The Use (and Misuse) of Statistical Significance Testing: Some Recommendations for Improved Editorial Policy and Practice.

The paper evaluates the logic underlying various criticisms of statistical significance testing and makes specific recommendations for scientific and editorial practice that might better increase the knowledge base. The effects of contemporary significance testing practice on the literature are evaluated. The paper explores why unconscious preferences for certain practices have emerged and why such practices are so impervious to change. The paper attempts to facilitate escape from some of the methodological paradigms that tend to unconsciously govern thinking regarding the processes of scientific inquiry. Few methodological offerings have sparked more controversy than Sir Ronald Fisher's (1925; 1926) contribution ..... the logic of null hypothesis testing. The last 30 years have involved periodic efforts (cf. Carver, 1978; Morrison & Henkel, 1970; Selvin, 1957;) by various researchers "to exorcise the null hypothesis" (Cronbach, 1975, p. 124). For example, Shaver (1979, pp. 5-6) has argued that The emphasis on statistics and the "test of significance" procedure has resulted in a methodolor:Ical orientation toward establishing generalizability that has ben deleterious in its effects on the scientific accumulation of knowledge