|
Activity Number:
|
47
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, August 8, 2004 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #300673 |
|
Title:
|
Model Selection for Geostatistical Models
|
|
Author(s):
|
Andrew A. Merton*+ and Jennifer A. Hoeting
|
|
Companies:
|
Colorado State University and Colorado State University
|
|
Address:
|
, Fort Collins, CO, ,
|
|
Keywords:
|
AIC ; kriging ; autocorrelation function
|
|
Abstract:
|
We consider the problem of model selection for geospatial data. The importance of accounting for spatial correlation has been discussed in other contexts, but the effect of spatial correlation on the choice of covariates in the model has not been fully explored. We consider kriging for geostatistical models to predict a response at unobserved locations, which involves the fitting of explanatory variables and an autocorrelation function. Spatial correlation is typically ignored in the selection of explanatory variables and this can influence model selection results. To address this problem, we consider the Akaike Information Criterion (AIC) as applied to a geostatistical model. We offer a heuristic derivation of the AIC in this context and provide simulation results that show that using AIC for a geostatistical model is superior to the traditional approach of ignoring spatial correlation in the selection of explanatory variables. An example further demonstrates these ideas.
|
- 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 2004 program |
