Empirical Bayes estimation smoothing of relative risks in disease mapping

摘要: A common index of disease incidence and mortality is the standardized ratio (SMR). The SMR a reliable measure relative risk for large geographical regions such as countries or states, but may be unreliable small areas counties. This paper reviews several empirical Bayes methods producing smoothed estimates well conditional autoregressive procedure which accounts spatial correlation. multi-level Poisson model with covariates developed, estimating functions are used to estimate parameters in Lahiri Maiti (University Nebraska Technical Report, 2000). hybrid parametric bootstrap delta MSE. proposed captures all sources uncertainty approximating MSE estimator SMR.