EFFECTS OF MULTICOLLINEARITY IN SIMULTANEOUS EQUATION MODELS AND COMPARISONS OF ALTERNATIVE ESTIMATORS

Abstract

The aim of this study is to determine the most efficient estimator for simultaneous equation models with multicollinearity problem by comparing the performance of alternative estimators that overcome the effect of multicollinearity and produce more stable estimates. For this purpose, Klein’s simultaneous equation model with multicollinearity problem presented in his study titled “Economic Fluctuations in the United States” in 1950 is used. The model is estimated with traditional estimators two-stage least squares, three-stage least squares and biased estimators ridge, generalized maximum entropy (GME). The performances of these estimators are compared according to the mean square error criteria obtained by the bootstrap method. As a result, GME is found to be the most efficient estimator in the presence of multicollinearity.