Improved inference for areal unit count data using graph-based optimisation

Spatial correlation in areal unit count data is typically modelled by a set of random effects that are assigned a conditional autoregressive (CAR) prior distribution. The spatial correlation structure implied by this model depends on a binary neighbourhood matrix, where two random effects are assumed to be partially autocorrelated if their areal units share a common border, and are conditionally independent otherwise. This paper proposes a novel graph-based optimisation algorithm for estimating the neighbourhood matrix from the data, by viewing the areal units as the vertices of the graph and the neighbour relations as the set of edges. The superiority of our methodology compared to using the border sharing rule is comprehensively evidenced by simulation, before the method is applied to a new respiratory disease surveillance study in the Greater Glasgow and Clyde Health board in Scotland between 2011 and 2017.

[1]  Geoffrey M. Jacquez,et al.  From fields to objects: A review of geographic boundary analysis , 2000, J. Geogr. Syst..

[2]  Duncan Lee,et al.  Boundary detection in disease mapping studies. , 2011, Biostatistics.

[3]  Duncan Lee,et al.  Estimating the health impact of air pollution in Scotland, and the resulting benefits of reducing concentrations in city centres. , 2019, Spatial and spatio-temporal epidemiology.

[4]  Bradley P. Carlin,et al.  Hierarchical Spatio-Temporal Mapping of Disease Rates , 1997 .

[5]  B. Carlin,et al.  Hierarchical and Joint Site-edge Methods for Medicare Hospice Service Region Boundary Analysis Hierarchical and Joint Site-edge Methods for Medicare Hospice Service Region Boundary Analysis , 2006 .

[6]  Duncan Lee,et al.  Estimating the changing nature of Scotland's health inequalities by using a multivariate spatiotemporal model , 2019, Journal of the Royal Statistical Society. Series A,.

[7]  S. Martino.  Approximate Bayesian Inference for Latent Gaussian Models , 2007 .

[8]  Anthony N. Pettitt,et al.  Comment on the paper: ‘Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations’ by Rue, H. Martino, S. and Chopin, N. , 2009 .

[9]  Jonathan R. Bradley,et al.  Bayesian Spatial Change of Support for Count-Valued Survey Data With Application to the American Community Survey , 2014, 1405.7227.

[10]  Oliver Stoner,et al.  A Hierarchical Framework for Correcting Under-Reporting in Count Data , 2018, Journal of the American Statistical Association.

[11]  W. H. Womble,et al.  Differential systematics. , 1951, Science.

[12]  Harrison Quick,et al.  Multivariate spatiotemporal modeling of age-specific stroke mortality , 2017 .

[13]  Duncan Lee,et al.  A spatio-temporal model for estimating the long-term effects of air pollution on respiratory hospital admissions in Greater London. , 2014, Spatial and spatio-temporal epidemiology.

[14]  J. Besag,et al.  Bayesian image restoration, with two applications in spatial statistics , 1991 .

[15]  Norman E. Breslow,et al.  Estimation of Disease Rates in Small Areas: A new Mixed Model for Spatial Dependence , 2000 .

[16]  D Walsh,et al.  History, politics and vulnerability: explaining excess mortality in Scotland and Glasgow. , 2017, Public health.

[17]  Duncan Lee,et al.  Spatio-Temporal Areal Unit Modeling in R with Conditional Autoregressive Priors Using the CARBayesST Package , 2018 .

[18]  D. Clayton,et al.  Bayesian analysis of space-time variation in disease risk. , 1995, Statistics in medicine.

[19]  Duncan Lee,et al.  Is There Really a “Wrong Side of the Tracks”in Urban Areas and Does It Matter for Spatial Analysis? , 2014 .

[20]  Chris Robertson,et al.  Syndromic surveillance of influenza‐like illness in Scotland during the influenza A H1N1v pandemic and beyond , 2012 .

[21]  Duncan Lee,et al.  A comparison of conditional autoregressive models used in Bayesian disease mapping. , 2011, Spatial and spatio-temporal epidemiology.

[22]  L Knorr-Held,et al.  Bayesian Detection of Clusters and Discontinuities in Disease Maps , 2000, Biometrics.

[23]  Bradley P. Carlin,et al.  Bayesian areal wombling for geographical boundary analysis , 2005 .

[24]  Samuel I. Berchuck,et al.  Diagnosing Glaucoma Progression With Visual Field Data Using a Spatiotemporal Boundary Detection Method , 2018, Journal of the American Statistical Association.

[25]  Andrew B Lawson,et al.  Conditional predictive inference for online surveillance of spatial disease incidence. , 2011, Statistics in medicine.

[26]  L Knorr-Held,et al.  Bayesian modelling of inseparable space-time variation in disease risk. , 2000, Statistics in medicine.