A case study in non-centering for data augmentation: Stochastic epidemics
A case study in non-centering for data augmentation: Stochastic epidemics
复制标题
DOI：
10.1007/s11222-005-4074-7
复制
发表时间：
2005-10-01
影响因子：
2.2
通讯作者：
Roberts, G
中科院分区：
文献类型：
--
作者：
Neal, P;Roberts, G
本文介绍了随机流行病模型的非中心和部分非中心MCMC算法。先前文献中考虑的中心算法在小数据集上表现得很好。然而，由于缺失数据和参数之间的模型固有的高度依赖性，当考虑更大的数据集时，中心算法的性能会明显变差。因此，介绍了非居中算法和部分非居中算法，并证明它们优于现有的居中算法。
In this paper, we introduce non-centered and partially non-centered MCMC algorithms for stochastic epidemic models. Centered algorithms previously considered in the literature perform adequately well for small data sets. However, due to the high dependence inherent in the models between the missing data and the parameters, the performance of the centered algorithms gets appreciably worse when larger data sets are considered. Therefore non-centered and partially non-centered algorithms are introduced and are shown to out perform the existing centered algorithms.