Solving multi-collinearity problem by ridge and eigen value regression with simulation

Abstract EN

In this paper, five new methods were proposed to estimate the ridge parameter by inserting the conditional number, which are used to estimate the parameters of the ridge regression model to deal with multicollinearity problem and then compare their efficiency with some classical methods that was studied by several researchers based on Mean square error and comparing them with Eigen value Regression through simulation study (MATLAB language program designed for this purpose), the research shows that the efficiency of the proposed methods in dealing with multicollinearity problem and the advantages of the proposed methods compared with the classical methods of Ridge and Eigen value Regression.