ON THE WEIGHTED STOCHASTIC RESTRICTED RIDGE REGRESSION AND SHRINKAGE ESTIMATORS

Abstract

The prior information on the restriction of the stochastic restricted linear regression models may reduce the effect of multicollinearity but cannot remove its effect completely from estimation of the parameter of the model. For this reason, two new types of weighted mixed estimators in the stochastic restricted linear regression model are proposed in this paper. The proposed estimators are general estimators which include some other estimators as a special case. We compared the performance of these estimators with some other estimators with respect to the mean squares error criterion. A simulation study has been conducted to illustrate the results