文章在非线性均值方差模型框架下基于K-L距离研究贝叶斯数据删除影响的统计诊断问题, 通过应用Gibbs抽样和MH算法估计贝叶斯数据删除影响诊断统计量.随机模拟研究和红鳟鲑鱼数据的数值例子说明该诊断方法的可行性.

Bayesian case deletion statistical diagnostics based on K-L divergence for nonlinear mean and variance models are studied in this paper, in which Gibbs sampler and Metropolis-Hastings algorithm are employed to calculate Bayesian case deletion statistic. Simulation studies and a sockeye salmon data example are used to demonstrate the proposed methodology.