Investigating Multicollinearity in Factors Affecting Number of Born Children in Iraq

Abstract

The occurrence of multicollinearity in several multiple regression models leads to major problems that can affect the entire multiple regression model outcomes, among the problems are a reduction in the precision of the estimated coefficients, which decreases the statistical power of the model. The effect of sensitivity on the estimated coefficients is due to a small swing in the model. This paper considers the two fundamental approaches for identifying multicollinearity. The first approach is the correlation coefficient (CC) and the second one is the variance inflation factor (VIF). The ridge regression method, principal components regression, intent root regression,  and weighted regression are advanced regression models for investigating the existence of multicollinearity, these findings would tackle, reduce, and fixed the multicollinearity among the independent variables, and help to predict the best-fitted model. Lastly, we came up with the best-fitted model.