EVIDENCE, INFERENCE, AND THE REJECTION OF THE SIGNIFICANCE TEST

Hammond (1996) reiterates Cohen's (1994) ''attack'' on simple-minded i nterpretations of significance tests and recommends the use of other s tatistical methods (including effect size measures and confidence inte rvals) in their place. Hammond's laudable aim is to inform the Austral ian psychology community of the resurgence of this debate in the US, a nd to open these issues to overdue debate here. In this paper we take the stand that the issues underlying some of the criticisms in this de bate have not been well drawn. In particular, we believe that the fund amental distinction between the interpretation of probability as relat ive frequency and its interpretation as evidentiary-belief - a distinc tion underlying the history of confusion about statistical inference i n psychology and elsewhere - is still not receiving the major focus it requires in this debate. We argue that these interpretive issues are just as relevant for confidence intervals as for significance tests an d that the problem of inference - that of specifying how sample data p rovide evidence about unknown population parameters - is not a purely mathematical one. As a result, such issues should not be left to the ' 'statistical types'' among us; rather, psychologists who wish to perfo rm or evaluate research and the conclusions drawn from it need to unde rstand the different approaches that have been taken to the problem. I ndeed, we see the encouragement - and liberty - to re-think the role o f data analysis in the interpretation of our research findings as the most positive aspect of the debate.