Grantee Research Project Results

1999 Progress Report: Combining Environmental Data Using Hierarchical Bayesian Space-Time Models

EPA Grant Number: R826887
Title: Combining Environmental Data Using Hierarchical Bayesian Space-Time Models
Investigators: Zimmerman, Dale , Cowles, Mary Kathryn
Institution: University of Iowa
EPA Project Officer: Hahn, Intaek
Project Period: January 1, 1999 through December 31, 2001
Project Period Covered by this Report: January 1, 1999 through December 31,1999
Project Amount: $199,904
RFA: Environmental Statistics (1998) RFA Text | Recipients Lists
Research Category:

Objective:

To develop general and flexible statistical models for combining temporal, spatial, and spatio-temporal data. The models and associated statistical methodology will allow users of environmental data to combine data from disparate sources when analyzing relationships between, for example, pollutants and effects endpoints.

Progress Summary:

The specific objectives of the grant are listed below along with a summary of the aspects that have been accomplished to date.

To develop Bayesian hierarchical models for time-series, spatial, and spatio-temporal processes that combine data from disparate sources.
We have developed and implemented Bayesian hierarchical models for time-series and geostatistical processes that combine data from different sources.
To develop efficient Markov Chain Monte Carlo (MCMC) algorithms for implementing such models, and to assess their convergence.
We have developed two efficient MCMC algorithms for Bayesian geostatistical models. Furthermore, we have developed a simulation method for verifying theoretical convergence bounds for MCMC samplers for a class of models that includes intrinsic autoregressions for time-series and spatial data.
To evaluate model performance using simulation studies.
We have carried out small simulation studies to evaluate the performance of our Bayesian models and computing algorithms for time-series and geostatistical data.
To demonstrate gains in efficiency and predictive ability using the combined data rather than any of its component parts individually.

Future Activities:

Having successfully developed models for data that are temporally correlated only or spatially correlated only, and having successfully fit these models to important environmental datasets, we will now turn our attention to space-time data (i.e., data that are temporally and spatially correlated). We will formulate Bayesian hierarchical models for such data and fit them by Markov Chain Monte Carlo techniques. We will continue our work on computational strategies for assessing and accelerating convergence of MCMC samplers.

Journal Articles on this Report : 3 Displayed | Download in RIS Format

Publications Views
Other project views:	All 15 publications	6 publications in selected types	All 6 journal articles

Publications
Type	Citation	Project	Document Sources
Journal Article	Cowles MK. MCMC sampler convergence rates for hierarchical normal linear models: A simulation approach. Statistics and Computing 2002;12(4):377-389.	R826887 (1999) R826887 (2000)	not available
Journal Article	Isaacson JD, Zimmerman DL. Combining temporally correlated environmental data from two measurement systems. Journal of Agricultural, Biological, and Environmental Statistics 2000;5(4):398-416.	R826887 (1999) R826887 (2000)	Abstract: JSTOR - Abstract HTML Exit
Journal Article	Zimmerman DL, Holland DM. Complementary co-kriging: spatial prediction using data combined from several environmental monitoring networks. Environmetrics 2005;16(3),219-234.	R826887 (1999)	not available

Supplemental Keywords:

global climate, acid rain, monitoring, RFA, Ecosystem Protection/Environmental Exposure & Risk, Economic, Social, & Behavioral Science Research Program, Environmental Statistics, Ecosystem/Assessment/Indicators, Ecological Effects - Environmental Exposure & Risk, Bayesian space-time model, combined data, data analysis, global warming, innovative statistical models, risk assessment, statistical methods, statistical models, prediction, co-pollutant effects, spatial-temporal methods, data models, global environmental data, streamflow, hierarchical Bayesian space-time models

Relevant Websites:

Relevant Web Sites:

Kate Cowles, Ph.D. Exit

Progress and Final Reports:

Original Abstract

2000 Progress Report

Final

Top of Page

The perspectives, information and conclusions conveyed in research project abstracts, progress reports, final reports, journal abstracts and journal publications convey the viewpoints of the principal investigator and may not represent the views and policies of ORD and EPA. Conclusions drawn by the principal investigators have not been reviewed by the Agency.