Deviance Information Criteria for Missing Data Models
Deviance Information Criteria for Missing Data Models
复制标题
DOI：
10.1214/06-ba122
复制
发表时间：
2006-01-01
影响因子：
4.4
通讯作者：
Titterington, D. M.
中科院分区：
文献类型：
--
作者：
Celeux, G.;Forbes, F.;Titterington, D. M.
Spiegelhalter等人（2002）引入的用于模型评估和模型比较的偏差信息准则（DIC）直接受到线性和广义线性模型的启发，但它对缺失数据模型设置的不同可能变化是开放的，特别是取决于缺失变量是否被视为参数。在本文中，我们重新评估了这些模型的准则，并比较了不同的DIC结构，测试了这些不同扩展在分布和随机效应模型混合情况下的行为。
The deviance information criterion (DIC) introduced by Spiegelhalter et al. (2002) for model assessment and model comparison is directly inspired by linear and generalised linear models, but it is open to different possible variations in the setting of missing data models, depending in particular on whether or not the missing variables are treated as parameters. In this paper, we reassess the criterion for such models and compare different DIC constructions, testing the behaviour of these various extensions in the cases of mixtures of distributions and random effect models.