Kernel-Averaged Predictors for Spatio-Temporal Processes

• Activity Number: 21
• Type: Topic Contributed
• Date/Time: Sunday, July 31, 2011 : 2:00 PM to 3:50 PM
• Sponsor: ENAR
• Author(s): Matthew J. Heaton*+ and Alan E. Gelfand
• Companies: Duke University and Duke University
• Keywords: distributed lags ; ozone ; environmental health ; kernel average

Abstract

For spatio-temporal processes, predictors from multiple locations affect the response at a separate location. For example, predictors such as precipitation, temperature, pollution emissions, etc.\ are often used to explain ground-level ozone production. Due to weather and other factors, however, the relationship between these predictors and ozone is not confined to a single spatial location or time period as is often assumed. Here, kernels are proposed as a tool to properly weight predictor surfaces in spatio-temporal regression models. The kernels are assumed to be parametric with parameters that are estimable from the data. This talk provides an overview of the modeling strategies used for kernel averaged predictors in the spatio-temporal setting with an emphasis on environmental applications.