On Appropriate Uses and Interpretations of Power Analysis: A Comment

Issues of Power: Rejoinder

“…However, the sentence immediately preceding it in the original article (Brewer, 1972, p. 391) is: "The computation is essential to the interpretation of negative results, that is, failures to reject the null hypothesis." This statement, besides being objectionable for the same reasons given by Dayton et al (1973), provides the mental set that Brewer thought power was useful for something beyond its calculation a priori.The statement in point (2) regarding coin-flipping is said by Brewer to be …”

Debate

“…This is relevant to a Bayesian, but only the loss function is necessary in the above decision theory. Dayton et al (1973) imply that the researchers surveyed should construct confidence intervals since they were disappointed with the wide intervals which would result with the sample sizes reported by Brewer. I feel sympathetic to this view except to note that the construction of an interval is of no utility if one is interested in two-action problems.…”

“…Dayton et al (1973) also pointed out the conditional nature of power. In their discussion they refer to the Bayesian inference model and while not necessarily intending to imply that Brewer is correct if interpreted Bayesianly, some readers might infer this from their comments.…”

“…With the critiques by Cohen (1973) and Dayton et al (1973). I feel it necessary to present my views and a Bayesian analysis in order that readers will not be misled as mentioned above.…”

Advantages of Computer Programs over Power Charts for the Estimation of Power

“…One of the earliest articles on this topic was by Cohen (1962), who documented a lack of concern toward power among researchers. Despite attention to this topic by methodologists in the quantitative research literature (e.g., Brewer 1972;Dayton, Schafer, and Rogers 1973), concern over power has not abated (Thomas and Krebs 1997, pp. 128-139).…”