The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Abstract Details
Activity Number:
|
21
|
Type:
|
Topic Contributed
|
Date/Time:
|
Sunday, July 31, 2011 : 2:00 PM to 3:50 PM
|
Sponsor:
|
ENAR
|
Abstract - #300745 |
Title:
|
Directional Weights Car Models Using Gaussian Process Mixing
|
Author(s):
|
Veronica J. Berrocal*+ and Alan E. Gelfand
|
Companies:
|
University of Michigan and Duke University
|
Address:
|
Department of Biostatistics, Ann Arbor, MI, 48109, US
|
Keywords:
|
Conditionally autoregressive model ;
Gaussian process ;
non-stationarity
|
Abstract:
|
Areal or lattice data is commonly analyzed using conditionally autoregressive (CAR) models. In a CAR specification the weighting scheme used to derive the full conditionals is constant over space and fixed a priori to be either binary and determined by the adjacency relationship among subregions/cells, or inversely proportional to the distances among subregions/cells. In this paper, we propose an extension of the CAR modeling framework where the weights are non-constant and are random variables obtained by mixing a latent Gaussian process. The resulting class of directional-weight CAR models is flexible, allows for non-stationarity and generalizes the class of fixed-weight CAR models, which arise as a special case of our directional-weights CAR models.
|
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 2011 program
|
2011 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.