these processes through population density results in nonstationarity in space. In the talk I will analyze a dataset on observed PM2.5 in three states in the U.S. - Illinois, Indiana and Ohio.
Actions (login required)