Construct proliferation—the accumulation of ostensibly different but potentially identical constructs representing organizational phenomena—is a salient problem in contemporary research. While a number of construct validation procedures exist, relatively few validation studies conduct comprehensive assessments of the discriminant validity of theoretically distinct constructs. In this article, we outline the key considerations a researcher must take into account when attempting to establish the empirical distinctness of new or existing constructs and provide a step-by-step guide on how to assess the discriminant validity of constructs while accounting for three major sources of measurement error: random error, specific factor error, and transient error. Using a number of popular measures from the leadership literature, we provide an illustrative example of how to conduct a study of discriminant validity. We include several analytic strategies in our study and discuss the similarities and differences between the results they yield. We also discuss several additional issues related to this type of research and make recommendations for conducting discriminant validity analyses.