This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 335
Type: Topic Contributed
Date/Time: Tuesday, August 3, 2010 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics and the Environment
Abstract - #308178
Title: Approximate Bayesian Computation for Spatial Extremes via Open-Faced Sandwich Adjustment
Author(s): Benjamin Shaby*+
Companies: Statistical and Applied Mathematical Sciences Institute
Address: 1100 Courtney Creek Blvd., Durham, NC, 27713, USA
Keywords: extremes ; max stable process ; MCMC ; spatial
Abstract:

Analysis of univariate extreme events is often carried out through models built around generalized extreme value distributions. Models that consider dependence among extreme events are more elusive. Max-stable process models explicitly consider spatial dependence of block maxima, and are therefore promising for applications like heat waves or storms. Unfortunately, though a handful of max-stable processes have been proposed, none feature joint likelihoods that can be expressed analytically for dimensions greater than two. The lack of available likelihoods is an obvious obstacle if one wishes to estimate model parameters in a Bayesian way through MCMC. We propose a method of constructing a sampler based on pairwise likelihoods, which are available. This sampler is motivated by existing asymptotic theory, and results in "posterior" inferences that have desirable frequentist properties.


The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2010 program




2010 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Continuing Education program, please contact the Education Department.