The sanctity of p < .05 obfuscates good stuff: A comment on kerr and goss

Abstract

Sports injuries can be a major source of both personal and financialud hardship, and Kerr and Goss (1996) in their article “The Effects of aud Stress Management Program on Injuries and Stress Levels” have conductedud important research that has implications for the health and welfareud of many athletes. Besides suggesting some potential avenues for reducingud the incidence of injury, Kerr and Goss have presented a study that offersud an opportunity to discuss some issues related to statistical inference, nullud hypothesis testing, power, and the requirement that p be less than .05.ud Past research and writings on psychosocial factors and athletic injuryud have focused on two major areas: antecedents and consequences of injuryud (Brewer, 1994; Petrie, 1992; Williams, Hogan, & Andersen, 1993). Theud literature has been noticeably bereft of studies directed at what most sportud psychologists, coaches, athletic trainers, and athletes would probably considerud the central issue, and that is reducing injury risk in sport. In 1991,ud Davis presented results that suggested a simple program of progressiveud relaxation could decrease injury rates. In turn, it was 5 years before anotherud such injury prevention study appeared in the literature (i.e., Kerr &ud Goss, 1996)