Gibbs Ensembles for Nearly Compatible and Incompatible Conditional Models.
Gibbs Ensembles for Nearly Compatible and Incompatible Conditional Models.
复制标题
DOI：
10.1016/j.csda.2010.11.006
复制
发表时间：
2011-04-01
影响因子：
1.8
通讯作者：
Wang, Yuchung J.
中科院分区：
文献类型：
--
作者：
Chen, Shyh-Huei;Ip, Edward H.;Wang, Yuchung J.
Gibbs采样器专门用于收敛于唯一不变联合分布的相容条件。然而，条件模型并不总是兼容的。本文提出了一种基于Gibbs抽样的方法——Gibbs集合——来寻找与一组规定的条件分布偏离最小的联合分布。该算法可以很容易地扩展，这样它就可以处理大量的高维数据集。使用模拟数据，我们表明所提出的方法提供的联合分布与文献中讨论的其他方法获得的不相容条件的差异较小。集合方法也应用于关于转移性结直肠癌患者的基因多态性和化疗反应的数据集
Gibbs sampler has been used exclusively for compatible conditionals that converge to a unique invariant joint distribution. However, conditional models are not always compatible. In this paper, a Gibbs sampling-based approach — Gibbs ensemble —is proposed to search for a joint distribution that deviates least from a prescribed set of conditional distributions. The algorithm can be easily scalable such that it can handle large data sets of high dimensionality. Using simulated data, we show that the proposed approach provides joint distributions that are less discrepant from the incompatible conditionals than those obtained by other methods discussed in the literature. The ensemble approach is also applied to a data set regarding geno-polymorphism and response to chemotherapy in patients with metastatic colorectal
登录
查看更多内容
影响因子：
1.8
作者：
Arnold, BC;Castillo, E;Sarabia, JM
通讯作者：
Sarabia, JM
影响因子：
1.6
作者：
Levine, Richard A.;Casella, George
通讯作者：
Casella, George
影响因子：
1.6
作者：
Ip, Edward H.;Wang, Yuchung J.
通讯作者：
Wang, Yuchung J.
影响因子：
45.3
作者：
Toffoli, Giuseppe;Cecchin, Erika;Frustaci, Sergio
通讯作者：
Frustaci, Sergio
影响因子：
6
作者：
Heckerman, D;Chickering, DM;Kadie, C
通讯作者：
Kadie, C