Spatio-temporal areal unit modeling in R with conditional autoregressive priors using the CARBayesST package

Duncan Lee, Alastair Rushworth, Gary Napier

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Spatial data relating to non-overlapping areal units are prevalent in fields such as economics, environmental science, epidemiology and social science, and a large suite of modeling tools have been developed for analysing these data. Many utilize conditional autoregressive (CAR) priors to capture the spatial autocorrelation inherent in these data, and software packages such as CARBayes and R-INLA have been developed to make these models easily accessible to others. Such spatial data are typically available for multiple time periods, and the development of methodology for capturing temporally changing spatial dynamics is the focus of much current research. A sizeable proportion of this literature has focused on extending CAR priors to the spatio-temporal domain, and this article presents the R package CARBayesST, which is the first dedicated software package for spatio-temporal areal unit modeling with conditional autoregressive priors. The software package allows to fit a range of models focused on different aspects of spacetime modeling, including estimation of overall space and time trends, and the identification of clusters of areal units that exhibit elevated values. This paper outlines the class of models that the software package implement, before applying them to simulated and two real examples from the fields of epidemiology and housing market analysis.
LanguageEnglish
Pages1-39
Number of pages39
JournalJournal of Statistical Software
Volume84
Issue number9
DOIs
Publication statusPublished - 20 Apr 2018

Fingerprint

Software Package
Software packages
Epidemiology
Unit
Spatial Data
Modeling
Spatial Autocorrelation
Social sciences
Social Sciences
Autocorrelation
Proportion
Space-time
Model
Economics
Methodology
Computer simulation
Range of data
Software

Keywords

  • Bayesian inference
  • conditional autoregressive priors
  • R package
  • spatio-temporal areal unit modeling

Cite this

@article{f3c9ec7c955a4f8b882f7578dd1c3b50,
title = "Spatio-temporal areal unit modeling in R with conditional autoregressive priors using the CARBayesST package",
abstract = "Spatial data relating to non-overlapping areal units are prevalent in fields such as economics, environmental science, epidemiology and social science, and a large suite of modeling tools have been developed for analysing these data. Many utilize conditional autoregressive (CAR) priors to capture the spatial autocorrelation inherent in these data, and software packages such as CARBayes and R-INLA have been developed to make these models easily accessible to others. Such spatial data are typically available for multiple time periods, and the development of methodology for capturing temporally changing spatial dynamics is the focus of much current research. A sizeable proportion of this literature has focused on extending CAR priors to the spatio-temporal domain, and this article presents the R package CARBayesST, which is the first dedicated software package for spatio-temporal areal unit modeling with conditional autoregressive priors. The software package allows to fit a range of models focused on different aspects of spacetime modeling, including estimation of overall space and time trends, and the identification of clusters of areal units that exhibit elevated values. This paper outlines the class of models that the software package implement, before applying them to simulated and two real examples from the fields of epidemiology and housing market analysis.",
keywords = "Bayesian inference, conditional autoregressive priors, R package, spatio-temporal areal unit modeling",
author = "Duncan Lee and Alastair Rushworth and Gary Napier",
year = "2018",
month = "4",
day = "20",
doi = "10.18637/jss.v084.i09",
language = "English",
volume = "84",
pages = "1--39",
journal = "Journal of Statistical Software",
issn = "1548-7660",
number = "9",

}

Spatio-temporal areal unit modeling in R with conditional autoregressive priors using the CARBayesST package. / Lee, Duncan; Rushworth, Alastair; Napier, Gary.

In: Journal of Statistical Software, Vol. 84, No. 9, 20.04.2018, p. 1-39.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Spatio-temporal areal unit modeling in R with conditional autoregressive priors using the CARBayesST package

AU - Lee, Duncan

AU - Rushworth, Alastair

AU - Napier, Gary

PY - 2018/4/20

Y1 - 2018/4/20

N2 - Spatial data relating to non-overlapping areal units are prevalent in fields such as economics, environmental science, epidemiology and social science, and a large suite of modeling tools have been developed for analysing these data. Many utilize conditional autoregressive (CAR) priors to capture the spatial autocorrelation inherent in these data, and software packages such as CARBayes and R-INLA have been developed to make these models easily accessible to others. Such spatial data are typically available for multiple time periods, and the development of methodology for capturing temporally changing spatial dynamics is the focus of much current research. A sizeable proportion of this literature has focused on extending CAR priors to the spatio-temporal domain, and this article presents the R package CARBayesST, which is the first dedicated software package for spatio-temporal areal unit modeling with conditional autoregressive priors. The software package allows to fit a range of models focused on different aspects of spacetime modeling, including estimation of overall space and time trends, and the identification of clusters of areal units that exhibit elevated values. This paper outlines the class of models that the software package implement, before applying them to simulated and two real examples from the fields of epidemiology and housing market analysis.

AB - Spatial data relating to non-overlapping areal units are prevalent in fields such as economics, environmental science, epidemiology and social science, and a large suite of modeling tools have been developed for analysing these data. Many utilize conditional autoregressive (CAR) priors to capture the spatial autocorrelation inherent in these data, and software packages such as CARBayes and R-INLA have been developed to make these models easily accessible to others. Such spatial data are typically available for multiple time periods, and the development of methodology for capturing temporally changing spatial dynamics is the focus of much current research. A sizeable proportion of this literature has focused on extending CAR priors to the spatio-temporal domain, and this article presents the R package CARBayesST, which is the first dedicated software package for spatio-temporal areal unit modeling with conditional autoregressive priors. The software package allows to fit a range of models focused on different aspects of spacetime modeling, including estimation of overall space and time trends, and the identification of clusters of areal units that exhibit elevated values. This paper outlines the class of models that the software package implement, before applying them to simulated and two real examples from the fields of epidemiology and housing market analysis.

KW - Bayesian inference

KW - conditional autoregressive priors

KW - R package

KW - spatio-temporal areal unit modeling

UR - https://www.jstatsoft.org/index

U2 - 10.18637/jss.v084.i09

DO - 10.18637/jss.v084.i09

M3 - Article

VL - 84

SP - 1

EP - 39

JO - Journal of Statistical Software

T2 - Journal of Statistical Software

JF - Journal of Statistical Software

SN - 1548-7660

IS - 9

ER -