Advertisement

Bayesian Modeling of Spatial Data

  • Peter CongdonEmail author
Living reference work entry

Abstract

Bayesian inference and applications have been a central aspect in recent developments in spatial statistics. This influence has rested on advances in computer-based estimations via Markov Chain Monte Carlo including recent improvements to random walk MCMC approaches (e.g., Hamiltonian Monte Carlo). Bayesian ideas have been particularly influential in spatial econometrics, disease mapping, and analysis of point-referenced spatial data. Starting with models for univariate spatial data at a single time point, models can be extended to multivariate outcomes or to a space-time framework. Spatial models vary in how spatial dependence or correlation is represented, including neighborhood dependence in Markov fields models, explicit spatial decay in point-referenced spatial process models, and spatial lags or residual correlation effects in spatial autoregressive models. Aims of spatial analysis also differ, from ensuring regression analysis to allow for spatial dependence (spatial autoregressive models), to detecting disease clusters or elevated relative risk (disease mapping), to spatial prediction and interpolation (spatial process models). Bayesian implementation has been facilitated by a much improved computational environment centered on the R package.

Keywords

Spatial autoregressive Conditional autoregression Spatial process Point pattern Disease mapping Spatial covariance Point patterns 

References

  1. Anselin L, Bera A (1998) Spatial dependence in linear regression models with an introduction to spatial econometrics. In: Ullah A, Giles D (eds) Handbook of applied economic statistics. Marcel Dekker, New York, pp 237–289Google Scholar
  2. Bell B, Broemeling L (2000) A Bayesian analysis for spatial processes with application to disease mapping. Stat Med 19(7):957–974Google Scholar
  3. Bernardinelli L, Clayton D, Pascutto C, Montomoli C, Ghislandi M (1995) Bayesian Analysis of space-time variations in disease risk. Stat Med 14(21–22):2433–2443CrossRefGoogle Scholar
  4. Besag J, Kooperberg C (1995) On conditional and intrinsic autoregressions. Biometrika 82(4):733–746Google Scholar
  5. Besag J, York J, Mollie A (1991) Bayesian image restoration, with two applications in spatial statistics. Ann Inst Stat Math 43(1):1–20CrossRefGoogle Scholar
  6. Blangiardo M, Cameletti M, Baio G, Rue H (2013) Spatial and spatio-temporal models with R-INLA. Spat Spatio-Temp Epidemiol 4(1):33–49CrossRefGoogle Scholar
  7. Carroll C, Johnson D, Dunk J, Zielinski W (2010) Hierarchical Bayesian spatial models for multispecies conservation planning and monitoring. Conserv Biol 24(6):1538–1548CrossRefGoogle Scholar
  8. Casella G, George E (1992) Explaining the Gibbs sampler. Am Stat 46(3):167–174Google Scholar
  9. Debarsy N, Ertur C, Sage J (2012) Interpreting dynamic space–time panel data models. Stat Methodol 9(1–2):158–171CrossRefGoogle Scholar
  10. Diggle P, Ribeiro P (2007) Model-based Geostatistics. Springer Durmus, New YorkGoogle Scholar
  11. Durmus A, Roberts GO, Vilmart G, Zygalakis K (2017) Fast Langevin based algorithm for MCMC in high dimensions. Ann Appl Probab 27(4):2195–2237CrossRefGoogle Scholar
  12. Finley A, Banerjee S, Gelfand A (2015) spBayes for large univariate and multivariate point-referenced spatio-temporal data models. J Stat Softw 63(13):1–28CrossRefGoogle Scholar
  13. Finley, A, Datta A, Cook B, Morton D, Andersen H, Banerjee S (2017) Applying nearest neighbor Gaussian processes to massive spatial data sets: forest canopy height prediction across Tanana Valley Alaska. https://arxiv.org/abs/1702.00434
  14. Fischer M, LeSage J (2015) A Bayesian space-time approach to identifying and interpreting regional convergence clubs in Europe. Pap Reg Sci 94(4):677–702CrossRefGoogle Scholar
  15. Gelfand, A, Banerjee, S (2017) Bayesian modeling and analysis of geostatistical data. Annu Rev Stat Appl 4:245–266CrossRefGoogle Scholar
  16. Higdon D (2007) A primer on space-time modelling from a Bayesian perspective. Chapter 6. In: Finkelstadt B, Held L, Isham V (eds) Statistical methods for spatio-temporal systems. CRC Press, Hoboken, pp 218–280Google Scholar
  17. Hoffman M, Gelman A (2014) The No-U-Turn sampler: adaptively setting path lengths in Hamiltonian Monte Carlo. J Mach Learn Res 15(1):1593–1623Google Scholar
  18. Illian J, Martino S, Sørbye S, Gallego-Fern’andez J, Zunzunegui M, Esquivias M, Travis J (2013) Fitting complex ecological point process models with integrated nested Laplace approximation. Methods Ecol Evol 4(4):305–315CrossRefGoogle Scholar
  19. Irvine K, Gitelman A, Hoeting J (2007) Spatial design and properties of spatial correlation: effects on covariance estimation. J Agric Biol Environ Stat 12(4):1–20CrossRefGoogle Scholar
