摘要:

This illuminating paper by Stone is the latest in a series of papers drawing attention to possible disadvantages of using nonintegrable prior densities. In these comments, I shall attempt to clarify the role of nonintegrable prior densities in Bayesian inference, thereby providing also a delayed answer to James and Stein [5], Dempster [1], Stone [9], Klotz,et al.[6], and Portnoy [7]. More extensive discussion of the ideas introduced will be given in a subsequent paper.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481491

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481492

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481493

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481494

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481496

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481498

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

In linear models, anF-test may be used to decide on restricted or unrestricted estimators. To avoid the arbitrariness of the significance level and undesirable quadratic risk properties, a regret criterion is proposed, extending the results of Sawa and Hiromatsu [4].

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481499

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

This paper describes admissible hypothesis tests for Markov order, the tests being defined on certain conditioned variables. In the spirit of classical hypothesis testing, the tests have the following appealing properties: The power function is constant on the hypothesis set (and, therefore, the level is not pessimistic), and the test is asymptotically most powerful within the class of tests based on regular estimators. Application of the tests herein derived to simulated and actual hydrologic data indicates that our test is superior to the usual chi-square test for Markov order, and that with moderate amounts of data, conclusions with significant physical import can be gleaned.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481500

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

A new stopping rule, together with play-the-winner sampling, is used to select the better of two binomial populations. This procedure is designed to reduce the expected number of trials on the poorer population. Numerical results are given which indicate that this procedure performs better (often substantially better) in this sense than existing alternatives. Asymptotic mathematical results are also given.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481501

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor

摘要:

Gupta has presented a method which, given samples of sizenfrom each ofknormal populations, selects a subset of thekpopulations which contains the population with the largest mean, with probability at leastP* The method guarantees thisP* no matter how small the differences between populations. The experimenter may only be interested in differences which are greater than some indifference. This difference allows either smaller subsets or a larger claimedP* for a given subset. An approximation using Gupta's and Sobel's tables and brief exact tables are presented.

ISSN:0162-1459    

DOI:10.1080/01621459.1976.10481502

出版商:Taylor & Francis Group    

年代:1976

数据来源: Taylor