Multicollinearity Reconsidered



In this paper we intend to improve the explanatory power of regressions when the deletion method is used for the remedy of Multicolinearity. If one deletes the variable (s) that is (are) responsible for Multicolinearity, he loses some information that is not common between the deleted variable (s) and the other remaining variables in the regression. To improve this method, we run the deleted variable (s) on the remaining variable (s) and use its residual as a new regressor in the main regression. Here we also focus on the Multicolinearity concept that is related to the population and samples separately. We will also show if one encounters with perfect Multicolinearity he can delete one of the variables without any biasedness costs. The procedure that saves some of the variables in the regression and input residuals of the other variable as regressors will give us ‘net effect regression’.