On Statistical Wizardry, Construct Proliferation, and Other Challenges for Our Science

Research in counseling psychology (and most social sciences) has come to rely on powerful data analytic strategies and computer software that allow researchers to test complex multivariate models quickly and easily. New constructs also appear in our literature with regularity. Although complex models and new constructs have benefits for advancing knowledge and application, they also have drawbacks. The purpose of this article is to caution readers to (a) choose designs and data analytic strategies that are minimally sufficient to address their research questions, and (b) ensure that new constructs are empirically as well as conceptually distinguishable from extant constructs.