Mitigating Effect of Additional Variables on Common Method Variance in Structural Equations Models

Abstract

This study examines the effect that adding addition exogenous variables has on mitigating the effect of common method variance. In an effort that replicates and extends the work of Siemsen, Roth, and Oliveira (2010), we consider the effects of adding variables in structural equations modelling as well as regression. We also consider the implications of imperfect measurement conditions, including measurement error and the use of exogenous variables that are not orthogonal to all other variables in the study. Using two types of data simulation, the current study indicates that the use of additional variables in structural equations models can reduce the inflationary effects of CMV. We also show that the beneficial effects of adding additional variables are not mitigated by the use of imperfect marker variables. The study has implications for researchers conducting studies where CMV may be a threat, as well as for interpreting prior research that did not take steps to test for or address potential CMV concerns.