Sparse Multivariate Regression With Covariance Estimation.

Sparse Multivariate Regression With Covariance Estimation.
复制标题

DOI:
10.1198/jcgs.2010.09188
复制
发表时间:
2010
期刊:
Journal of computational and graphical statistics : a joint publication of American Statistical Association, Institute of Mathematical Statistics, Interface Foundation of North America
影响因子:
--
通讯作者:
Zhu J
Zhu J
中科院分区:
其他
文献类型:
--
作者:
Rothman AJ;Levina E;Zhu J

文献摘要

参考文献

被引文献

相似文献

我们提出了一种构造多元回归系数矩阵的稀疏估计的方法,该估计考虑了响应变量之间的相关性。这种方法,我们称之为多元回归与协方差估计(MRCE),涉及惩罚似然,同时估计回归系数和协方差结构。提出了一种计算MRCE的高效优化算法和快速逼近算法。通过仿真研究表明,当响应高度相关时,该方法的性能优于相关竞争者。我们还将新方法应用到一个预测资产收益的金融实例中。包含该数据集和用于计算MRCE及其近似值的代码的R包可在网上获得。
We propose a procedure for constructing a sparse estimator of a multivariate regression coefficient matrix that accounts for correlation of the response variables. This method, which we call multivariate regression with covariance estimation (MRCE), involves penalized likelihood with simultaneous estimation of the regression coefficients and the covariance structure. An efficient optimization algorithm and a fast approximation are developed for computing MRCE. Using simulation studies, we show that the proposed method outperforms relevant competitors when the responses are highly correlated. We also apply the new method to a finance example on predicting asset returns. An R-package containing this dataset and code for computing MRCE and its approximation are available online.
DOI: 10.1137/070695915
发表时间: 2009-01-01
影响因子: 3.1
作者:
Lu, Zhaosong
通讯作者: Lu, Zhaosong
DOI: 10.1111/1467-9868.00348
发表时间: 2002-01-01
影响因子: 5.8
作者:
Brown, PJ;Vannucci, M;Fearn, T
通讯作者: Fearn, T
DOI: 10.1214/08-ejs176
发表时间: 2008-01-01
影响因子: 1.1
作者:
Rothman, Adam J.;Bickel, Peter J.;Zhu, Ji
通讯作者: Zhu, Ji
DOI: 10.1111/j.1467-9868.2007.00591.x
发表时间: 2007-01-01
影响因子: 5.8
作者:
Yuan, Ming;Ekici, Ali;Monteiro, Renato
通讯作者: Monteiro, Renato
DOI: 10.1111/1467-9868.00054
发表时间: 1997-01-01
期刊: JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL
影响因子: --
作者:
Breiman, L;Friedman, JH
通讯作者: Friedman, JH