|
Activity Number:
|
122
|
|
Type:
|
Invited
|
|
Date/Time:
|
Monday, August 4, 2008 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
International Society of Bayesian Analysis
|
| Abstract - #300444 |
|
Title:
|
Hierarchical Models for Combining Data from Multiple Sources for Risk Assessment
|
|
Author(s):
|
Louise Ryan and Tianxi Cai*+
|
|
Companies:
|
Harvard School of Public Health and Harvard University
|
|
Address:
|
Department of Biostatistics, Boston, MA, 02115,
|
|
Keywords:
|
|
|
Abstract:
|
Assessing the risk of rare adverse events associated with environmental or pharmaceutical exposures generally encounters the challenge of dealing with low-powered studies. Power to quantify such risks can be boosted by synthesizing data from multiple studies. While Bayesian hierarchical models provide a natural tool in such settings, it can be a challenge to construct appropriate prior distributions, and the results are often sensitive to the assumptions being made. We present several case studies that illustrate these challenges, along with effective solutions.
|
