Spatial regression with an informatively missing covariate: Application to mapping fine particulate matter

Grantham, Neal S.; Reich, Brian J.; Liu, Yang; Chang, Howard H.

doi:10.1002/env.2499

Cited by 8 publications

(7 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The average number of MISR retrievals is around 30 per year across grid cells, and regulatory monitors typically provide measurements every 6 days. To gap-fill predictions, recent studies for total PM 2.5 mass considered imputing total AOD that was informatively missing [ 38 , 39 ] and ensemble modeling that included members without AOD as a predictor [ 40 ]. Both approaches warrant further investigation for predicting PM 2.5 components and for BART.…”

Section: Discussionmentioning

confidence: 99%

Application of Bayesian Additive Regression Trees for Estimating Daily Concentrations of PM2.5 Components

et al. 2020

Self Cite

View full text Add to dashboard Cite

Bayesian additive regression tree (BART) is a recent statistical method that combines ensemble learning and nonparametric regression. BART is constructed under a probabilistic framework that also allows for model-based prediction uncertainty quantification. We evaluated the application of BART in predicting daily concentrations of four fine particulate matter (PM2.5) components (elemental carbon, organic carbon, nitrate, and sulfate) in California during the period 2005 to 2014. We demonstrate in this paper how BART can be tuned to optimize prediction performance and how to evaluate variable importance. Our BART models included, as predictors, a large suite of land-use variables, meteorological conditions, satellite-derived aerosol optical depth parameters, and simulations from a chemical transport model. In cross-validation experiments, BART demonstrated good out-of-sample prediction performance at monitoring locations (R2 from 0.62 to 0.73). More importantly, prediction intervals associated with concentration estimates from BART showed good coverage probability at locations with and without monitoring data. In our case study, major PM2.5 components could be estimated with good accuracy, especially when collocated PM2.5 total mass observations were available. In conclusion, BART is an attractive approach for modeling ambient air pollution levels, especially for its ability to provide uncertainty in estimates that may be useful for subsequent health impact and health effect analyses.

show abstract

Section: Discussionmentioning

confidence: 99%

Application of Bayesian Additive Regression Trees for Estimating Daily Concentrations of PM2.5 Components

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…AOD is a proxy measurement of particle air pollution data since it measures light extinction due to particles in the atmospheric column. We consider the regression model with PM 2.5 as the response variable and AOD as the covariate since AOD was shown in previous studies to have positive impacts on PM 2.5 (Chu et al, 2016;Grantham et al, 2018;Ma et al, 2016;Yu et al, 2017). The study domain covers the Northeastern United States (Connecticut, Delaware, Maine, Maryland, Massachusetts, New Hampshire, New Jersey, New York, Pennsylvania, Rhode Island, Vermont, and District of Columbia), which is defined by the National Climatic Data Center (Karl & Koss, 1984).…”

Section: Data Applicationmentioning

confidence: 99%

“…The satellite-derived aerosol optical depth (AOD) is a proxy measurement of particle air pollution data since it measures light extinction due to particles (e.g., dust, smoke, pollution) in the atmospheric column. Previous studies showed that PM 2.5 concentrations have positive associations with AOD (Chu et al, 2016;Grantham et al, 2018;Ma et al, 2016;Yu et al, 2017). For spatial data, it is often assumed that regression coefficients are homogeneous across the entire spatial domain of interest.…”

Section: Introductionmentioning

confidence: 99%

Spatial cluster detection with threshold quantile regression

2021

View full text Add to dashboard Cite

Spatial cluster detection, which is the identification of spatial units adjacent in space associated with distinctive patterns of data of interest relative to background variation, is useful for discerning spatial heterogeneity in regression coefficients. Some real studies with regression-based models on air quality data show that there exists not only spatial heterogeneity but also heteroscedasticity between air pollution and its predictors. Since the low air quality is a well-known risk factor for mortality, various cardiopulmonary diseases, and preterm birth, the analysis at the tail would be of more interest than the center of air pollution distribution. In this article, we develop a spatial cluster detection approach using a threshold quantile regression model to capture the spatial heterogeneity and heteroscedasticity. We introduce two threshold variables in the quantile regression model to define a spatial cluster. The proposed test statistic for identifying the spatial cluster is the supremum of the Wald process over the space of threshold parameters. We establish the limiting distribution of the test statistic under the null hypothesis that the quantile regression coefficient is the same over the entire spatial domain at the given quantile level. The performance of our proposed method is assessed by simulation studies. The proposed method is also applied to analyze the particulate matter (PM 2.5 ) concentration and aerosol optical depth (AOD) data in the Northeastern United States in order to study geographical heterogeneity in the association between AOD and PM 2.5 at different quantile levels.

show abstract

“…Previous studies on predicting PM 2.5 concentration from AOD were reviewed by Chu et al (2016). In addition, those regression-based models showed that PM 2.5 concentrations have positive relationships with AOD (Chang, Hu, & Liu, 2013;Grantham, Reich, Liu, & Chang, 2018;Kloog, Koutrakis, Coull, Lee, & Schwartz, 2011;Kloog, Nordio, Coull, & Schwartz, 2012;Lee, Liu, Coull, Schwartz, & Koutrakis, 2011;Liu, Sarnat, Kilaru, Jacob, & Koutrakis, 2005;Ma et al, 2016;Paciorek, Liu, Moreno-Macias, & Kondragunta, 2008;Yu, Liu, Ma, & Bi, 2017) because AOD measures light extinction due to particles (e.g., dust, smoke, and pollution) in the atmospheric column. We also obtain satellite-measured AOD data for the Northeastern United States from the Moderate Resolution Imaging Spectroradiometer in order to investigate its relationship to the PM 2.5 concentrations in the fused CMAQ data via our mixed-effects model with spatial block-wise random effects.…”

Section: Data Descriptionmentioning

confidence: 99%

Spatial cluster detection of regression coefficients in a mixed‐effects model

2019

Self Cite

View full text Add to dashboard Cite

Identifying spatial clusters of different regression coefficients is a useful tool for discerning the distinctive relationship between a response and covariates in space. Most of the existing cluster detection methods aim to identify the spatial similarity in responses, and the standard cluster detection algorithm assumes independent spatial units. However, the response variables are spatially correlated in many environmental applications. We propose a mixed‐effects model for spatial cluster detection that takes spatial correlation into account. Compared to a fixed‐effects model, the introduced random effects explain extra variability among the spatial responses beyond the cluster effect, thus reducing the false positive rate. The developed method exploits a sequential searching scheme and is able to identify multiple potentially overlapping clusters. We use simulation studies to evaluate the performance of our proposed method in terms of the true and false positive rates of a known cluster and the identification of multiple known clusters. We apply our proposed methodology to particulate matter (PM2.5) concentration data from the Northeastern United States in order to study the weather effect on PM2.5 and to investigate the association between the simulations from a numerical model and the satellite‐derived aerosol optical depth data. We find geographical hot spots that show distinct features, comparing to the background.

show abstract

Spatial regression with an informatively missing covariate: Application to mapping fine particulate matter

Cited by 8 publications

References 29 publications

Application of Bayesian Additive Regression Trees for Estimating Daily Concentrations of PM2.5 Components

Application of Bayesian Additive Regression Trees for Estimating Daily Concentrations of PM2.5 Components

Spatial cluster detection with threshold quantile regression

Spatial cluster detection of regression coefficients in a mixed‐effects model

Contact Info

Product

Resources

About