Abstract
A criticism is offered for the recent efforts to encourage psychologists to report the proportion of variance accounted for (ω2 ) by analysis of variance effects. Few psychological experiments employ designs that allow legitimate inferences as to the strength of particular effects. As such, ω2 is a descriptive statistic that is extremely limited in its usefulness. It is suggested that a widespread reporting of ω2 in psychology is not only unnecessary, but could also be misleading.
Article PDF
Similar content being viewed by others
References
Danks, J. H. Grammaticalness and meaningfulness in the comprehension of sentences. Journal of Verbal Learning & Verbal Behavior, 1969, 8, 687–696.
Dodd, D. H., & Schultz, R. F. Computational procedures for estimating magnitude of effect for some analysis of variance designs. Psychological Bulletin, 1973, 79, 391–395.
Hays, W. L. Statistics for psychologists. New York: Holt, Rinehart & Winston, 1963.
Loftus, E. F. Category dominance, instance dominance, and categorization time. Journal of Experimental Psychology, 1973, 97, 70–74.
Vaughan, G. M. & Corballis, M. C. Beyond tests of significance: Estimating strength of effects in selected ANOVA designs. Psychological Bulletin, 1969, 72, 204–213.
Author information
Authors and Affiliations
Additional information
We are grateful to Clyde Hendrick, Roy Lachman, Roy S. Lilly, and Terry J. Spencer for their comments on an earlier version of this manuscript.
Rights and permissions
About this article
Cite this article
Dooling, D.J., Danks, J.H. Going beyond tests of significance: Is psychology ready?. Bull. Psychon. Soc. 5, 15–17 (1975). https://doi.org/10.3758/BF03336685
Received:
Published:
Issue Date:
DOI: https://doi.org/10.3758/BF03336685