๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Admissibility of the constant-coverage probability estimator for estimating the coverage function of certain confidence interval

โœ Scribed by Hsiuying Wang

Publisher
Elsevier Science
Year
1998
Tongue
English
Weight
283 KB
Volume
36
Category
Article
ISSN
0167-7152

No coin nor oath required. For personal study only.

โœฆ Synopsis

Consider a confidence interval for a randomly chosen linear combination of the elements of the mean vector of a p-dimensional normal distribution. The constant coverage probability is the usual estimator for the coverage function of this interval. Wang (1995) have shown that this estimator is inadmissible under the squared error loss, if p~>5. In this paper, we consider the case where p~<4 and prove that it is admissible under the same loss. @ 1998 Elsevier Science B.V.

๐Ÿ“œ SIMILAR VOLUMES

Can coverage of confidence intervals be
Can coverage of confidence intervals be used to judge the goodness of point estimators in finite population double sampling?
โœ A.Adam Ding ๐Ÿ“‚ Article ๐Ÿ“… 2000 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 80 KB

It is shown that there exists no valid conรฟdence interval under nonparametric double-sampling model. Hence the low coverage of the associated conรฟdence intervals in some situations should not be used against the application of the regression estimator, because it is a universal phenomenon for all es

Improved confidence estimators for the u
Improved confidence estimators for the usual one-sided confidence intervals for the ratio of two normal variances
โœ Hsiuying Wang ๐Ÿ“‚ Article ๐Ÿ“… 2002 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 116 KB

The usual conรฟdence intervals for the ratio of two normal variances are constructed from F-distribution. These conรฟdence intervals are especially important in the variance component model. In this paper, I focus on conรฟdence estimate and conditional performance of these conรฟdence intervals. Under so