Grantee Research Project Results
2005 Progress Report: Bayesian Methods for Characterizing Complex Multivariate Exposures
EPA Grant Number: R831843Title: Bayesian Methods for Characterizing Complex Multivariate Exposures
Investigators: Herring, Amy H. , Savitz, David A.
Institution: University of North Carolina at Chapel Hill
EPA Project Officer: Aja, Hayley
Project Period: November 1, 2004 through October 31, 2007
Project Period Covered by this Report: November 1, 2004 through October 31, 2005
Project Amount: $389,248
RFA: Environmental Statistics Research: Novel Analyses of Human Exposure Related Data (2004) RFA Text | Recipients Lists
Research Category: Environmental Statistics , Human Health
Objective:
The objectives of this research project are to: (1) develop useful methods for summarizing complex exposures and for examining the relationship between the exposures and health outcomes; (2) account properly for resultant uncertainty in the exposure assessment; and (3) use the models for estimation, prediction, and other inferences about the effects of multichemical, multipathway exposures.
Progress Summary:
We have made substantial progress toward our goal of developing statistical methods for assessing the relationship between complex multivariate exposures and health outcomes of interest. During Year 1 of the project, we have concentrated on exploring different methods of shrinkage for the purpose of borrowing information across similar exposure times and disinfection byproducts (DBPs), using the point mass mixture priors discussed in the proposal. At this time, we have submitted one manuscript for publication. We use Dirichlet process priors, incorporating a point mass mixture in the base measure, as an approach for adaptive shrinkage. In addition, two manuscripts are in preparation and will be submitted this winter. The first manuscript compares the proposed shrinkage method with popular shrinkage methods (including semi-Bayes and parametric Bayes) currently being used, with simulation results indicating the superior performance of our proposed method in a variety of settings. Another manuscript applies these methods in a basic model using the water exposure data, assessing the association between each component DBP and spontaneous abortion while simultaneously adjusting for the other DBPs, which share high correlation with each other.
Future Activities:
For the next reporting period, we will extend the methods developed to the complex data structure present in Right from the Start. We will continue model building and assessment with respect to assessing the sensitivity of results to the particular uptakes factors used, and we will determine whether certain periods of gestation are more sensitive to DBP effects than others. Using the methods developed during the first year of the grant, we will use shrinkage to handle the high-dimensionality of the exposure and large number of predictor variables. We plan to present preliminary results based on this work at the ENAR Meeting in Tampa, Florida in March.
Journal Articles on this Report : 12 Displayed | Download in RIS Format
| Other project views: | All 15 publications | 12 publications in selected types | All 12 journal articles |
|---|
| Type | Citation | ||
|---|---|---|---|
|
|
Carmichael SL, Herring AH, Sj÷din A, Jones R, Needham L, Ma C, Ding K, Shaw GM. Hypospadias and halogenated organic pollutant levels in maternal mid-pregnancy serum samples. Chemosphere 2010;80(6):641-646. |
R831843 (2005) |
Exit Exit |
|
|
Dunson DB, Herring AH, Engel SM. Bayesian selection and clustering of polymorphisms in functionally related genes. Journal of the American Statistical Association 2008;103(482):534-546. |
R831843 (2005) R831711 (2007) R831711 (Final) |
Exit Exit |
|
|
Herring AH. Nonparametric Bayes Shrinkage for Assessing Exposures to Mixtures Subject to Limits of Detection. Epidemiology 2010;21(4):S71-S76. |
R831843 (2005) |
Exit |
|
|
Hoffman CS, Mendola P, Savitz DA, Herring AH, Loomis D, Hartmann KE, Singer PC, Weinberg HS, Olshan AF. Drinking Water Disinfection By-Product Exposure and Duration of Gestation. Epidemiology 2008;19(5):738-746. |
R831843 (2005) |
Exit |
|
|
Hoffman CS, Mendola P, Savitz DA, Herring AH, Loomis D, Hartmann KE, Singer PC, Weinberg HS, Olshan AF. Drinking Water Disinfection By-Product Exposure and Fetal Growth. Epidemiology 2008;19(5):729-737. |
R831843 (2005) |
Exit |
|
|
Horton BJ, Luben TJ, Herring AH, Savitz DA, Singer PC, Weinberg HS, Hartmann KE. The Effect of Water Disinfection By-products on Pregnancy Outcomes in Two Southeastern US Communities. Journal of Occupational and Environmental Medicine 2011;53(10):1172-1178. |
R831843 (2005) |
Exit |
|
|
MacLehose RF, Dunson DB, Herring AH, Hoppin JA. Bayesian Methods for Highly Correlated Exposure Data. Epidemiology 2007;18(2):199-207. |
R831843 (2005) |
Exit |
|
|
MacLehose RF, Savitz DA, Herring AH, Hartmann KE, Singer PC, Weinberg HS. Drinking Water Disinfection By-Products and Time to Pregnancy. Epidemiology 2008;19(3):451-458. |
R831843 (2005) |
Exit |
|
|
Saville BR, Herring AH. Testing random effects in the linear mixed model using approximate Bayes factors. Biometrics 2009;65(2):369-376. |
R831843 (2005) |
Exit |
|
|
Saville BR, Herring AH, Koch GG. A robust method for comparing two treatments in a confirmatory clinical trial via multivariate time-to-event methods that jointly incorporate information from longitudinal and time-to-event data. Statistics in Medicine 2010;29(1):75-85. |
R831843 (2005) |
|
|
|
Slaughter JC, Herring AH, Hartmann KE. Bayesian modeling of embryonic growth using latent variables. Biostatistics 2008;9(2):373-389. |
R831843 (2005) |
Exit Exit |
|
|
Wright JM, Hoffman CS, Savitz DA. The relationship between water intake and foetal growth and preterm delivery in a prospective cohort study. BMC Pregnancy and Childbirth 2010;10(1):1-8. |
R831843 (2005) |
Exit Exit |
Supplemental Keywords:
Bayesian methods, chlorination, disinfection byproducts, drinking water, pregnancy outcome, spontaneous abortion, water quality,, RFA, Health, Scientific Discipline, INTERNATIONAL COOPERATION, ENVIRONMENTAL MANAGEMENT, Water, Economic, Social, & Behavioral Science Research Program, POLLUTANTS/TOXICS, Environmental Statistics, Health Risk Assessment, Risk Assessments, Environmental Chemistry, Biochemistry, Drinking Water, Environmental Monitoring, Water Pollutants, Risk Assessment, cumulative effects, complex chemical mixtures, Bayesian method, pollutant mixtures, DBP risk assessment, water quality, health risk analysis, chemical mixtures, human exposure, drinking water supplies, multivariate exposure assessment, co-pollutant effects, other - risk assessment, disinfection byproducts, air pollution, Bayesian statistical theory, human health risk, disinfection byproducts (DPBs), exposure assessment, multi chemical exposureRelevant Websites:
http://www2.sph.unc.edu/profiles/?fuseaction=profile_detail&subject=bios&profile_id=1388&class=FACULTY,STAFF&dropnull=1 Exit
Progress and Final Reports:
Original AbstractThe 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.