Latent spatial grouping in Bayesian AFT modeling Keywords: AFT, spatial, latent, Bayesian, SEER, prostate cancer The analysis of population level survival data can have a major impact on health policy and Public Health resource allocation. Prostate cancer (PrCa) has been examined spatially with a variety of modeling approaches and latent groupings in the spatial distribution of such data can be present. These groupings have a bearing on the analysis of disparities in PrCa. Our aim is to provide a general framework for the analysis of prostate cancer survival which is flexible and can isolate underlying latent survival patterns that have a spatial reference. To this end we examine the use of Bayesian AFT models with SEER registry prostate cancer data from the state of Louisiana for time period 2005 - 2007. We model latent grouping in spatially-defined parameters of the survival model. We demonstrate that latent structures in survival can have marked spatial expression and hence policy implications.
|
Important Dates & Deadlines
- May 31, 2011
Registration Deadline for All Session Presenters - September 1, 2011
Poster Abstract Online Submission Closes - September 9, 2011
Hotel Reservations Close - September 15, 2011
Conference Registration Closes