Number of Predictors and Multicollinearity: What Are Their Effects on Error and Bias in Regression?

• In Event: Multiple Linear Regression: The General Linear Model SIG Special Topics Paper Session

Abstract

The present study adds to the literature by analyzing parameter bias, rates of Type I and Type II error, and variance inflation factor (VIF) values produced under various multicollinearity conditions by multiple regressions with two predictors, four predictors, and six predictors. Preliminary findings seem to suggest that multicollinearity may tend to reduce Type II error. The investigation of bias suggests that multicollinearity increases the variability in parameter bias, while leading to underestimated parameters overall.

Authors

• Matthew R. Lavery, Polk County Public Schools

• Parul Acharya, University of Central Florida

• Stephen A. Sivo, University of Central Florida

• Lihua Xu, University of Central Florida