  20. Ismaila A, Canty A, Thabane L (2007) Comparison of Bayesian and frequentist approaches in modelling risk of preterm birth near the Sydney Tar Ponds, Nova Scotia, Canada. BMC Med Res Methodol 2007(Sep 10):7–39Google Scholar
  21. Kakamu K, Wago H (2008) Small-sample properties of panel spatial autoregressive models: comparison of the Bayesian and maximum likelihood methods. Spat Econ Anal 3(3):305–319CrossRefGoogle Scholar
  22. Kavanagh L, Lee D, Pryce G (2016) Is poverty decentralizing? Quantifying uncertainty in the decentralization of urban poverty. Ann Am Assoc Geogr 106(6):1286–1298Google Scholar
  23. Lagazio C, Dreassi E, Bernardinelli A (2001) A hierarchical Bayesian model for space-time variation of disease risk. Stat Model 1(1):17–29Google Scholar
  24. Lawson A, Clark A (2002) Spatial mixture relative risk models applied to disease mapping. Statistics in Medicine 21:359–370CrossRefGoogle Scholar
  25. Lee D (2011) A comparison of conditional autoregressive models used in Bayesian disease mapping. Spat Spatio-Temp Epidemiol 2(2):79–89CrossRefGoogle Scholar
  26. Leininger T, Gelfand A (2017) Bayesian inference and model assessment for spatial point patterns using posterior predictive samples. Bayesian Anal 12(1):1–30CrossRefGoogle Scholar
  27. Lindgren F, Rue H, Lindström J (2011) An explicit link between Gaussian fields and Gaussian Markov random fields: the stochastic partial differential equation approach. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 73(4):423–498CrossRefGoogle Scholar
  28. Ma B, Lawson A, Liu Y (2007) Evaluation of Bayesian models for focused clustering in health data. Environmetrics 18(8):871–887CrossRefGoogle Scholar
  29. Mardia K (1988) Multi-dimensional multivariate Gaussian Markov random fields with application to image processing. J Multivar Anal 24(2):265–284CrossRefGoogle Scholar
  30. Maule M, Magnani C, Dalmasso P, Mirabelli D, Merletti F, Biggeri A (2007) Modeling mesothelioma risk associated with environmental asbestos exposure. Environ Health Perspect 115(7):1066–1071CrossRefGoogle Scholar
  31. Mollie A (1996) Bayesian mapping of disease. In: Gilks W, Richardson S, Spiegel-halter DJ (eds) Markov chain Monte Carlo in practice. Chapman & Hall, London, pp 359–379Google Scholar
  32. Morris, M (2019) Spatial models in stan: intrinsic auto-regressive models for areal data. http://mc-stan.org/users/documentation/case-studies/icar_stan.html
  33. Opitz T (2017) Latent Gaussian modeling and INLA: a review with focus on space-time applications. J Fr Stat Soc 158(3):62–85Google Scholar
  34. Pace R, LeSage J (2010) Spatial econometrics. In: Gelfand A, Diggle P, Fuentes M, Guttorp P (eds) Handbook of spatial statistics. CRC Press, Boca Raton, pp 245–262CrossRefGoogle Scholar
  35. Ratcliffe J (2010) Crime mapping: spatial and temporal challenges. In: Piquero A, Wiesburd D (eds) Quantitative criminology. Springer, New York, pp 5–24CrossRefGoogle Scholar
  36. Richardson S, Thomson A, Best N, Elliott P (2004) Interpreting posterior relative risk estimates in disease-mapping studies. Environ Health Perspect 112(9):1016–1025CrossRefGoogle Scholar
  37. Riebler A, Sørbye S, Simpson D, Rue H (2016) An intuitive Bayesian spatial model for disease mapping that accounts for scaling. Stat Methods Med Res 25(4):145–1165CrossRefGoogle Scholar
  38. Rodrigues A, Assuncao R (2008) Propriety of posterior in Bayesian space varying parameter models with normal data. Statist Probab Lett 78(15):2408–2411CrossRefGoogle Scholar
  39. Smith T, LeSage J (2004) A bayesian probit model with spatial dependencies. In: LeSage JP, Pace RK (eds) Advances in Econometrics: Spatial and Spatiotemporal Econometrics. Elsevier Science 18:127–160Google Scholar
  40. Septier F, Peters G (2016) Langevin and Hamiltonian based sequential MCMC for efficient Bayesian filtering in high-dimensional spaces. J Sel Topics Sign Proces 10(2):312–327CrossRefGoogle Scholar
  41. Stern H, Cressie N (2000) Posterior predictive model checks for disease mapping models. Stat Med 19(17–18):2377–2397CrossRefGoogle Scholar
  42. Sun D, Tsutakawa RK, Speckman PL (1999) Posterior distribution of hierarchical models using CAR (1) distributions. Biometrika 86(2):341–350CrossRefGoogle Scholar
  43. Wakefield J, Morris S (2001) The Bayesian modeling of disease risk in relation to a point source. J Am Stat Assoc 96(453):77–91CrossRefGoogle Scholar
  44. Wheeler D, Waller L (2009) Comparing spatially varying coefficient models: a case study examining violent crime rates and their relationships to alcohol outlets and illegal drug arrests. J Geogr Syst 11(1):1–22CrossRefGoogle Scholar
  45. Yan J (2007) Spatial stochastic volatility for lattice data. J Agric Biol Environ Stat 12(1):25–40CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.School of GeographyQueen Mary University of LondonLondonUK

Personalised recommendations