Admissible Minimax Estimation of a Multivariate Normal Mean with Arbitrary Quadratic Loss
Berger, James O.
Ann. Statist., Tome 4 (1976) no. 1, p. 223-226 / Harvested from Project Euclid
The problem of estimating the mean of a $p$-variate $(p \geqq 3)$ normal distribution is considered. It is assumed that the covariance matrix $\not\sum$ is known and that the loss function is quadratic. A class of minimax estimators is given, out of which admissible minimax estimators are developed.
Publié le : 1976-01-14
Classification:  Admissible,  minimax,  normal mean,  generalized Bayes,  quadratic loss,  62C15,  62F10,  62H99
@article{1176343356,
     author = {Berger, James O.},
     title = {Admissible Minimax Estimation of a Multivariate Normal Mean with Arbitrary Quadratic Loss},
     journal = {Ann. Statist.},
     volume = {4},
     number = {1},
     year = {1976},
     pages = { 223-226},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176343356}
}
Berger, James O. Admissible Minimax Estimation of a Multivariate Normal Mean with Arbitrary Quadratic Loss. Ann. Statist., Tome 4 (1976) no. 1, pp.  223-226. http://gdmltest.u-ga.fr/item/1176343356/