We discuss identification of structural characteristics of the underlying relative risks ensemble for posterior relative risks inference within Bayesian generalized linear mixed model framework for small-area disease mapping and ecological–spatial regression. We revisit conditionally specified and locally characterized Gaussian Markov random field risks ensemble priors in univariate disease mapping and communicate insight into Gaussian Markov random field variance–covariance characteristics for representing disease risks variability and spatial risks interactions and for structural identification with respect to risks ensemble prior choices. Illustrative examples of identification in Bayesian disease mapping and ecological–spatial regression models are presented for Bayesian hierarchical generalized linear mixed Poisson models and zero-inflated Poisson models.
ClaytonDGKaldorJ. Empirical Bayes estimates of age-standardized relative risks for use in disease mapping. Biometrics1987; 43: 671–681.
2.
BesagJYorkJMolliéA. Bayesian image restoration, with two applications in spatial statistics. Ann Inst Stat Math1991; 43: 1–21.
3.
MacNabYC. On Gaussian Markov random fields and Bayesian disease mapping. Stat Meth Med Res2011; 20(1): 49–68.
4.
RueHHeldL. Gaussian Markov random fields: theory and applications, New York: Chapman and Hall/CRC, 2005.
5.
BreslowNEClaytonDG. Approximate inference in generalized linear mixed models. J Am Stat Assoc1997; 88: 9–25.
6.
MacNabYCDeanCB. Parametric bootstrap and penalized quasi-likelihood inference in conditional autoregressive models. Stat Med2000; 19(15/16): 15–30.
7.
MacNabYCLinY. On empirical Bayes penalized quasilikelihood inference in GLMMs and in disease mapping and ecological modeling. Comput Stat Data Anal2009; 53(8): 2950–2967.
8.
MacNabYC. Hierarchical Bayesian modelling of spatially correlated health service outcome and utilization rates. Biometrics2003; 59(2): 305–316.
9.
MacNabYC. Hierarchical Bayesian spatial modelling of small-area rates of non-rare disease. Stat Med2003; 22(10): 1761–1773.
10.
MacNabYC. Bayesian multivariate disease mapping and ecological regression with errors in covariates: Bayesian estimation of DALYs and ‘preventable’ DALYs. Stat Med2009; 28(9): 1369–1385.
11.
MacNabYC. On Bayesian shared component disease mapping and ecological regression with errors in covariates. Stat Med2010; 29(11): 1239–1249.
12.
MacNabYC. Spline smoothing in Bayesian disease mapping. Environmetrics2007; 18(7): 727–744.
13.
MacNabYCGustafsonP. Regression B-spline smoothing in Bayesian disease mapping: with an application to patient safety surveillance. Stat Med2007; 26(24): 4455–4474.
14.
GelfandAESahuSK. Identifiability, improper priors, and gibbs sampling for generalized linear models. J Am Stat Assoc1999; 94(445): 247–253.
15.
LerouxBGLeiXBreslowNEstimation of disease rates in small areas: a new mixed model for spatial dependence. In: HalloranMEBerryD (eds). Statistical models in epidemiology, the environment and clinical trials, New York: Springer-Verlag, 1999, pp. 135–178.
16.
SpiegelhalterDJThomasABestNG. WinBUGS version 1.4 user manual, Cambridge: MRC Biostatistics Unit, Institute of Public Health, Cambridge University, 2003.
17.
ThomasABestNGLunnD. GeoBUGS 1.2 User Manual, Cambridge: MRC Biostatistics Unit, Institute of Public Health, Cambridge University, 2004.
18.
SternHSCressieNACInference for extremes in disease mapping. In: LawsonA (eds). Disease mapping and risk assessment for public health, Chapter 5, New York: John Wiley & Sons, 1999.
19.
StrongMPearsonTMacNabY. Mapping gender variation in the spatial pattern of alcohol-related mortality: a Bayesian analysis using data from South Yorkshire, United Kingdom. To appear in Spat Spatio-temporal Epidemiology.
20.
WangFWallM. Generalized common spatial factor model. Biostatistics2003; 4: 569–582.
GhoshSMukhopadhyayPLuJC. Bayesian analysis of zero-inflated regression models. J Stat Plann Inference2006; 136: 1360–1375.
23.
BestNGBayesian ecological modelling. In: LawsonA (eds). Disease mapping and risk assessment for public health, New York: John Wiley and Sons, 1999, pp. 194–201.
24.
MacNabYCKmeticAGustafsonP. An innovative application of Bayesian disease mapping methods to patient safety research: the Canadian iatrogenic injury study. Stat Med2006; 25(23): 3960–3980.
25.
BestNGRichardsonSThomsonA. A comparison of spatial models for disease mapping. Stat Meth Med Res2005; 14: 35–59.
