摘要:

The paper reconsiders some of the recent developments in experimental design for linear regression models. Atfirst, some attention is paid to a discussion of the advantages and limitations of a decision–theoretically oriented approach to the compound problem including the choice of set–up, estimator and experimental design, with special emphasis on the use of prior knowledge and on robustness inverstigations. In the main part of the paraper we review and discuss our results obtained since 1979 concerning BAYESian experimental design and experimental design in case of correalted observations. As a main feaurer we can point out an analogy between continuous experimental designing and linear regression estimation which opens the possibility to use experimental designs methods for the ocnstructions of optimal lineal estimators. This is demosntrated, in praticular, for the fields of minimaz linear estiamtion with a restircted parameter space and best linear unbiased estimation of the trend functions of random processes

ISSN:0233-1888    

DOI:10.1080/02331888708802008

出版商:Akademie-Verlag    

年代:1987

数据来源: Taylor

摘要:

N. A. Rahman: Theoretical Execises in Probability and Statistics, 2nd ed. Griffin & Co., Ltd., High Wycombe 1983, xi, 440 S., 18.95.

ISSN:0233-1888    

DOI:10.1080/02331888708802009

出版商:Akademie-Verlag    

年代:1987

数据来源: Taylor

摘要:

Since the explicit determination of the minimax estimator in th elinear regression model usually is difficult we propose to minimize an upper bound of the maximal risk instead. The resulting estimator coincides with the minimax estimator when the weight matrix of the risk function has rank one. Specific attention is paid to additional equality restrictions

ISSN:0233-1888    

DOI:10.1080/02331888708802010

出版商:Akademie-Verlag    

年代:1987

数据来源: Taylor

摘要:

It is shown that, by a reparametrization, the problems of estimationg a linear combination of variance components can be reduced to that of estimating a single variance component. Such a reduction is used to obtain some characterizations of nonnegatively estimable linear combinations of varaince components. Characterization of nonnegative estimability using MINQUE is also discussed

ISSN:0233-1888    

DOI:10.1080/02331888708802011

出版商:Akademie-Verlag    

年代:1987

数据来源: Taylor

摘要:

We show how the likelihood equation can be simplified for the so called balanced mixed of MANOVA

ISSN:0233-1888    

DOI:10.1080/02331888708802012

出版商:Akademie-Verlag    

年代:1987

数据来源: Taylor

摘要:

D. Szynal, A. Weron: Probability Theory on Vector Spaces III. Proc., Lublin 1983. Lect. Notes in Math. 1080. Springer-Verlag, Berlin - Heidelberg - New York - Tokyo 1984, v, 373 pp., DM 51,50.

ISSN:0233-1888    

DOI:10.1080/02331888708802013

出版商:Akademie-Verlag    

年代:1987

数据来源: Taylor

摘要:

For an unbalanced one way calssification under the random effect model the problem of estimation of the fixed effect parameter and the variance is considered. Tje error variance which are funtionally related to the above set of parameters are assumed to fall into k classes with constant error varaince for a class. The asymptotic properties of the proposed estimate is established for increasing number of classes k, assuming the number of observations in the classes form a fixed sequence

ISSN:0233-1888    

DOI:10.1080/02331888708802014

出版商:Akademie-Verlag    

年代:1987

数据来源: Taylor

摘要:

F. Mosteller, D. L. Wallace: Applied Bayesian and Classical inference: The Case of the Federalist Papers. (Springer Series in Statistics) Springer-Verlag,Berlin - Heidelberg - New York - Tokyo 1984, 11 figs, XXXVII, 303 pp., DM 92,-, ISBN 3-540-90991-5.

ISSN:0233-1888    

DOI:10.1080/02331888708802015

出版商:Akademie-Verlag    

年代:1987

数据来源: Taylor

摘要:

Asymptotically with probability close to one, the convergence in variation (also in distribution) to the multivariate normal, of the aposteriori density function of a parameter agains an apriori density, viz. the BERNSTEIN–VON MISES results are established when observations are not necessarily indenpendent or identically distributed but satisfy weak regularity assumptions on their joint density function. Regular BAYES' estimators are defined with respect to regular loss functions and a positive apriori density and proved consistent, asymptotically efficient and asymptotically normal. Examples and applications to conjugate families of densities, to inference in MARKOV Chains and other nonstandard cases illustrate results

ISSN:0233-1888    

DOI:10.1080/02331888708802016

出版商:Akademie-Verlag    

年代:1987

数据来源: Taylor

ISSN:0233-1888    

DOI:10.1080/02331888708802019

出版商:Akademie-Verlag    

年代:1987

数据来源: Taylor