Bivariate Quantile Regression

• Activity Number: 254
• Type: Contributed
• Date/Time: Monday, July 30, 2012 : 2:00 PM to 3:50 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Luke Smith*+ and Montserrat Fuentes and Brian Reich
• Companies: North Carolina State University and North Carolina State University and North Carolina State University
• Keywords: quantile regression ; bivariate response ; air pollution ; gestational age ; birth weight

Abstract

Infants with low birth weight (<2500 g) or born prematurely (< 37 week gestational period) have enhanced risk of morbidity and mortality. The effect of maternal exposure to ambient air pollution on gestational age and birth weight is still unknown. To assess the potential harmful impacts, we jointly regress the quantiles of birth weight and gestational age on multiple pollutants, including stratospheric ozone, elemental carbon, organic carbon, nitrate, sulfate, and aggregate fine particles (PM 2.5), while controlling for several covariates, including parental race, age and education level and infant sex. We estimate ambient air pollution levels at geocoded maternal addresses in Texas from 2001-2006 by integrating monitor data from the Environmental Protection Agency's (EPA) Air Quality System network and numerical output from the EPA's Community Multiscale Air Quality product.