No label defined (Q3694495)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 3919605
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | No label defined |
scientific article; zbMATH DE number 3919605 |
Statements
1985
0 references
tables
0 references
estimation of reliability function
0 references
scale parameter
0 references
type II censored sample
0 references
exponential failure distribution
0 references
prior distribution
0 references
shrunken estimator
0 references
Bayesian shrinkage estimators
0 references
maximum likelihood estimators
0 references
0.8712393045425415
0 references
0.868683934211731
0 references
In this paper the problem of estimation of reliability function R(t) and the scale parameter \(\theta\) from a type II censored sample with exponential failure distribution is considered. The problem of shrinking an unbiased estimator \({\tilde \theta}\) of the parameter \(\theta\) was considered by several authors. The ordinary shrunken estimator, K\({\tilde \theta}+(1-K)\theta_ 0\), with K a constant (0\(\leq K\leq 1)\), was found to be better than \({\tilde \theta}\) if \(\theta\) is close to the natural origin \(\theta_ 0.\) Here we postulate a prior distribution for the parameter around the natural origin and use the ordinary Bayes estimator in place of \(\theta_ 0\) in the ordinary shrunken estimator. Bayesian shrinkage estimators of \(\theta\) and R(t) have thus been obtained and Monte Carlo study of their efficiencies with respect to unbiased and maximum likelihood estimators (mle's) was undertaken and it was found that the proposed estimators are better than unbiased estimators and mle's.
0 references