Exploratory Factor Analysis (EFA) is a powerful and commonly-used tool for investigating the underlying
variable structure of a psychometric instrument. However, there is much controversy in the social sciences
with regard to the techniques used in EFA (Ford, MacCallum, & Tait, 1986; Henson & Roberts, 2006) and
the reliability of the outcome. Simulations by Costello and Osborne (2005), for example, demonstrate how
poorly some EFA analyses replicate, even with clear underlying factor structures and large samples. Thus, we
argue that researchers should routinely examine the stability or volatility of their EFA solutions to gain more
insight into the robustness of their solutions and insight into how to improve their instruments while still at
the exploratory stage of development.