1. |
On admissible invariant estimators of variance components which dominate unbiased invariant estimators |
|
Statistics,
Volume 18,
Issue 4,
1987,
Page 483-498
W. Klonecki,
S. Zontek,
Preview
|
PDF (3890KB)
|
|
摘要:
A characterization of admissible invariant quadratic estimators for linear combinations of variance components for mixed linear models is established.This allows us to construct for the balanced random, one–way ANOVA model, as well as for some other mixed linear models, admissible estimators which are also better than the best unbiased estimator with respect to the matrix risk function. Admissible estimators better than the best unbiased estimator may be used to construt admissible estimators which dominate the unbiased estimators for any parametric function of the variance components.
ISSN:0233-1888
DOI:10.1080/02331888708802046
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
2. |
A note on estimating the msep in nonlinear regression |
|
Statistics,
Volume 18,
Issue 4,
1987,
Page 499-520
BERND Droge,
Preview
|
PDF (5933KB)
|
|
摘要:
We consider the problem of estimating the mean squared error of prediction in the nonlinear regression case using the bootstrap and cross–validation approach.Emphasis is put on numerical economy in calculating the different estimates. For comparison,alterative proposals known from the literature are briefly discussed.Our in vestigation lead to the recommendation of some variants of bootstrap estimates.
ISSN:0233-1888
DOI:10.1080/02331888708802047
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
3. |
On a adaptive design in regression |
|
Statistics,
Volume 18,
Issue 4,
1987,
Page 521-525
R. Schwabe,
Preview
|
PDF (1300KB)
|
|
摘要:
GEBHARDT and HECKENDORFF [5] proposed an adaptive design for the linear regression problem and iillstrated its use by simulation .In this note we give an exact proof for their one–step adaptive design to be superior relatively to the A–optimal determinstic design with respect to some modified A–criterion.
ISSN:0233-1888
DOI:10.1080/02331888708802048
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
4. |
Book review |
|
Statistics,
Volume 18,
Issue 4,
1987,
Page 526-526
Preview
|
PDF (236KB)
|
|
ISSN:0233-1888
DOI:10.1080/02331888708802049
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
5. |
Contamination games in a robust k–sample model |
|
Statistics,
Volume 18,
Issue 4,
1987,
Page 527-562
HELMUT RIEDER,
Preview
|
PDF (8587KB)
|
|
摘要:
Given a k–sample model indexed by one real parameter θ,the statistician's task is considered to estimate θ robustly when Nature may assign varying contamination to each sample subject to some overall average contamination. After determining the estimators which are asymptotically optimum for a fixed contamination, asymptotic minimax estimators. least favorable contaminations, and saddle points are derived for the contamination game. Different loss criteria are employed: asymptotic variance, confidence interval loss, mean squared error, and general non–negative, monotone, convex loss. The different kinds of contamination used are: constant(symmetric)∈–contamination in the variance case, and for the other loss criteria infinitesimal contamination of the types: HELLINGER, total variation, ∈–contamination.Minimax estimators for infinitesimal contamination are obtained by uniformly bounding the influence curves(∈–contamination, total variation) or their variance (HELLINGER). The existence of saddle points is shown quite generally, only for infinitesimal ∈– contamination depending on a proporrionality property of the minimax influence curve. In all cases, the least favorable contamination assignt largest contamination to the most informative samples.
ISSN:0233-1888
DOI:10.1080/02331888708802050
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
6. |
An asymptotically most bias–stable estimator of location parameter |
|
Statistics,
Volume 18,
Issue 4,
1987,
Page 563-571
TOMASZ Rychlik,
Preview
|
PDF (1910KB)
|
|
摘要:
In the paper, a sequence of equivariant estimators of location parameter which is asymptotically most bias–stable under nonidentically distributed disturbances in the metric of the KOLMOGOROV–LEVY type ,is constructed without any assumption about the location model. The sequence consists of properly chosen order statistics modified by adding a constant. Some examples of location models are considered.
ISSN:0233-1888
DOI:10.1080/02331888708802051
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
7. |
Book review |
|
Statistics,
Volume 18,
Issue 4,
1987,
Page 572-572
Preview
|
PDF (167KB)
|
|
ISSN:0233-1888
DOI:10.1080/02331888708802052
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
8. |
R–estimation of normed bivariate density functions |
|
Statistics,
Volume 18,
Issue 4,
1987,
Page 573-585
Egmar Rödel,
Preview
|
PDF (2334KB)
|
|
摘要:
Normed bivariate density funtions were introduced by HOEFFDING (1940/41). In the present paper estimators for normed bivariate ranks and on a FOURIER series expansion in LEGENDRE polynomials. The estimation of normed bivarate density functions under positive dependence is also described
ISSN:0233-1888
DOI:10.1080/02331888708802053
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
9. |
Book review |
|
Statistics,
Volume 18,
Issue 4,
1987,
Page 586-586
Preview
|
PDF (296KB)
|
|
ISSN:0233-1888
DOI:10.1080/02331888708802054
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|
10. |
Note on parameter estimation for general non–linear time series models |
|
Statistics,
Volume 18,
Issue 4,
1987,
Page 587-590
Wilfried Loges,
Preview
|
PDF (2740KB)
|
|
摘要:
Least squares estimation is shown to be strongly consistent for non–linear autoregressive processes. The use of KRONECKER'S lemma enables us to avoid any assumptions about integrability and stationarity of the underlying time series
ISSN:0233-1888
DOI:10.1080/02331888708802055
出版商:Akademie-Verlag
年代:1987
数据来源: Taylor
|