Multicollinearity Myth Buster

• In Event: Poster Session 2
  In Poster Session: Division D Section 2 Poster Session 1

Abstract

Recommendations from popular statistics texts regarding avoidance of predictor variable multicollinearity in the use of traditional prediction methods (multiple regression, discriminant analysis, and logistic regression) are considered from the perspective of the alternate purposes of explanation and prediction. In the case of both relative and absolute prediction accuracy, it is shown that multicollinearity has no effect on prediction. Moreover, from the perspective of prediction accuracy, not only does multicollinearity not disadvantage the traditional methods, but indeed, it is, in most data conditions presented, advantageous to model prediction accuracy, as it allows validity concentration to become large enough for alternative methods to exceed the traditional ones.

Authors

• John D. Morris, Florida Atlantic University

• Mary G. Lieberman, Florida Atlantic University