Estimating daily nitrogen dioxide level: application of a longitudinal model with spatially-correlated random effects

详细信息    查看全文

• 作者：Lixun Zhang ; Yongtao Guan ; Brian P. Leaderer…
• 关键词：Air pollution ; Bayesian model ; Environmental Protection Agency (EPA) ; Longitudinal model ; Markov chain Monte Carlo (MCMC)
• 刊名：Environmental and Ecological Statistics
• 出版年：2015
• 出版时间：June 2015
• 年：2015
• 卷：22
• 期：2
• 页码：329-344
• 全文大小：945 KB
• 参考文献：Bellander T, Berglind N, Gustavsson P, Jonson T, Nyberg F, Pershagen G, Jarup L (2001) Using geographic information systems to assess individual historical exposure to air pollution from traffic and house heating in Stockholm. Environ Health Perspect 109(6):633鈥?39View Article PubMed Central PubMed
  Brown PE, Diggle PJ, Lord ME, Young PC (2001) Space-time calibration of radar rainfall data. J R Stat Soc Ser C Appl Stat 50:221鈥?41View Article
  Cressie N (1989) The many faces of spatial prediction. In: Armstrong M (ed) Geostatistics, quantitative geology and geostatistics, vol 1. Kluwer, Dordrecht, pp 163鈥?76
  Cressie N, Wikle CK (2011) Statistics for spatio-temporal data. Wiley, Hoboken
  Diggle P, Moyeed R, Rowlingson B, Thomson M (2002) Childhood malaria in the Gambia: a case-study in model-based geostatistics. J R Stat Soc Ser C Appl Stat 51:493鈥?06View Article
  Dutilleul PRL (2011) Spatio-temporal heterogeneity: concepts and analyses. Cambridge University Press, Cambridge
  Gauderman WJ, Avol E, Lurmann F, Kuenzli N, Gilliland F, Peters J, McConnell R (2005) Childhood asthma and exposure to traffic and nitrogen dioxide. Epidemiology 16(6):737鈥?43View Article PubMed
  Ghosh SK, Bhave PV, Davis JM, Lee H (2010) Spatio-temporal analysis of total nitrate concentrations using dynamic statistical models. J Am Stat Assoc 105(490):538鈥?51View Article
  Jerrett M, Arain A, Kanaroglou P, Beckerman B, Potoglou D, Sahsuvaroglu T, Morrison J, Giovis C (2005) A review and evaluation of intraurban air pollution exposure models. J Expo Anal Environ Epidemiol 15(2):185鈥?04View Article PubMed
  Laird NM, Ware JH (1982) Random-effects models for longitudinal data. Biometrics 38(4):963鈥?74View Article PubMed
  Lee H, Ghosh SK (2008) A reparametrization approach for dynamic space-time models. J Stat Theory Pract 2:1鈥?4View Article PubMed Central PubMed
  Molitor J, Molitor NT, Jerrett M, McConnell R, Gauderman J, Berhane K, Thomas D (2006) Bayesian modeling of air pollution health effects with missing exposure data. Am J Epidemiol 164(1):69鈥?6View Article PubMed
  Palmes ED, Gunnison AF, DiMattio J, Tomczyk C (1976) Personal sampler for nitrogen dioxide. Am Ind Hyg Assoc J 37:570鈥?77View Article PubMed
  Peters JM, Avol E, Navidi W, London SJ, Gauderman WJ, Lurmann F, Linn WS, Margolis H, Rappaport E, Gong H, Thomas DC (1999) A study of twelve southern California communities with differing levels and types of air pollution鈥擨. Prevalence of respiratory morbidity. Am J Respir Crit Care Med 159(3):760鈥?67View Article PubMed
  Ribeiro PJ, Diggle PJ (2001) geoR: a package for geostatistical analysis. R News 1(2):15鈥?8
  Romanowicz R, Young P, Brown P, Diggle P (2006) A recursive estimation approach to the spatio-temporal analysis and modelling of air quality data. Environ Model Softw 21:759鈥?69View Article
  Rose N, Cowie C, Gillett R, Marks GB (2009) Weighted road density: a simple way of assigning traffic-related air pollution exposure. Atmos Environ 43(32):5009鈥?014View Article
  Ryan PH, LeMasters GK (2007) A review of land-use regression for characterizing intraurban air models pollution exposure. Inhal Toxicol 19:127鈥?33View Article PubMed Central PubMed
  SAS Institute Inc (2013) SAS/STAT 9.3 user鈥檚 guide: the MIXED procedure (Chapter). SAS Institute Inc, Cary
  Skene KJ, Gent JF, McKay LA, Belanger K, Leaderer BP, Holford TR (2010) Modeling effects of traffic and landscape characteristics on ambient nitrogen dioxide levels in Connecticut. Atmos Environ 44:5156鈥?164View Article PubMed Central
  Smith BJ (2007) boa: an R package for MCMC output convergence assessment and posterior inference. J Stat Softw 21:1鈥?7
  Zhang L, Guan Y, Leaderer BP, Holford TR (2013) Estimating daily nitrogen dioxide level: exploring traffic effects. Ann Appl Stat 7:1763鈥?777View Article
  
• 作者单位：Lixun Zhang (1)
  Yongtao Guan (2)
  Brian P. Leaderer (1)
  Theodore R. Holford (1)
  
  1. Yale School of Public Health, PO Box 208034, 60 College Street, New Haven, CT, 06520, USA
  2. Professor of Management Science, University of Miami, Coral Gables, FL, 33124, USA
  
• 刊物类别：Biomedical and Life Sciences
• 刊物主题：Life Sciences
  Ecology
  Statistics
  Mathematical Biology
  Evolutionary Biology
  
• 出版者：Springer Netherlands
• ISSN：1573-3009

文摘

Typically available nitrogen dioxide (\({\hbox {NO}}_{2}\)) measurements are either spatially representative but temporally sparse or temporally representative but spatially sparse. This article illustrates an approach for making use of the strengths of these two types of data to obtain pollution estimates that are representative both spatially and temporally. The model uses three data sources: a Connecticut epidemiological study with average monthly \({\hbox {NO}}_{2}\) measurements at 651 sites in each season for 1 year; hourly measurements at four Environmental Protection Agency (EPA) sites; and, geospatial data on traffic volume, population density, elevation, and land use. We start by establishing a relationship between observations from the epidemiological study and those at the EPA sites at the monthly level. This relationship is assumed to hold for daily \({\hbox {NO}}_{2}\) levels, enabling us to estimate average daily \({\hbox {NO}}_{2}\) levels using EPA data. Validation study confirmed that this assumption is sound and that the method performs best among three alternatives: a linear model, a mixed-effects model, and the proposed mix-effects model that takes into account spatial correlation. The model can provide predictions of daily \({\hbox {NO}}_{2}\) levels at both study sites and random sites that have no measurements at all. Application of this approach provides pollution estimates that make it possible to study short term relationships between \({\hbox {NO}}_{2}\) exposure and respiratory symptoms such as asthma severity. The approach also offers significant cost reduction for future studies of higher temporal/spatial resolution of air pollution levels by making effective use of readily available EPA monitoring site measurements and observations at spatially dispersed sites from epidemiological studies. The model is implemented under the Bayes framework with a Gibbs sampler.