Releasing the death-grip of null hypothesis statistical testing (p < .05): Applying complexity theory and somewhat precise outcome testing (SPOT)

Abstract

Even though several scholars describe the telling weaknesses in such procedures, the dominating logic in research in the management sub-disciplines continues to rely on symmetric modeling using continuous variables and null hypothesis statistical testing (NHST). Though the term of reference is new, somewhat precise outcome testing (SPOT) procedures are available now and, along with asymmetric modeling, enable researchers to better match data analytics with their theories than the current pervasive theory–analysis mismatch. The majority (70%+) of articles in the leading journals of general management, marketing, finance, and the additional management sub-disciplines are examples of the mismatch. The mismatch may be a principal cause for the scant impact of the majority of articles. Asymmetric modeling and SPOT rests on the principal tenets of complexity theory rather than overly shallow and simplistic symmetric modeling and reporting of NHST findings. Though relatively rare, examples of asymmetric modeling and SPOT are available now in the management literature. The current lack of instructor knowledge and student training in MBA and PhD programs of asymmetric modeling and SPOT are the likely principal reasons for this scarcity.