Bayesian variable selection for understanding mixtures in environmental exposures
Open Access
- 15 June 2021
- journal article
- research article
- Published by Wiley in Statistics in Medicine
- Vol. 40 (22) , 4850-4871
Abstract
Social and environmental stressors are crucial factors in child development. However, there exists a multitude of measurable social and environmental factors—the effects of which may be cumulative, interactive, or null. Using a comprehensive cohort of children in North Carolina, we study the impact of social and environmental variables on 4th end‐of‐grade exam scores in reading and mathematics. To identify the essential factors that predict these educational outcomes, we design new tools for Bayesian linear variable selection using decision analysis. We extract a predictive optimal subset of explanatory variables by coupling a loss function with a novel model‐based penalization scheme, which leads to coherent Bayesian decision analysis and empirically improves variable selection, estimation, and prediction on simulated data. The Bayesian linear model propagates uncertainty quantification to all predictive evaluations, which is important for interpretable and robust model comparisons. These predictive comparisons are conducted out‐of‐sample with a customized approximation algorithm that avoids computationally intensive model refitting. We apply our variable selection techniques to identify the joint collection of social and environmental stressors—and their interactions—that offer clear and quantifiable improvements in prediction of reading and mathematics exam scores.Keywords
Funding Information
- Army Research Office (W911NF‐ 20‐1‐0184)
- National Institute of Environmental Health Sciences (R01ES028819)
- National Institute on Minority Health and Health Disparities (R00MD011304)
This publication has 46 references indexed in Scilit:
- Nearly unbiased variable selection under minimax concave penaltyThe Annals of Statistics, 2010
- Is Segregation Bad for Your Health?Epidemiologic Reviews, 2009
- Sure Independence Screening for Ultrahigh Dimensional Feature SpaceJournal of the Royal Statistical Society Series B: Statistical Methodology, 2008
- Durable effects of concentrated disadvantage on verbal ability among African-American childrenProceedings of the National Academy of Sciences, 2008
- The Relationship between Early Childhood Blood Lead Levels and Performance on End-of-Grade TestsEnvironmental Health Perspectives, 2007
- The Development of a Standardized Neighborhood Deprivation IndexJournal of Urban Health, 2006
- The Environmental “Riskscape” and Social Inequality: Implicationsfor Explaining Maternal and Child Health DisparitiesEnvironmental Health Perspectives, 2006
- Spike and slab variable selection: Frequentist and Bayesian strategiesThe Annals of Statistics, 2005
- Better Subset Regression Using the Nonnegative GarroteTechnometrics, 1995
- Bayesian Variable Selection in Linear RegressionJournal of the American Statistical Association, 1988