SURE estimates under dependence and heteroscedasticity

SURE estimates under dependence and heteroscedasticity
复制标题

依赖性和异方差下的 SURE 估计

DOI:
10.1016/j.jmva.2017.07.001
复制
发表时间:
2017-09
影响因子:
1.6
通讯作者:
Wang Zhou
Wang Zhou
中科院分区:
数学2区
文献类型:
--
作者:
Xinbing Kong;Zhi Liu;Peng Zhao;Wang Zhou

文献摘要

参考文献

相似文献

具有独立均值的多变量贝叶斯层次模型已经得到了广泛的研究,并在实际中得到了广泛的应用。相比之下,依赖手段的情况下,很少受到关注,即使多变量观测往往是相关的。在本文中,我们研究了多元异方差贝叶斯分层模型,其中假设一个信息先验与等相关的均值。我们估计的均值向量的收缩估计的基础上斯坦的无偏风险估计(SURE)。它示出的SURE估计的平方误差损失是接近的一个oracle估计的数量的手段的增长。我们的SURE估计量包括了Xie et al.认为的独立性下的SURE估计量。2012年,作为特例。我们的估计有限样本的性能进行了探讨,通过模拟和两个真实的数据集用于说明目的。
The multivariate Bayesian hierarchical model with independent means has been studied extensively and is widely used in practice. In contrast, the case of dependent means has received scant attention, even though multivariate observations are often correlated. In this paper, we investigate a multivariate heteroscedastic Bayesian hierarchical model in which an informative prior with equicorrelated means is assumed. We estimate the mean vector by the shrinkage estimator based on Stein’s unbiased risk estimation (SURE). It is shown that the squared error loss of the SURE estimator is close to that of an oracle estimator as the number of means grows. Our SURE estimator includes the SURE estimator under independence considered by Xie et al. (2012) as a special case. The finite-sample performance of our estimator is explored via simulations and two real data sets are used for illustration purposes.
DOI: 10.1080/01621459.1973.10481350
发表时间: 1973-03
影响因子: 3.7
作者:
B. Efron;C. Morris
通讯作者: B. Efron;C. Morris
DOI: 10.1080/01621459.1975.10479883
发表时间: 1975-06
影响因子: 3.7
作者:
L. Brown
通讯作者: L. Brown
DOI: 10.3905/jpm.1993.409440
发表时间: 1993-12-01
影响因子: 1.4
作者:
CHOPRA, VK;ZIEMBA, WT
通讯作者: ZIEMBA, WT
DOI: 10.1198/016214506000001211
发表时间: 2007-03-01
影响因子: 3.7
作者:
Efron, Bradley
通讯作者: Efron, Bradley
DOI: 10.1214/11-sts380
发表时间: 2012-02
影响因子: 5.7
作者:
D. Fourdrinier;M. Wells
通讯作者: D. Fourdrinier;M. Wells