A G1-Minimax Estimator for a Linear Combination of Binomial Probabilities

A G 1 -minimax estimator for an arbitrary linear combination of binomial probabilities {θ i } is derived. Only the mean of each prior distribution is specified. The resulting G 1 -minimax estimator is shown to be formed by estimating each θ i by a weighted average of its prior mean and its maximum l...

Full description

Saved in:
Bibliographic Details
Published in:Journal of the American Statistical Association 1974-03, Vol.69 (345), p.231-233
Main Authors: Derouen, T. A., Mitchell, Toby J.
Format: Article
Language:English
Subjects:
A priori knowledge
Bayes estimators
Binomial coefficients
Binomials
Coefficients
Consistent estimators
Estimators
Maximum likelihood estimation
Minimax
Statistics
Theory and Methods
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:A G 1 -minimax estimator for an arbitrary linear combination of binomial probabilities {θ i } is derived. Only the mean of each prior distribution is specified. The resulting G 1 -minimax estimator is shown to be formed by estimating each θ i by a weighted average of its prior mean and its maximum likelihood estimate.
ISSN:0162-1459
1537-274X
DOI:10.1080/01621459.1974.10480160