The lower limits of a confidence ratio (proportion of alternative hypotheses accepted that are true) and a power ratio (proportion of true H1s tested that are accepted) were proposed by Hand, et al. (1985) to help make statistical decisions. It is argued that the proposed ratios are statistically questionable and of little practical use. Alternative ways to ensure meaningful statistical decisions are presented.
Get full access to this article
View all access options for this article.
References
1.
BickelP. J.DoksumK. A. (1977) Mathematical statistics. San Francisco, CA: Holden-Day.
2.
Erratum. (1985) Perceptual and Motor Skills, 61, No. 3(Part 1).
3.
HandJ.JannaroneR. J.LaughlinJ. E.HandM. R. (1985) Developing an estimate of the lower bound of a confidence ratio for statistical decisions. Perceptual and Motor Skills, 61, 599–602.
