摘要:

A class of estimation procedures that are robust, relatively efficient, and yet computationally simple is proposed for the one- and two-sample location problems. Particular emphasis is placed on the problem of determining confidence intervals, a topic that has seen limited exposure in the literature. As a by-product, some interesting point estimates are obtained. A class of score functions that are ordinary step functions is considered for the location model. Point estimates and confidence intervals are obtained by inverting the corresponding rank statistics. Efficiency and robustness properties of the procedures are investigated. Simple computational schemes for the estimates and intervals are provided.

ISSN:0162-1459    

DOI:10.1080/01621459.1982.10477905

出版商:Taylor & Francis Group    

年代:1982

数据来源: Taylor

摘要:

We study the family of power transformations proposed by Box and Cox (1964) when the choice of the power parameter λ is restricted to a finite set ΩR. The behavior of the Box-Cox procedure is as anticipated in two extreme cases: when the true parameter λ is an element of ΩRand when λ is “far” from ΩR.We study the case in which λ0is “close” to ΩR, finding that the resulting methods can be very different from unrestricted maximum likelihood and that inferences may depend on the design, the values of the regression parameters, and the distance of λ to ΩR.

ISSN:0162-1459    

DOI:10.1080/01621459.1982.10477906

出版商:Taylor & Francis Group    

年代:1982

数据来源: Taylor

摘要:

Consider a polynomial regression situation on an interval and also a robustness-type formulation of Stigler's. A technique involving canonical moments is discussed and some explicit solutions are given.

ISSN:0162-1459    

DOI:10.1080/01621459.1982.10477907

出版商:Taylor & Francis Group    

年代:1982

数据来源: Taylor

摘要:

In this article we present a general Bayesian approach to discrimination. We describe how the difference between two separate families of distributions can be assessed in terms of differences between two binomial models. Two examples that illustrate the methodology are included. Specifically, we investigate the extent to which it is possible to discriminate between the von Mises and the wrapped normal distributions and also between the normal and a family oftdistributions.

ISSN:0162-1459    

DOI:10.1080/01621459.1982.10477908

出版商:Taylor & Francis Group    

年代:1982

数据来源: Taylor

摘要:

Order statistics from a strongly unimodal distribution are strongly unimodal.

ISSN:0162-1459    

DOI:10.1080/01621459.1982.10477909

出版商:Taylor & Francis Group    

年代:1982

数据来源: Taylor

摘要:

Among the many reasons underlying the practice of randomization some of the main ones can be described asaveragingout oreliminationof the effects of nuisance parameters. It is already well known (Godambe 1966) that averaging over all the possible results of the adopted randomization is directly in conflict with thelikelihood principle.The process of elimination of nuisance parameters has possibly deeper intuitive appeal. But this process contradicts a very basic principle of statistical inference subsequently defined as theancillarity principle.This is demonstrated in relation to a practice of randomization calledbalanced sampling.We would use a formalism very similar to that of Birnbaum (1962).

ISSN:0162-1459    

DOI:10.1080/01621459.1982.10477910

出版商:Taylor & Francis Group    

年代:1982

数据来源: Taylor

摘要:

Suppose several parameters are to be estimated in sequence. Independent data relating to them are available, but data later in the sequence cannot be used to estimate earlier parameters. Then the use of an admissible estimator for each individual parameter is an admissible procedure in the combined problem using summed loss. If the estimator werenotrequired to be nonanticipative, the use might be inadmissible as in Stein's famous inadmissibility result.

ISSN:0162-1459    

DOI:10.1080/01621459.1982.10477911

出版商:Taylor & Francis Group    

年代:1982

数据来源: Taylor

摘要:

Mathematics of Genetic Diversity.: J.F.C. Kingman. Philadelphia: Society for Industrial and Applied Mathematics, 1980. vii + 70 pp. $13.00 (paperback). reviewed by C.C. Heyde

ISSN:0162-1459    

DOI:10.1080/01621459.1982.10477912

出版商:Taylor & Francis Group    

年代:1982

数据来源: Taylor

ISSN:0162-1459    

DOI:10.1080/01621459.1982.10477913

出版商:Taylor & Francis Group    

年代:1982

数据来源: Taylor

摘要:

This article has no abstract

ISSN:0162-1459    

DOI:10.1080/01621459.1982.10477874

出版商:Taylor & Francis Group    

年代:1982

数据来源: Taylor