Identifying Meteorological Factors Associated with High PM_2.5 Levels via a Bayesian Spatial Quantile Regression

• Activity Number: 503 - Climate and Meteorological Statistics
• Type: Contributed
• Date/Time: Thursday, August 6, 2020 : 10:00 AM to 2:00 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Stella Coker Watson Self* and Christopher McMahan and Brook Russell
• Companies: University of South Carolina and Clemson University and Clemson University
• Keywords: Conditional autoregressive models; penalized spline estimation; random effects models; spatio-temporal modeling; air pollution

Abstract

Recently, due to accelerations in urban and industrial development, the health impact of air pollution has become a topic of key concern. Of the various forms of air pollution, fine atmospheric particulate matter (PM_2.5; particles less than 2.5 micrometers in diameter) appears to pose the greatest risk to human health. While even moderate levels of PM_2.5 can be detrimental to health, spikes in PM_2.5 to atypically high levels are even more dangerous. These spikes are believed to be associated with regionally specific meteorological factors. To quantify these associations, we develop a Bayesian spatio-temporal quantile regression model to estimate the spatially varying effects of meteorological variables purported to be related to PM_2.5 levels. By adopting a quantile regression model, we are able to examine the entire distribution of PM_2.5 levels; e.g., we are able to identify which meteorological drivers are related to abnormally high PM_2.5 levels. Our approach uses penalized splines to model the spatially varying meteorological effects and to account for spatio-temporal dependence. We apply our method to five years of daily PM_2.5 data collected across the United States.