|
Activity Number:
|
259
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Tuesday, August 4, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #303564 |
|
Title:
|
Bayesian Model Averaging for Clustered Data: Imputing Missing Daily Air Pollution Concentrations
|
|
Author(s):
|
Howard Chang*+ and Francesca Dominici and Roger D. Peng
|
|
Companies:
|
Johns Hopkins University and Johns Hopkins University and Johns Hopkins Bloomberg School of Public Health
|
|
Address:
|
, Baltimore, MD, ,
|
|
Keywords:
|
Bayesian model averaging ; Missing data ; Imputation ; Air pollution ; Particulate matter ; Nonattainment status
|
|
Abstract:
|
The presence of missing observations is a challenge in statistical analysis especially when data are clustered. In this paper, we develop a Bayesian model averaging (BMA) approach for imputing missing observations in clustered data. Our approach extends BMA by allowing the weights of competing regression models for missing data imputation to vary between clusters while borrowing information across clusters in estimating model parameters. We then apply our proposed method to a national data set of daily ambient coarse particulate matter (PM10-2.5) concentration between 2003 and 2005. We impute missing daily monitor-level PM10-2.5 measurements and estimate the posterior probability of PM10-2.5 nonattainment status for 95 US counties based on the Environmental Protection Agency's proposed 24-hour standard.
|
