A Generalized Measure of Uncertainty in Geostatistical Regression Model Selection

• Activity Number: 31
• Type: Contributed
• Date/Time: Sunday, July 31, 2016 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Chun-Shu Chen* and Jun Zhu and Tingjin Chu
• Companies: National Changhua University of Education and University of Wisconsin - Madison and Renmin University of China
• Keywords: Data perturbation ; Geostatistics ; Information criterion ; Model complexity ; Spatial prediction

Abstract

Model selection and model averaging are essential to regression analysis in environmental studies, but determining which of the two approaches is the more appropriate and under what circumstances remains an active research topic. In this paper, we focus on geostatistical regression models for spatially referenced environmental data. For a general information criterion, we develop a new perturbation-based criterion that measures the uncertainty of spatial model selection, as well as an empirical rule for choosing between model selection and model averaging. Statistical inference based on the proposed model selection instability measure is justified both in theory and via a simulation study. The results suggest that the performance of model selection and model averaging can be quite different for smaller models but are more comparable when the model is relatively large. For illustration, a precipitation data set in the state of Colorado is analyzed.