The importance of scale for spatial-confounding bias and precision of spatial regression estimators
From MaRDI portal
Publication:903318
DOI10.1214/10-STS326zbMATH Open1328.62596arXiv1011.1139WikidataQ42721906 ScholiaQ42721906MaRDI QIDQ903318FDOQ903318
Authors: Christopher J. Paciorek 
Publication date: 5 January 2016
Published in: Statistical Science (Search for Journal in Brave)
Abstract: Residuals in regression models are often spatially correlated. Prominent examples include studies in environmental epidemiology to understand the chronic health effects of pollutants. I consider the effects of residual spatial structure on the bias and precision of regression coefficients, developing a simple framework in which to understand the key issues and derive informative analytic results. When unmeasured confounding introduces spatial structure into the residuals, regression models with spatial random effects and closely-related models such as kriging and penalized splines are biased, even when the residual variance components are known. Analytic and simulation results show how the bias depends on the spatial scales of the covariate and the residual: one can reduce bias by fitting a spatial model only when there is variation in the covariate at a scale smaller than the scale of the unmeasured confounding. I also discuss how the scales of the residual and the covariate affect efficiency and uncertainty estimation when the residuals are independent of the covariate. In an application on the association between black carbon particulate matter air pollution and birth weight, controlling for large-scale spatial variation appears to reduce bias from unmeasured confounders, while increasing uncertainty in the estimated pollution effect.
Full work available at URL: https://arxiv.org/abs/1011.1139
Recommendations
- Spatial+: A novel approach to spatial confounding
- scientific article; zbMATH DE number 1487689
- Adding spatially-correlated errors can mess up the fixed effect you love
- An approach to the estimation of chronic air pollution effects using spatio-temporal information
- Sensitivity Analyses for Ecological Regression
Nonparametric estimation (62G05) Inference from spatial processes (62M30) Applications of statistics to biology and medical sciences; meta analysis (62P10) Medical applications (general) (92C50) Estimation in multivariate analysis (62H12) Applications of statistics to environmental and related topics (62P12)
Cites Work
- Semiparametric Regression
- Generalized additive models. An introduction with R.
- Statistical Methods for Spatial Data Analysis
- Asymptotic properties of penalized spline estimators
- Approximate Inference in Generalized Linear Mixed Models
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Disease mapping and spatial regression with count data
- Adding spatially-correlated errors can mess up the fixed effect you love
- Applied Spatial Statistics for Public Health Data
- Convergence rates for partially splined models
- Effects of Residual Smoothing on the Posterior of the Fixed Effects in Disease‐Mapping Models
- Linear smoothers and additive models
- A Nonstationary Negative Binomial Time Series With Time-Dependent Covariates
- Improved Semiparametric Time Series Models of Air Pollution and Mortality
- Statistical methods in spatial epidemiology.
- Semiparametric Latent Variable Regression Models for Spatiotemporal Modelling of Mobile Source Particles in the Greater Boston Area
- The Performance of Random Coefficient Regression in Accounting for Residual Confounding
- A Spatial Model for the Needle Losses of Pine-Trees in the Forests of Baden-Württemberg: An Application of Bayesian Structured Additive Regression
Cited In (41)
- The Bayesian group Lasso for confounded spatial data
- Restricted spatial regression in practice: geostatistical models, confounding, and robustness under model misspecification
- Rejoinder
- On the Effects of Spatial Confounding in Hierarchical Models
- Controlling for unmeasured confounding and spatial misalignment in long‐term air pollution and health studies
- Spatial Confounding in Generalized Estimating Equations
- Additive multivariate Gaussian processes for joint species distribution modeling with heterogeneous data
- Adding spatially-correlated errors can mess up the fixed effect you love
- A generalized Gaussian process model for computer experiments with binary time series
- Optimal model average prediction in orthogonal kriging models
- Spatial regression with covariate measurement error: a semiparametric approach
- Spatial regression and spillover effects in cluster randomized trials with count outcomes
- Discussion on “Spatial+: A novel approach to spatial confounding” by Dupont, Wood, and Augustin
- Discussion on “Spatial+: A novel approach to spatial confounding” by Emiko Dupont, Simon N. Wood, and Nicole H. Augustin
- Measurement error in air pollution epidemiology: guidance for uncertain times
- Spatial cluster detection of regression coefficients in a mixed-effects model
- Modeling Dependence in Spatio-Temporal Econometrics
- A Bayesian spatial hierarchical model for extreme precipitation in Great Britain
- Analyzing environmental-trait interactions in ecological communities with fourth-corner latent variable models
- A double fixed rank kriging approach to spatial regression models with covariate measurement error
- Improving piecewise linear snow density models through hierarchical spatial and orthogonal functional smoothing
- Mitigating spatial confounding by explicitly correlating Gaussian random fields
- Geostatistical Methods for Disease Mapping and Visualisation Using Data from Spatio‐temporally Referenced Prevalence Surveys
- A class of covariate-dependent spatiotemporal covariance functions for the analysis of daily ozone concentration
- Structural Equation Models for Dealing With Spatial Confounding
- Accounting for Location Measurement Error in Imaging Data With Application to Atomic Resolution Images of Crystalline Materials
- A Review of Spatial Causal Inference Methods for Environmental and Epidemiological Applications
- Spatially explicit survival modeling for small area cancer data
- Population counts along elliptical habitat contours: hierarchical modeling using Poisson-lognormal mixtures with nonstationary spatial structure
- Bayesian 2-stage space-time mixture modeling with spatial misalignment of the exposure in small area health data
- On estimation and selection of autologistic regression models via penalized pseudolikelihood
- A Bayesian localized conditional autoregressive model for estimating the health effects of air pollution
- Modeling complex spatial dependencies: low-rank spatially varying cross-covariances with application to soil nutrient data
- Spatiotemporal event studies for environmental data under cross-sectional dependence: an application to air quality assessment in Lombardy
- On Deconfounding Spatial Confounding in Linear Models
- Evaluating recent methods to overcome spatial confounding
- Mitigating unobserved spatial confounding when estimating the effect of supermarket access on cardiovascular disease deaths
- Restricted Spatial Regression Methods: Implications for Inference
- Spatial+: A novel approach to spatial confounding
- Estimation and selection for spatial confounding regression models
- Alleviating spatial confounding for areal data problems by displacing the geographical centroids
Uses Software
This page was built for publication: The importance of scale for spatial-confounding bias and precision of spatial regression estimators
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q903318)
