ABSTRACT
It has become commonplace to speak of a “level of significance” in reporting outcomes of experiments. The shortage of publication space and the desire for objectivity it often seems that the responsibility for rejecting a hypothesis rests squarely on a crucial value in a table of probabilities. As Savage notes, publications tend to report the results of the test as well as that level of significance for which the corresponding test of the relevant family would be on the borderline between acceptance and rejection. Some publications, notably of social science content, have adopted a somewhat more extreme convention. From a commonly admitted tendency to acknowledge only the most significant findings, and from perusal of statements concerning publication pressures, one could infer another reasonable assumption. Since the Psychological Abstracts essentially attempt to present an outline of the major points made in almost all research articles of interest to psychologists the procedure used here could be checked for reliability with that publication.
