A Simulation Study for Evaluation of some Ridge Regression Estimators.

Document Type : Original Article

Author

Statistics,Mathematics and Insurance Department Faculty of Commerce Alexandria University Alexandria Egypt

Abstract

Ridge regression estimator has been introduced as an alternative to the ordinary least squares estimator (OLS) in the presence of multicollinearity. Several studies concerning ridge regression have dealt with the choice of the ridge parameter. In this article, a simulation study has been conducted to evaluate the performance of 20 ridge regression estimators based on the mean squared error (MSE) criterion. Based on the simulation study, it is found that as the number of correlated variable increase, and  the correlation between the independent variables increase, the MSE also increase; while When increasing the sample size, it is found that MSE decreases even when the correlation between the independent variables and the variance of the random error are large. The simulation study indicates in general that the estimators K1-1, K12 (Muniz and K-ibria, 2009), K3 (Lawless and Wang, 19-76), K13 (Al-Hassan, 2010), and K6 (K-ibria, 2003), perform well compared to the other estimators

Keywords

Files

Share

How to cite

Statistics