|
Activity Number:
|
386
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Wednesday, August 1, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #309109 |
|
Title:
|
Bayesian Hierarchical Models for Extreme Values Observed over Space and Time
|
|
Author(s):
|
Huiyan Sang*+ and Alan E. Gelfand
|
|
Companies:
|
Duke University and Duke University
|
|
Address:
|
Rm 214 Old Chem Bldg, Durham, NC, 27705,
|
|
Keywords:
|
generalized extreme valued distribution ; Spatial random effects ; MCMC Langevin algorithm ; Markov random field ; Temperature surface
|
|
Abstract:
|
We propose a hierarchical Bayesian approach for modeling a collection of spatially-referenced time series of extreme values. We assume that the observations follow Generalized Extreme Value (GEV) distributions where the dependence is captured using the transformed spatial Gaussian process and the spatially dependent locations and scales. The models can be fitted using a Markov Chain Monte Carlo (MCMC) Langevin algorithm to enable inference for parameters and to provide spatio-temporal predictions. We fit the models to a set of weather station temperature data collected over a 50-year period for the Cape Floristic Region in South Africa.
|
