Bayesian Estimation of the Incidence Rate in Birth Defects Monitoring

摘要: Although non-Bayesian statistical methods have been used to detect a significant increase of birth defect incidence in monitoring, they require large number data. In this paper Bayesian statistics is applied estimate the rate particularly small population. The method as follows. Assuming that follows binomial distribution and prior beta distribution, posterior distribution. hyperparameters are determined objectively by maximum marginal likelihood or minimum ABIC based on past observations. compared with when monthly data anencephaly from defects monitoring program Tokyo Metropolitan hospitals between 1979 1984. variation point estimates 25% ones. average confidence interval 29% method. results indicate estimation more appropriate than type analysis.