Original Articles Open access

Bayesian hierarchical spatial models for disease mapping in the presence of missing covariates

Authors

Published
20 August 2026
Section
Original Articles

Abstract

Bayesian spatial models for disease mapping, such as Besag-York-Mollié (BYM) models, are widely used to model disease counts while accounting for spatial dependence. However, these models are not equipped to handle missing covariate values. Covariates are often partially observed, yet these models require separate imputation that ignores imputation uncertainty. We extend this Bayesian framework for disease mapping to accommodate missing covariates while modeling the disease counts. Missing covariate values are treated as unknown parameters that are estimated simultaneously with the other model’s parameters within the same Bayesian model. Evaluation on the benchmark Scottish lip cancer dataset demonstrates that the proposed model is effective in recovering the parameters of interest, compared with the complete-data BYM2 model under low-to-moderate missingness in a covariate.

Ethics Approval

Not applicable.

Data Availability Statement

The Scottish lip cancer data used in this study are available from the published article(Clayton and Kaldor, 1987) . The data were sourced from the scotland_data.R script provided in the Stan example models repository (Stan Development Team) available at: https://github.com/stan-dev/example-models/blob/master/knitr/car-iar-poisson/scotland_data.R). The North Carolina SIDS dataset available in the published article (Cressie and Chan, 1989) can be accessed via the `sf` R package (Pebesma, 2018) using the following command: nc <- sf::st_read(system.file ("shape/nc.shp", package, "sf"))

References

  1. Besag J, York J, Mollié A, 1991. Bayesian image restoration, with two applications in spatial statistics. Ann Inst Stat Math 43:1–20. DOI: https://doi.org/10.1007/BF00116466
  2. Best N, Richardson S, Thomson A, 2005. A comparison of Bayesian spatial models for disease mapping. Stat Methods Med Res 14:35–59. DOI: https://doi.org/10.1191/0962280205sm388oa
  3. Bhakkan-Mambir B, Luce D, Deloumeaux J, 2025. Cancer incidence in the vicinity of open landfills in Guadeloupe, French West Indies. BMC Public Health 25:1–8. DOI: https://doi.org/10.1186/s12889-025-22896-w
  4. Cifo D, Estévez-Reboredo RM, González-Barrio D, Jado I, Gómez-Barroso D, 2024. Epidemiology of Q fever in humans in four selected regions, Spain, 2016 to 2022. Eurosurveillance 29:2300688. DOI: https://doi.org/10.2807/1560-7917.ES.2024.29.27.2300688
  5. Clayton D, Kaldor J, 1987. Empirical Bayes estimates of age-standardized relative risks for use in disease mapping. Biometrics 43:671-81. DOI: https://doi.org/10.2307/2532003
  6. Cressie N, Chan NH, 1989. Spatial modeling of regional variables. J Am Stat Assoc 84:393–401. DOI: https://doi.org/10.1080/01621459.1989.10478783
  7. Dean CB, Ugarte MD, Militino AF, 2001. Detecting interaction between random region and fixed age effects in disease mapping. Biometrics 57:197–202. DOI: https://doi.org/10.1111/j.0006-341X.2001.00197.x
  8. Haque S, Price A, Mengersen K, Hu W, 2025. Evaluating the impact of the modifiable areal unit problem on ecological model inference: a case study of COVID-19 data in Queensland, Australia. Infect Dis Model 10:1002-19. DOI: https://doi.org/10.1016/j.idm.2025.05.003
  9. Lee D, 2011. A comparison of conditional autoregressive models used in Bayesian disease mapping. Spat Spatiotemporal Epidemiol 2:79–89. DOI: https://doi.org/10.1016/j.sste.2011.03.001
  10. Leroux BG, Lei X, Breslow N, 2000. Estimation of disease rates in small areas: a new mixed model for spatial dependence. Statistical models in epidemiology, the environment, and clinical trials, New York, pp. 179-191. DOI: https://doi.org/10.1007/978-1-4612-1284-3_4
  11. Leveau CM, Riancho J, Shaman J, Santurtún A, 2024. Spatial analysis of ischemic stroke in Spain: the roles of accessibility to healthcare and economic development. Cad Saude Publica 40:e00212923. DOI: https://doi.org/10.1590/0102-311xen212923
  12. Ma Z, Hu G, Chen MH, 2021. Bayesian hierarchical spatial regression models for spatial data in the presence of missing covariates with applications. Appl Stoch Models Bus Ind 37:342–59. DOI: https://doi.org/10.1002/asmb.2568
  13. MacNab YC, 2011. On Gaussian Markov random fields and Bayesian disease mapping. Stat Methods Med Res 20:49–68. DOI: https://doi.org/10.1177/0962280210371561
  14. Morris M, 2019. spatial models in stan: intrinsic auto-regressive models for areal data. Stan case study. Accessed 1 January 2026. Available from: https://mc-stan.org/learn-stan/case-studies/icar_stan.html
  15. Morris M, Wheeler-Martin K, Simpson D, Mooney SJ, Gelman A, DiMaggio C, 2019. Bayesian hierarchical spatial models: Implementing the Besag York Mollié model in stan. Spat Spatiotemporal Epidemiol 31:100301. DOI: https://doi.org/10.1016/j.sste.2019.100301
  16. Simpson D, Rue H, Riebler A, Martins TG, Sørbye SH, 2017. Penalising model component complexity: A principled, practical approach to constructing priors. Statist Sci 32: 1-28 DOI: https://doi.org/10.1214/16-STS576
  17. Slater JJ, Brown PE, Rosenthal JS, Mateu J, 2022. Capturing spatial dependence of COVID-19 case counts with cellphone mobility data. Spat Stat 49:100540. DOI: https://doi.org/10.1016/j.spasta.2021.100540
  18. Vehtari A, Gelman A, Simpson D, Carpenter B, Bürkner PC, 2021. Rank-normalization, folding, and localization: An improved R ̂ for assessing convergence of MCMC. Bayesian analysis 16:667-718 DOI: https://doi.org/10.1214/20-BA1221
  19. Wakefield J, 2007. Disease mapping and spatial regression with count data. Biostatistics 8:158–83. DOI: https://doi.org/10.1093/biostatistics/kxl008

Metrics

Citations and online attention from Dimensions, Altmetric and PlumX.