Spatial measurement error and correction by spatial SIMEX in linear regression models when using predicted air pollution exposures.

Spatial modeling of air pollution exposures is widespread in air pollution epidemiology research as a way to improve exposure assessment. However, there are key sources of exposure model uncertainty when air pollution is modeled, including estimation error and model misspecification. We examine the use of predicted air pollution levels in linear health effect models under a measurement error framework. For the prediction of air pollution exposures, we consider a universal Kriging framework, which may include land-use regression terms in the mean function and a spatial covariance structure for the residuals. We derive the bias induced by estimation error and by model misspecification in the exposure model, and we find that a misspecified exposure model can induce asymptotic bias in the effect estimate of air pollution on health. We propose a new spatial simulation extrapolation (SIMEX) procedure, and we demonstrate that the procedure has good performance in correcting this asymptotic bias. We illustrate spatial SIMEX in a study of air pollution and birthweight in Massachusetts.

[1]  Linda J Young,et al.  A comparison of errors in variables methods for use in regression models with spatially misaligned data , 2011, Statistical methods in medical research.

[2]  Bert Brunekreef,et al.  Development of Land Use Regression models for PM(2.5), PM(2.5) absorbance, PM(10) and PM(coarse) in 20 European study areas; results of the ESCAPE project. , 2012, Environmental science & technology.

[3]  A. Peters,et al.  Particulate Matter Air Pollution and Cardiovascular Disease: An Update to the Scientific Statement From the American Heart Association , 2010, Circulation.

[4]  Itai Kloog,et al.  Using new satellite based exposure methods to study the association between pregnancy pm2.5 exposure, premature birth and birth weight in Massachusetts , 2012, Environmental Health.

[5]  R J Carroll,et al.  Transformations to additivity in measurement error models. , 1997, Biometrics.

[6]  Daniel Wartenberg,et al.  Maternal Exposure to Particulate Air Pollution and Term Birth Weight: A Multi-Country Evaluation of Effect and Heterogeneity , 2013, Environmental health perspectives.

[7]  Raymond J. Carroll,et al.  Bias Analysis and SIMEX Approach in Generalized Linear Mixed Measurement Error Models , 1998 .

[8]  Raymond J. Carroll,et al.  Measurement error in nonlinear models: a modern perspective , 2006 .

[9]  Michelle L. Bell,et al.  Ambient Air Pollution and Low Birth Weight in Connecticut and Massachusetts , 2007, Environmental health perspectives.

[10]  Noel A Cressie,et al.  Statistics for Spatial Data. , 1992 .

[11]  F. O. Hoffman,et al.  Shared Uncertainty in Measurement Error Problems, with Application to Nevada Test Site Fallout Data , 2007, Biometrics.

[12]  Jonathan I Levy,et al.  Land use regression modeling of intra-urban residential variability in multiple traffic-related air pollutants , 2008, Environmental health : a global access science source.

[13]  N. Cressie,et al.  Mean squared prediction error in the spatial linear model with estimated covariance parameters , 1992 .

[14]  J. R. Cook,et al.  Simulation-Extrapolation Estimation in Parametric Measurement Error Models , 1994 .

[15]  Kazuhiko Ito,et al.  A land use regression for predicting fine particulate matter concentrations in the New York City region , 2007 .

[16]  J. Schwartz,et al.  Incorporating local land use regression and satellite aerosol optical depth in a hybrid model of spatiotemporal PM2.5 exposures in the Mid-Atlantic states. , 2012, Environmental science & technology.

[17]  Francesca Dominici,et al.  Estimating the acute health effects of coarse particulate matter accounting for exposure measurement error. , 2011, Biostatistics.

[18]  Roger D Peng,et al.  Spatial misalignment in time series studies of air pollution and health data. , 2010, Biostatistics.

[19]  Kenneth K. Lopiano,et al.  Estimated generalized least squares in spatially misaligned regression models with Berkson error. , 2013, Biostatistics.

[20]  F. O. Hoffman,et al.  Semiparametric Regression Modeling with Mixtures of Berkson and Classical Error, with Application to Fallout from the Nevada Test Site , 2002, Biometrics.

[21]  Duanping Liao,et al.  GIS Approaches for the Estimation of Residential-Level Ambient PM Concentrations , 2006, Environmental Health Perspectives.

[22]  J. Schwartz,et al.  Estimating spatio-temporal resolved PM10 aerosol mass concentrations using MODIS satellite data and land use regression over Lombardy, Italy , 2013 .

[23]  Lianne Sheppard,et al.  Efficient measurement error correction with spatially misaligned data. , 2011, Biostatistics.

[24]  Lianne Sheppard,et al.  A National Prediction Model for PM2.5 Component Exposures and Measurement Error–Corrected Health Effect Inference , 2013, Environmental health perspectives.

[25]  Christopher J Paciorek,et al.  Measurement error in two‐stage analyses, with application to air pollution epidemiology , 2012, Environmetrics.

[26]  Mike Rees,et al.  5. Statistics for Spatial Data , 1993 .

[27]  David Ruppert,et al.  Regression with spatially misaligned data , 2008 .

[28]  Itai Kloog,et al.  Consequences of kriging and land use regression for PM2.5 predictions in epidemiologic analyses: insights into spatial variability using high-resolution satellite data , 2014, Journal of Exposure Science and Environmental Epidemiology.

[29]  A. Just,et al.  A New Hybrid Spatio-Temporal Model For Estimating Daily Multi-Year PM2.5 Concentrations Across Northeastern USA Using High Resolution Aerosol Optical Depth Data. , 2014, Atmospheric environment.

[30]  Noel A Cressie,et al.  Statistics for Spatial Data, Revised Edition. , 1994 .

[31]  Noel A. C. Cressie,et al.  Statistics for Spatial Data: Cressie/Statistics , 1993 .

[32]  Bert Brunekreef,et al.  Estimating Long-Term Average Particulate Air Pollution Concentrations: Application of Traffic Indicators and Geographic Information Systems , 2003, Epidemiology.

[33]  Joel Schwartz,et al.  Measurement error caused by spatial misalignment in environmental epidemiology. , 2009, Biostatistics.

[34]  J. Schwartz,et al.  Assessing temporally and spatially resolved PM2.5 exposures for epidemiological studies using satellite aerosol optical depth measurements , 2011 .