Semiparametric space–time survival modeling of chronic wasting disease in deer

Environmental and Ecological Statistics - Tập 17 - Trang 559-571 - 2009
Andrew Lawson1, Hae-Ryoung Song
1Department of Biostatistics, Bioinformatics & Epidemiology, College of Medicine, Medical University of South Carolina, Charleston, USA

Tóm tắt

In this paper, we propose a semiparametric survival model to investigate the pattern of spatial and temporal variation in disease prevalence of chronic wasting disease (CWD) in wild deer in Wisconsin over the years 2002 and 2006. The semiparametric survival model we suggested allows to build a more flexible model than the parametric model with fewer parametric assumptions by modeling the baseline hazard using a Gamma process prior. Based on the proposed model, we investigate the geographical distribution of CWD, and assess the effect of sex on disease prevalence. We use a Bayesian hierarchical framework where latent parameters capture temporal and spatial trends in disease incidence, incorporating sex and spatially correlated random effects. We also propose bivariate baseline hazard which change over age and time simultaneously to adopt different effects of age and time on the baseline hazard. Inference is carried out by using MCMC simulation techniques in a fully Bayesian framework. Our results suggest that disease has been spreaded mainly in the disease eradication zone and male deer show a significantly higher infection probability than female deer.

Tài liệu tham khảo

Angelos James, Lee Carl M-S, Singh K (2006) B-spline approximation for the baseline hazard function. Environmetrics 2: 323–339 Banerjee S, Wall M, Carlin BP (2003) Frailty modeling for spatially correlated survival data, with application to infant mortality in Minnesota. Biostatistics 4: 123–142 Banerjee S, Carlin BP, Gelfand AE (2004) Hierarchical modeling and analysis for spatial data. Chapman and Hall, Boca Raton Florida, USA Bastos L, Gamerman D (2006) Dynamic survival models with spatial frailty. Lifetime Data Anal 12: 441–460 Besag J, Kooperberg C (1995) On conditional and intrinsic autoregressions. Biometrika 82: 733–746 Besag J, York JC, Mollie A (1991) Bayesian image restoration, with two applications in spatial statistics (with discussion). Ann Inst Stat Math 43: 1–59 Celeux G, Forbes F, Robert C, Titterington M (2006) Deviance information criteria for missing data models. Bayesian Anal 1(4): 651–674 Farnsworth M, Wolfe L, Hobbs N, Burnham K, Williams E, Theobald D, Conner M, Miller M (2005) Human land use influences chronic wasting disease prevalence in mule deer. Ecol Appl 15(1): 119–126 Farnsworth M, Hoeting J, Hobbs N, Miller M (2006) Linking chronic wasting disease to mule deer movement scales: a hierarchical bayesian approach. Ecol Appl 16(3): 1026–1036 Johns C, Mehl C (2006) A dynamic spatial model for chronic wasting disease in Colorado. J Data Sci 4: 21–37 Lawson A (2006) Statistical methods in spatial epidemiology. 2 edn. Wiley, New York Lawson A, Leimich P (2000) Approaches to space–time modeling of infectious disease behaviour. IMA J Math Appl Med Biol 17: 1–13 Miller M, Williams E (2003) Horizontal prion transmission in mule deer. Nature 425: 35–36 Miller M, Williams E, Hobbs T, Wolfe L (2004) Environmental sources of prion transmission in mule deer. Emerg Infect Dis 10: 1003–1006 Miller M, Conner M (2005) Epidemiology of chronic wasting disease in free-ranging mule deer: spatial, temporal, and demographic influences on observed prevalence patterns. J Wildl Dis 41(2): 275–290 Spiegelhalter DJ, Thomas A, Best NG (2002) Bayesian measures of model complexity and fit. J R Stat Soc Series B, Stat Methodol 64: 583–616