A Dangerous Blind Spot in IS Research: False Positives Due to Multicollinearity Combined With Measurement Error

Econometrics textbooks generally conclude that in regression, because the calculation of path estimate variances includes a variance inflation factor (VIF) that reflects correlations between “independent” constructs, multicollinearity should not cause false positives except in extreme cases. However, textbook treatments of multicollinearity assume perfect measurement – rare in behavioral research. VIF is based on apparent correlations between constructs -- always less than actual correlations when measurement error exists. A brief review of recent articles in the MIS Quarterly suggests that the conditions for excessive false positives are present in published research. In this paper we show (analytically and with a series of Monte Carlo simulations) that multicollinearity combined with measurement error presents greater than expected dangers from false positives in IS research when regression or PLS is used. Suggestions for how to address this situation are offered.