Some shrinkage preliminary test ridge regression estimators are consider under the multicollinearity situation, when it is suspected that the regression coefficients may be restricted to a subspace and the regression coefficients combining the idea of shrinkage preliminary test and ridge regression methodology. We consider four estimators namely the Unrestricted Ridge Regression Estimator, the Restricted Ridge Regression Estimator, the
Shrinkage Restricted Ridge Regression Estimator and finally, the Shrinkage Preliminary Test Ridge Regression Estimator. The biases and the mean square errors (MSE) of the estimators are derived under the null and alternative hypothesis. By studying the MSE criterion, the conditions of superiority of the estimators over the traditional estimators have been discussed. It is analytically showed that the proposed shrinkage preliminary test ridge regression estimator provides a wider range for the ridge parameter than the preliminary test ridge regression estimator in which it dominates the unrestricted ridge regression estimator. Finally, we graphically demonstrated the superiority of the proposed estimators.