A statistical power analysis of applied psychological research.

Abstract

The average statistical power exhibited in the 1974 volume of the Journal oj Applied Psychology was studied. One hundred twenty-one articles were poweranalytically examined using three effect-size estimates, standardized (.05) alpha level, and assuming nondirectional nulls. The mean power figures for small, medium, and large population effect-size estimates were .25, .66, and .84, respectively. Interdisciplinary comparisons involving abnormal-social psychology, education, and communication indicate that applied psychology is relatively strong in terms of average statistical power.

Statistical Power and the Testing of Null Hypotheses: A Review of Contemporary Management Research and Recommendations for Future Studies

“…The belief is that the consequences of a false positive (Type I error) claim are more serious than those of a false negative (Type II error) claim. As a result, Type I errors are usually focused on more frequently and guarded against more stringently by researchers (Baroudi & Orlikowski, 1989;Brewer, 1972;Chase & Chase, 1976;Cohen, 1977;Cowles & Davis, 1982;Greenwald, 1993;Mazen, Graf, et al, 1987;Myers & Melcher, 1969;Mone et al, 1996;Nickerson, 2000;Rossi, 1990;Sedlmeier & Gigerenzer, 1989). However, it is important to note that several authors (e.g., Mazen, Graf, et al, 1987;Sauley & Bedeian, 1989) advocate distributing the risk between Type I and Type II errors because the risks/consequences associated with committing a Type II error may be extremely costly.…”

POWERF: A program that computes the power of F tests in fixed-effects ANOVA designs

“…His findings of minimal power values of statistical tests in published research has been replicated by Brewer (1972) in educational research and by Chase and Chase (1976) in applied psychology.…”

Conducting tests of hypotheses: The need for an adequate sample size

“…However, if they cannot tolerate the adjusted levels of alpha, power or both, that is, if alpha is too high or power too low to be justifiable from a research point of view, then they should consider postponing the study until they can get a larger sample. Cohen (1962), Brewer (1972), Jones and Brewer (1972), Penick and Brewer (1972), Brewer and Owen (1973), Katzer and Sodt (1973), and Chase and Chase (1976), respectively, the researchers found a dismal state of affairs with regard to the power of the tests conducted, as indicated in Table 2. Table 2: Results of studies on the power of hypotheses tests…”

“…Journal of Applied Psychology Chase and Chase (1976) . 25 .67 .86 known, as one does not have the population scores at hand.…”