|
Activity Number:
|
330
|
|
Type:
|
Roundtables
|
|
Date/Time:
|
Wednesday, August 6, 2008 : 7:00 AM to 8:15 AM
|
|
Sponsor:
|
Section on Statistics and the Environment
|
| Abstract - #300598 |
|
Title:
|
Bayesian Space-Time Disease Mapping: Issues and Opportunities
|
|
Author(s):
|
Andrew B. Lawson*+
|
|
Companies:
|
University of South Carolina
|
|
Address:
|
Dept of Epoidemiology & Biostatistics, Columbia, SC, 29208,
|
|
Keywords:
|
Bayesian ; spatial ; health ; pollution ; space-time
|
|
Abstract:
|
Bayesian hierarchical modeling of georeferenced health data is often concerned with temporal changes to maps of disease. The focus can be related to estimation of the linkage to environmental covariates or simply the relative risk estimation over time. In this roundtable, issues relating to space-time modeling will be considered in relation to environmental risk gradients. In particular, the concern that space-time interaction effects could play a significant part in both description of the risk surface as it changes and the relation with covariates displaying subtle interactions. An example of this is the possible change in risk relations over time for pollution emission sources and their risk imprint. Discussion will focus on unobserved and observed time-labeled pollution events.
|
