Online Program Home
My Program

Abstract Details

Activity Number: 289
Type: Invited
Date/Time: Tuesday, August 2, 2016 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistics and the Environment
Abstract #318346 View Presentation
Title: Implication of Nonlinear Air Pollutant Concentrations: Response Functions in Risk Assessment
Author(s): Ana G. Rappold* and James Crooks
Companies: EPA and National Jewish Health
Keywords: ozone ; risk assessment ; nonlinear concentration response funtion
Abstract:

We characterize the sensitivity of the ozone attributable health burden assessment with respect to different modeling strategies of concentration-response function. For this purpose, we develop a flexible Bayesian hierarchical model allowing for a nonlinear ozone risk curve with a shape parameter controlling the prior belief about the monotonicity of the risk through the prior distribution of basis function parameters. We used polynomial spline basis functions and their derivatives to evaluate the relative risk of ozone at all percentiles of the distribution. Linear concentration-response model and the model reflecting no prior belief about the monotonicity are examined as special cases. We examine the sensitivity of the health burden with respect to hypothetical and observed changes in the ozone distribution by applying modeled concentration-response functions. The model is applied to the mortality time series data from major US urban centers between 1985 and 2005. This abstract does not necessarily reflect U.S. EPA policy.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association