IMPROVING OUTCOME RESEARCH IN REHABILITATION PSYCHOLOGY - SOME METHODOLOGICAL RECOMMENDATIONS

There has been an ongoing debate concerning the dubious value of null hypothesis statistical testing (NHST). The purpose of this article is to review the value of NHST and discuss its limitations and misuses. I n doing so, we advocate that NHST is of nominal utility in outcomes re search, and argue that rehabilitation researchers should focus on the calculation and interpretation of statistical power and effect size. D uring this era when outcomes are paramount, researchers in rehabilitat ion psychology cannot afford to conduct studies wherein significant me thodological shortcomings compromise the validity of the results. Reco mmendations for the appropriate use and interpretation of statistical analysis in outcomes research are offered.