Multilevel quantile function modeling with application to birth outcomes

Luke B Smith; Brian J Reich; Amy H Herring; Peter H Langlois; Montserrat Fuentes

doi:10.1111/biom.12294

Back

Multilevel quantile function modeling with application to birth outcomes

Journal article

Peer reviewed

Multilevel quantile function modeling with application to birth outcomes

Luke B Smith, Brian J Reich, Amy H Herring, Peter H Langlois and Montserrat Fuentes

Biometrics, Vol.71(2), pp.508-519

06/2015

DOI: 10.1111/biom.12294

PMCID: PMC6601633

PMID: 25761678

Files and links (1)

url

https://www.ncbi.nlm.nih.gov/pmc/articles/6601633View

Open Access

Abstract

Infants born preterm or small for gestational age have elevated rates of morbidity and mortality. Using birth certificate records in Texas from 2002 to 2004 and Environmental Protection Agency air pollution estimates, we relate the quantile functions of birth weight and gestational age to ozone exposure and multiple predictors, including parental age, race, and education level. We introduce a semi-parametric Bayesian quantile approach that models the full quantile function rather than just a few quantile levels. Our multilevel quantile function model establishes relationships between birth weight and the predictors separately for each week of gestational age and between gestational age and the predictors separately across Texas Public Health Regions. We permit these relationships to vary nonlinearly across gestational age, spatial domain and quantile level and we unite them in a hierarchical model via a basis expansion on the regression coefficients that preserves interpretability. Very low birth weight is a primary concern, so we leverage extreme value theory to supplement our model in the tail of the distribution. Gestational ages are recorded in completed weeks of gestation (integer-valued), so we present methodology for modeling quantile functions of discrete response data. In a simulation study we show that pooling information across gestational age and quantile level substantially reduces MSE of predictor effects. We find that ozone is negatively associated with the lower tail of gestational age in south Texas and across the distribution of birth weight for high gestational ages. Our methods are available in the R package BSquare.

Biometry

Pregnancy

Ozone - adverse effects

Infant Mortality

Humans

Infant

Male

Models, Statistical

Gestational Age

Birth Weight

Regression Analysis

Computer Simulation

Infant, Premature

Bayes Theorem

Air Pollutants - adverse effects

Female

Infant, Small for Gestational Age

Infant, Newborn

Texas - epidemiology

Details

Title: Subtitle: Multilevel quantile function modeling with application to birth outcomes
Creators: Luke B Smith - Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, U.S.A
Brian J Reich - Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, U.S.A
Amy H Herring - Department of Biostatistics and Carolina Population Center, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina 27599-7420, U.S.A
Peter H Langlois - Texas Department of State Health Services, Austin, Texas 78714-9347, U.S.A
Montserrat Fuentes - Department of Statistics, North Carolina State University, Raleigh, North Carolina 27695-8203, U.S.A
Resource Type: Journal article
Publication Details: Biometrics, Vol.71(2), pp.508-519
DOI: 10.1111/biom.12294
PMID: 25761678
PMCID: PMC6601633
NLM abbreviation: Biometrics
ISSN: 0006-341X
eISSN: 1541-0420
Publisher: United States
Grant note: U01DD000494 / NCBDD CDC HHS SR01ES014843 / NIEHS NIH HHS R01 ES014843 / NIEHS NIH HHS
Language: English
Date published: 06/2015
Academic Unit: Statistics and Actuarial Science; President; Biostatistics
Record Identifier: 9984065773502771

Metrics

31 Record Views

10 Times Cited - Web of Science