Evaluating the Performance of Spatio-Temporal Bayesian Models in Disease Mapping

• Activity Number: 244
• Type: Invited
• Date/Time: Tuesday, August 5, 2008 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics and the Environment
• Author(s): Maria Dolores Ugarte*+ and Tomas Goicoa and Berta Ibañez and Ana F. Militino
• Companies: Public University of Navarra and Public University of Navarra and Fundación Vasca de Innovación e Investigación Sanitarias and Public University of Navarra
• Keywords: Bayesian Decision Rules ; Models Sensitivity and Specificity ; bias and MSE of relative risks estimates ; Hierarchical Bayesian Models

Abstract

In this work, alternative Bayesian spatio-temporal models are fitted using MCMC techniques. The models performance is analyzed through a simulation study with two objectives in mind: the first one is to evaluate the relative bias and the relative MSE of the posterior mean relative risks, and the second one is to investigate recent Bayesian decision rules to detect raised-risk areas in a spatio-temporal context. The simulation study is based on colorectal cancer mortality data in males from Navarra, Spain at four five-year time windows. When there are a number of high-risk areas in some of the time periods we conclude that the bias of the posterior mean relative risks could be substantial. The decision rules to detect these high-risk areas should be determined with caution. A final rule combining alternative threshold and cut-off values for the different time periods seems to be needed.