BAYESIAN-ANALYSIS OF OUTLIER PROBLEMS USING DIVERGENCE MEASURES
BAYESIAN-ANALYSIS OF OUTLIER PROBLEMS USING DIVERGENCE MEASURES
复制标题
DOI：
10.2307/3315445
复制
发表时间：
1995-06-01
影响因子：
0.6
通讯作者：
DEY, DK
中科院分区：
文献类型：
--
作者：
PENG, FC;DEY, DK
提出了一种基于后验分布的广义发散测度的贝叶斯估计方法。一个基于采样的方法，使用吉布斯或吉布斯内的大都市方法被用来计算后验发散措施。提出了四个具体的措施，传达一个单一的观察或协变量的后验的影响。该技术被应用到一个广义线性模型与二进制响应数据，过分散模型和非线性模型。文中还简要讨论了用拉普拉斯方法求后验发散的渐近近似。
A Bayesian approach is presented for detecting influential observations using general divergence measures on the posterior distributions. A sampling-based approach using a Gibbs or Metropolis-within-Gibbs method is used to compute the posterior divergence measures. Four specific measures are proposed, which convey the effects of a single observation or covariate on the posterior. The technique is applied to a generalized linear model with binary response data, an overdispersed model and a nonlinear model. An asymptotic approximation using Laplace method to obtain the posterior divergence is also briefly discussed.