论文信息 - A Bayesian Method for Comparing the Means of Multinomial Populations

A Bayesian Method for Comparing the Means of Multinomial Populations

Let X(Y) be a random variable which takes on the values a1 …, ak with probabilities p1,…,pk (p′1, …, p′k) respectively. Let μx = a1p1 +… + akpk and μv = a1p′1 + … + akp′k. A Bayesian approach to comparing μx and μv is considered. An extension of the results to multiple comparisons is suggested.

Robert H. Lochner

[1] E. Belbin,et al. Programmed instruction as a method of teaching paired associates to older learners. , 1967, Journal of gerontology.

[2] Geoffrey S. Watson,et al. A Bayesian Study of the Multinomial Distribution , 1967 .

[3] Melvin R. Novick,et al. A Bayesian Approach to the Analysis of Data from Clinical Trials , 1965 .

[4] G. Box. Some Theorems on Quadratic Forms Applied in the Study of Analysis of Variance Problems, I. Effect of Inequality of Variance in the One-Way Classification , 1954 .

[5] A. Basu,et al. Bayesian Analysis of the Two-Sample Problem with Incomplete Data , 1972 .

[6] I. Good. A Bayesian Significance Test for Multinomial Distributions , 1967 .

[7] H. Raiffa,et al. Applied Statistical Decision Theory. , 1961 .