OUP user menu


Darren Dahl (Editor in Chief)Eileen FischerGita JoharVicki Morwitz

18 out of 120

From the Editor

Dawn Iacobucci
DOI: http://dx.doi.org/10.1086/430648 6-11 First published online: 1 June 2005

On p-values

Periodically, social scientists debate the strengths and weaknesses of hypothesis testing (for which researchers pose the question, e.g., “Are my group means the same or different?”) compared with effects estimation (motivated by the question, “How large is the difference between my group means?”). As is often the case, the extreme positions are clear but they approach ideology, and a moderate stance seems the more constructive prescription.

The testing of null hypotheses affords researchers many advantages (Abelson 1997; Cortina and Dunlap 1997; Frick 1996; Greenwald et al. 1996; Hagen 1997; Harris 1997; Mulaik, Raju, and Harshman 1997). Of primary importance, the test of a null hypothesis is conducted in the context of a simple decision rule and provides a dichotomous outcome (Greenwald et al. 1996, 177). While critics would argue that hypothesis tests provide less information compared to alternative techniques, supporters argue that the binary decisions nevertheless enable scholarly progress and theory testing, which “requires nothing more than a binary decision about the relation between two variables” (Chow 1988, 105; Wainer 1999).

Issues with Null Hypothesis Testing

When hypothesis testing is criticized, it derives not so much from anything inherent to the technique or philosophy itself as from users' fallacious interpretations of the corresponding results. There are several major concerns.

The first concern is the misinterpretation of a finding when a computed test statistic does not exceed a critical value. We quickly learn to avoid the improper semantics of “accepting” the null hypothesis, in part because there are “many ways (including incompetence of the researcher), other than the null hypothesis being …

View Full Text

Sign in

Log in through your institution

Sign in as a personal subscriber

Log in through your institution

Purchase a personal subscription