Activity Number:
|
215
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 13, 2002 : 12:00 PM to 1:50 PM
|
Sponsor:
|
Section on Bayesian Stat. Sciences*
|
Abstract - #300697 |
Title:
|
Spatial Hierarchical Bayes Small Area Estimators
|
Author(s):
|
Ferry Butar Butar*+
|
Affiliation(s):
|
Sam Houston State University
|
Address:
|
Box 2206, Huntsville, Texas, 77341, USA
|
Keywords:
|
Mortality rates ; MCMC ; Spatial structure ; hierarchical model
|
Abstract:
|
The purpose of this paper is to estimate cancer mortality rates for counties or small areas. Standardized mortality rates (SMRs) are maximum likelihood estimates of mortality rates under Poisson random variable. Since cancer is a relatively rare disease, maps of SMRs are highly unstable. The empirical and hierarchical Bayes methods are suitable to smooth the small-area estimates which borrow strength from neighboring areas. We consider spatial structure on the random effects. We apply our model to construct smooth maps of lung cancer mortality data in Texas counties from 1990 to 1997. To obtain the estimators, MCMC will be used to measure the accuracy of the proposed hierarchical Bayes estimator of a small-area estimate.
|