This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.
Abstract Details
Activity Number:
|
317
|
Type:
|
Invited
|
Date/Time:
|
Tuesday, August 3, 2010 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Statistical and Applied Mathematical Sciences Institute
|
Abstract - #306065 |
Title:
|
A Generalized Bayesian Spatial Prediction Method
|
Author(s):
|
Jim Zidek*+ and Yiping Dou and Nhu Le
|
Companies:
|
The University of British Columbia and The University of British Columbia and BC Cancer Agency
|
Address:
|
Department of Statistics, Vancouver, BC, V6T 1Z2, Canada
|
Keywords:
|
Spatial prediction ;
space-time modeling ;
empirical orthogonal functions ;
dynamic linear models ;
Bayesian hierarchial models
|
Abstract:
|
This paper presents a generalized Bayesian spatial prediction (GBSP) method for modeling space--time fields as an extension of a Bayesian spatial prediction (BSP) method developed some time ago. We obtain the generalization by integrating the BSP into the dynamic linear modeling (DLM) framework. However the extension preserves the computational advantages that guided the creation of the BSP in the first place, while gaining some of the DLM's advantages for prediction across the entire spatio--temporal region. In particular, the GBSP can handle spatial--temporal fields of high resolution. It also incorporates recently developed Bayesian empirical orthogonal functions for representing complex spatial patterns and covers data generated by multivariate response vectors. The advantages of the approach will be compared to a number of competitors.
|
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.