Abstract:
|
We propose a novel Bayesian statistical methodology for spatial survival data. Our methodology broadens the definition of the survival, density and hazard functions by explicitly modeling the spatial dependency using direct derivations of these functions and their marginals and conditionals. We also derive spatially dependent likelihood functions. We examine the applications of these derivations with geographically augmented survival distributions in the context of the Louisiana Surveillance, Epidemiology, and End Results (SEER) registry prostate cancer data and use simulated data to compare the results with existing methodologies. After controlling for other covariates in the model, black race, distant stage, higher age at diagnosis were associated with lower survival. Being married was associated with higher survival. We estimated that some counties with higher risk are in the south-estern part of the state, while counties in the central and north-eastern part have lower risk.
|
ASA Meetings Department
732 North Washington Street, Alexandria, VA 22314
(703) 684-1221 • meetings@amstat.org
Copyright © American Statistical Association.