Shrinkage Estimation in Restricted Elliptical Regression Models

نویسندگان
Falah, ‎R‎eza‎ ‎ ID 1
Arashi, ‎M‎ohammad ID 2
‎Tabatabaey, Seyed Mohammad M. ID 3

1 Department of Statistics, Ferdowsi University of Mashhad, International campus, Iran

2 Department of Statistics, Shahrood University of Technology, Shahrood, Iran

3 Department of Statistics, Ferdowsi University of Mashhad, Mashhad, Iran

doi
10.29252/jirss.17.1.49
چکیده

In the restricted elliptical linear model, an approximation for the risk of a general shrinkage estimator of the regression vector-parameter is given. Superiority condition of the shrinkage estimator over the restricted estimator is investigated under the elliptical assumption. It is evident from numerical results that the shrinkage estimator performs better than the unrestricted one in the multivariate t-regression model.  

کلیدواژه‌ها
Approximate risk, Elliptically contoured distribution, Linear regression model, Restricted estimator, Shrinkage estimator‎