|
Activity Number:
|
486
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 2, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #308077 |
|
Title:
|
Nonparametric Modeling for Spatial Functional Data Analysis
|
|
Author(s):
|
Alan E. Gelfand*+
|
|
Companies:
|
Duke University
|
|
Address:
|
ISDS, Durham, NC, 27708-0251,
|
|
Keywords:
|
Dirichlet processes ; hierarchical model ; random functions
|
|
Abstract:
|
Recently there has been increased interest in flexible modeling for functional data analysis. We consider a strategy based upon Dirichlet process mixing. But then, we may encounter unknown functions at various spatial locations. However, we might expect that functions closer to each other in space will be more similar than those farther apart. We would like to develop a spatial process model that is again, nonparametric but captures this behavior. Here we can employ spatial Dirichlet processes. Altogether, we create a Bayesian nonparametric model for spatial functional data analysis. We illustrate the application of this modeling methodology with a dataset involving temperature vs. depth relationships at many locations in the Atlantic Ocean.
|
- 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 2007 program |
