Bayesian hierarchical spatial models: Implementing the Besag York Mollié model in stan - PubMed (original) (raw)
Bayesian hierarchical spatial models: Implementing the Besag York Mollié model in stan
Mitzi Morris et al. Spat Spatiotemporal Epidemiol. 2019 Nov.
Abstract
This report presents a new implementation of the Besag-York-Mollié (BYM) model in Stan, a probabilistic programming platform which does full Bayesian inference using Hamiltonian Monte Carlo (HMC). We review the spatial auto-correlation models used for areal data and disease risk mapping, and describe the corresponding Stan implementations. We also present a case study using Stan to fit a BYM model for motor vehicle crashes injuring school-age pedestrians in New York City from 2005 to 2014 localized to census tracts. Stan efficiently fit our multivariable BYM model having a large number of observations (n=2095 census tracts) with small outcome counts < 10 in the majority of tracts. Our findings reinforced that neighborhood income and social fragmentation are significant correlates of school-age pedestrian injuries. We also observed that nationally-available census tract estimates of commuting methods may serve as a useful indicator of underlying pedestrian densities.
Keywords: Bayesian inference; Besag-York-Mollié model; Intrinsic conditional auto-regressive model; Pedestrian injuries; Probabilistic programming; Stan.
Copyright © 2019 Elsevier Ltd. All rights reserved.
Figures
Listing 1:
Program icar.stan
Listing 2:
Program bym2.stan
Figure 1:
Correlation Matrix for NYC Census Tracts ordered by Borough, Tract ID
Figure 2:
Correlations Between Queens and Staten Island Census Tracts
Figure 3:
School age pedestrians injured in traffic crashes, NYC 2005–2014
Figure 4:
Histogram of school-age pedestrian injury counts per census tract, NYC 2005–2014
Figure 5:
Posterior Predictive Check, density overlay
Figure 6:
Posterior Predictive Check, test statistic
Figure 7:
Per-tract injuries, actual counts vs. fitted BYM2 model estimates
Figure 8:
Fitted BYM2 model estimated counts of school-age pedestrian crash injuries, 2005–2014
Similar articles
- Small-area spatiotemporal analysis of pedestrian and bicyclist injuries in New York City.
DiMaggio C. DiMaggio C. Epidemiology. 2015 Mar;26(2):247-54. doi: 10.1097/EDE.0000000000000222. Epidemiology. 2015. PMID: 25643104 - A Poisson-lognormal conditional-autoregressive model for multivariate spatial analysis of pedestrian crash counts across neighborhoods.
Wang Y, Kockelman KM. Wang Y, et al. Accid Anal Prev. 2013 Nov;60:71-84. doi: 10.1016/j.aap.2013.07.030. Epub 2013 Aug 21. Accid Anal Prev. 2013. PMID: 24036167 - Revisiting Gaussian Markov random fields and Bayesian disease mapping.
MacNab YC. MacNab YC. Stat Methods Med Res. 2023 Jan;32(1):207-225. doi: 10.1177/09622802221129040. Epub 2022 Nov 1. Stat Methods Med Res. 2023. PMID: 36317373 Free PMC article. Review. - Evaluating the informativeness of the Besag-York-Mollié CAR model.
Quick H, Song G, Tabb LP. Quick H, et al. Spat Spatiotemporal Epidemiol. 2021 Jun;37:100420. doi: 10.1016/j.sste.2021.100420. Epub 2021 Mar 27. Spat Spatiotemporal Epidemiol. 2021. PMID: 33980402 - Macro-level vulnerable road users crash analysis: A Bayesian joint modeling approach of frequency and proportion.
Cai Q, Abdel-Aty M, Lee J. Cai Q, et al. Accid Anal Prev. 2017 Oct;107:11-19. doi: 10.1016/j.aap.2017.07.020. Epub 2017 Jul 25. Accid Anal Prev. 2017. PMID: 28753415 Review.
Cited by
- Patient- and Areal-Level Risk Factors Associated With Lung Cancer Mortality in Victoria, Australia: A Bayesian Spatial Survival Analysis.
Tesema GA, Stirling RG, Tessema ZT, Heritier S, Earnest A. Tesema GA, et al. Cancer Med. 2024 Oct;13(19):e70293. doi: 10.1002/cam4.70293. Cancer Med. 2024. PMID: 39382193 Free PMC article. - Spatio-temporal distributions of COVID-19 vaccine doses uptake in the Netherlands: a Bayesian ecological modelling analysis.
Wang H, Varol T, Gültzow T, Zimmermann HML, Ruiter RAC, Jonas KJ. Wang H, et al. Epidemiol Infect. 2024 Oct 7;152:e119. doi: 10.1017/S0950268824001249. Epidemiol Infect. 2024. PMID: 39370683 Free PMC article. - Assessing and correcting neighborhood socioeconomic spatial sampling biases in citizen science mosquito data collection.
Padilla-Pozo Á, Bartumeus F, Montalvo T, Sanpera-Calbet I, Valsecchi A, Palmer JRB. Padilla-Pozo Á, et al. Sci Rep. 2024 Sep 28;14(1):22462. doi: 10.1038/s41598-024-73416-6. Sci Rep. 2024. PMID: 39341898 Free PMC article. - The spike-and-slab lasso and scalable algorithm to accommodate multinomial outcomes in variable selection problems.
Leach JM, Yi N, Aban I, The Alzheimer's Disease Neuroimaging Initiative. Leach JM, et al. J Appl Stat. 2023 Sep 14;51(11):2039-2061. doi: 10.1080/02664763.2023.2258301. eCollection 2024. J Appl Stat. 2023. PMID: 39157266 Free PMC article. - Impact of Indoor Radon Exposure on Lung Cancer Incidence in Slovenia.
Birk M, Žagar T, Tomšič S, Lokar K, Mihor A, Bric N, Mlakar M, Zadnik V. Birk M, et al. Cancers (Basel). 2024 Apr 9;16(8):1445. doi: 10.3390/cancers16081445. Cancers (Basel). 2024. PMID: 38672527 Free PMC article.
References
- “American Factfinder.” n.d. US Census Bureau. https://factfinder.census.gov/faces/nav/jsf/pages/index.xhtml.
- “Annual Average Daily Traffic (Aadt): Beginning 1977.” n.d. New York State Department of Transportation, Highway Data Services Bureau. http://data.ny.gov/Transportation/Annual-Average-Daily-Traffic-AADT-by-R....
- Bernardinelli L, Clayton D, and Montomoli C. 1995. “Bayesian Estimates of Disease Maps: How Important Are Priors?” Statistics in Medicine 14 (21–22). Wiley Online Library: 2411–31. - PubMed
- Besag Julian. 1974. “Spatial Interaction and the Statistical Analysis of Lattice Systems” Journal of the Royal Statistical Society. Series B (Methodological). JSTOR, 192–236.
- Besag J, York J, and Mollié A. 1991. “Bayesian Image Restoration with Two Applications in Spatial Statistics.” Ann Inst Stat Math 43: 1–59. https://doi.org/10.1007.
MeSH terms
LinkOut - more resources
Full Text Sources