Superfund Research Program

Optimizing Sampling and Statistical Analysis for Hazardous Waste Site Assessment

Project Leader: Brent A. Coull
Co-Investigator: Peter Toscas (Commonwealth Scientific Industrial Research Organization (CSIRO))
Grant Number: P42ES016454
Funding Period: 2010-2015

Project-Specific Links

Final Progress Reports

Year:   2013 

Studies and Results

Statistical analysis strategies that integrate multiple data types: In 2013 Dr. Coull and his research team completed a second revision requested by the Annals of Applied Statistics on a manuscript (Nikolov, Paciorek, Schwartz, and Coull 2012) describing computationally efficient strategies for integrating spatio-temporal data from multiple data sources. Briefly, this work considered a Bayesian hierarchical framework in which a joint model consists of a set of submodels, one for each data source, and a model for the latent process that serves to relate the submodels to one another. When a submodel depends on the latent process nonlinearly, inference using standard MCMC techniques can be computationally prohibitive. To make such problems tractable, this work linearized the nonlinear components with respect to the latent process and induce sparsity in the covariance matrix of the latent process using compactly supported covariance functions. Project researchers proposed an efficient MCMC scheme that takes advantage of these approximations. They used their model to address a temporal change of support problem whereby interest focuses on pooling daily and multiday black carbon readings in order to maximize the spatial coverage of the study region.

Correlated Measurement Error Models for Spatial Health Effects Analyses: Dr. Coull and trainee, Dr. Stacey Ackerman-Alexeeff, submitted two other papers focusing new statistical methods that properly estimate associations between environmental concentrations and biologic outcomes while accounting for measurement error association with spatially misaligned exposure and biologic data. In the last year, Dr. Stacey Ackerman-Alexeeff won a student paper award in environmental statistics from the American Statistical Association for this work, and presented this paper at the 2013 Joint Statistical Meetings in Montreal. She was also awarded a prestigious National Science Foundation postdoctoral fellowship to continue her studies in environmental statistics and climate change.

Characterizing exceedances for remediation purposes: Dr. Brent Coull collaborated with doctoral student Mark Meyer and colleague Dr. Jeffrey Morris on a project that compared different methods for identifying hot spots on a two-dimensional spatial surface using Bayesian false discovery and other multiple comparison adjustments. This paper is currently submitted for publication.

Significance

While this project focuses on soil and sediment as closely related to the goals of the Superfund program, methods for selecting spatial sites for other media could benefit from insight on how to place samples and conduct analyses. For example, air pollution considered at scales of tens to hundreds of kilometers may be comparable to soil data at scales of meters or tens of meters, provided one adjusts the scale of analysis. The generalness of applicability includes methods to account for targeted samples; for example, many EPA air pollution monitors have been placed in areas of high concentration to monitor peak concentrations, which could distort standard spatial statistical analyses.