Title
A general approach to nonparametric empirical Bayes estimation
Keywords
Convergence rate; Empirical Bay estimation; Posterior quadratic risk; Reliability characteristics
Abstract
Let (X1, θ1), (X2, θ2),⋯, (XN, 0N), (XN+1, 0N+1) be independent random vectors with each θi- distributed according to some unknown prior density g. Given θi, let Xi have the conditional density qi(x/θi), i = 1,⋯, N + 1. In each pair the first component is observable, but the second is not. The objective is to estimate a known function b(θN+1) of θN+1. A general technique for construction of empirical Bayes estimators of b(θN+1) is proposed and their convergence rates are examined. The special case, when the conditional densities qi(x/θ), i = 1,⋯, N + 1, are identical, is also discussed. The theory is used to estimate of some reliability characteristics of nuclear power plant equipment.
Publication Date
1-1-1997
Publication Title
Statistics
Volume
29
Issue
1
Number of Pages
61-80
Document Type
Article
Personal Identifier
scopus
DOI Link
https://doi.org/10.1080/02331889708802574
Copyright Status
Unknown
Socpus ID
0039319762 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/0039319762
STARS Citation
Pensky, Marianna, "A general approach to nonparametric empirical Bayes estimation" (1997). Scopus Export 1990s. 2719.
https://stars.library.ucf.edu/scopus1990/2719