|
Activity Number:
|
26
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Sunday, August 3, 2003 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #301212 |
|
Title:
|
Extending Bayesian Approaches to Measuring and Mapping Small Area Disparities: Heart Disease Mortality Disparity in Counties in the Southeastern United States
|
|
Author(s):
|
Eric C. Tassone*+ and Lance A. Waller and Michele Casper and Ishmael Williams and Kurt Greenlund and Linda Neff
|
|
Companies:
|
Emory University and Emory University and Centers for Disease Control and Prevention and Centers for Disease Control and Prevention and Centers for Disease Control and Prevention and Centers for Disease Control and Prevention
|
|
Address:
|
1408 Rock Springs Circle NE, Atlanta, GA, 30306-2252,
|
|
Keywords:
|
hierarchical Bayesian disease mapping ; disparity measures ; equity measures ; generalized linear mixed models ; standardization of rates ; socio-economic effects
|
|
Abstract:
|
We measure county-level disparities in heart disease mortality between African-Americans and whites in the southeastern United States (defined as the Department of Health and Human Services Region IV) during 1991-1995, for men and women separately. We extend the typical hierarchical Bayesian disease mapping model to measure disparity by exploiting the race-sex group structure of the study population. We offer two disparity measures, each extending the typical disease mapping model in different ways. Additionally, we introduce covariates that measure socio-economic characteristics of the counties as possible explanatory variables. We obtain similar results under the two disparity measures for both men and women. Point estimates of disparity are comparable between the two approaches, though associated variability shows some differences. The effects of the covariates are also consistent under the two approaches. Finally, we discuss the relative merits of the two disparity measures, and suggest possible enhancements of the measures.
|
