Minimum Bayes Riskt-Intervals for Multiple Comparisons
- 1 December 1975
- journal article
- theory and-method
- Published by Taylor & Francis in Journal of the American Statistical Association
- Vol. 70 (352) , 822-831
- https://doi.org/10.1080/01621459.1975.10480309
Abstract
The purpose is to develop interval estimates for differences between treatment means which, when used for testing, would be equivalent to the Waller-Duncan k-ratio rule for multiple comparisons. First the intervals are derived from a family of extended k-ratio Bayes testing rules (exchangeable priors and additive linear losses). Then the intervals are shown to be Bayes also (same priors and squared-error losses). Particularly striking is the dependence of width and location on the between-treatments F-ratio rather than the number of treatments. As F decreases the new k-ratio t-intervals shrink in width and shift toward zero.Keywords
This publication has 12 references indexed in Scilit:
- A bayes solution for the problem of ranking Poisson parametersAnnals of the Institute of Statistical Mathematics, 1971
- BAYESIAN COMPARISONS OF THE ORIGINS OF TRANSLATED EXPONENTIAL DISTRIBUTIONS1Australian Journal of Statistics, 1970
- A Bayes Rule for the Symmetric Multiple Comparisons ProblemJournal of the American Statistical Association, 1969
- A Bayesian Approach to the Problem of Ranking Binomial ProbabilitiesSIAM Journal on Applied Mathematics, 1968
- Bayes rules for comparisons of scale parameters of certain distributionsAnnals of the Institute of Statistical Mathematics, 1967
- Bayesian analysis of random-effect models in the analysis of variance. I. Posterior distribution of variance-componentsBiometrika, 1965
- A Bayesian Approach to Multiple ComparisonsTechnometrics, 1965
- Length of Confidence IntervalsJournal of the American Statistical Association, 1961
- A Theory of some Multiple Decision Problems, IThe Annals of Mathematical Statistics, 1957
- Multiple Range and Multiple F TestsPublished by JSTOR ,1955