期刊
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
卷 46, 期 23, 页码 11854-11865出版社
TAYLOR & FRANCIS INC
DOI: 10.1080/03610926.2017.1285928
关键词
Approximate risk; elliptically contoured distribution; linear regression model; restricted estimator; shrinkage estimator; ridge estimator
In the linear regression model with elliptical errors, a shrinkage ridge estimator is proposed. In this regard, the restricted ridge regression estimator under sub-space restriction is improved by incorporating a general function which satisfies Taylor's series expansion. Approximate quadratic risk function of the proposed shrinkage ridge estimator is evaluated in the elliptical regression model. A Monte Carlo simulation study and analysis based on a real data example are considered for performance analysis. It is evident from the numerical results that the shrinkage ridge estimator performs better than both unrestricted and restricted estimators in the multivariate t-regression model, for some specific cases.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据