On Multiple Comparison of Geometric Means of Exponential Parameters via Graphical Model

作者:

DOI: 10.5351/KJAS.2006.19.3.447

关键词:

摘要: This paper develops a multiple comparison method for finding an optimal ordering of K geometric means exponential parameters. is based on the paired experimental arrangement whose results can naturally be represented by completely oriented graph. Introducing posterior preference probabilities and stochastic transitivity conditions to graph, we obtain new graphical model that yields criteria in comparison. Necessary theories involved some computational aspects are provided. Some numerical examples given illustrate efficiency suggested method.

参考文章(7)
L. Adleman, Molecular computation of solutions to combinatorial problems Science. ,vol. 266, pp. 1021- 1024 ,(1994) , 10.1126/SCIENCE.7973651
H. A. DAVID, Ranking from unbalanced paired-comparison data Biometrika. ,vol. 74, pp. 432- 436 ,(1987) , 10.1093/BIOMET/74.2.432
ROBERT TIBSHIRANI, Noninformative priors for one parameter of many Biometrika. ,vol. 76, pp. 604- 608 ,(1989) , 10.1093/BIOMET/76.3.604
Seong-Hee Kim, Barry L. Nelson, A fully sequential procedure for indifference-zone selection in simulation ACM Transactions on Modeling and Computer Simulation. ,vol. 11, pp. 251- 273 ,(2001) , 10.1145/502109.502111
Scott Gilbert, Distribution of Rankings for Groups Exhibiting Heteroscedasticity and Correlation Journal of the American Statistical Association. ,vol. 98, pp. 147- 157 ,(2003) , 10.1198/016214503388619175
ROGER R. DAVIDSON, DANIEL L. SOLOMON, A Bayesian approach to paired comparison experimentation Biometrika. ,vol. 60, pp. 477- 487 ,(1973) , 10.1093/BIOMET/60.3.477
P. Bauer, A note on multiple testing procedures in dose finding. Biometrics. ,vol. 53, pp. 1125- 1128 ,(1997) , 10.2307/2533569