Robust multicollinearity diagnostic measure in collinear data set

Abstract

It is now evident that high leverage points or outliers in the X-direction may affect the collinearity pattern of a data set. Their presence may decrease or increase multicollinearity problem of a collinear data matrix X. The usage of Classical Variance Inflation Factor (CVIF) for multicollinearity diagnostics is not reliable as it is not resistant to the presence of high leverage points. In this paper, we proposed a robust Variance Inflation Factors (RVIF) which is based on the GM(DRGP) estimator. We denote this estimator as RVIF(GM(DRGP)). The empirical evidences indicate that the CVIF performs poorly in the presence of high leverage points. Nonetheless, the RVIF (GM (DRGP)) successfully detect the collinearity pattern when high leverage points are present in the collinear data.