Estimation of Normal Means: Frequentist Estimation of Loss
Lu, K. L. ; Berger, James O.
Ann. Statist., Tome 17 (1989) no. 1, p. 890-906 / Harvested from Project Euclid
In estimation of a $p$-variate normal mean with identity covariance matrix, Stein-type estimators can offer significant gains over the $\operatorname{mle}$ in terms of risk with respect to sum of squares error loss. Their maximum risk is still equal to $p$, however, which will typically be their "reported loss." In this paper we consider use of data-dependent "loss estimators." Two conditions that are attractive for such a loss estimator are that it be an improved loss estimator under some scoring rule and that it have a type of frequentist validity. Loss estimators with these properties are found for several of the most important Stein-type estimators. One such estimator is a generalized Bayes estimator, and the corresponding loss estimator is its posterior expected loss. Thus Bayesians and frequentists can potentially agree on the analysis of this problem.
Publié le : 1989-06-14
Classification:  Estimated loss,  communication loss,  communication risk,  Stein estimation,  generalized Bayes estimator,  posterior variance,  62J07,  62C10,  62C15
@article{1176347149,
     author = {Lu, K. L. and Berger, James O.},
     title = {Estimation of Normal Means: Frequentist Estimation of Loss},
     journal = {Ann. Statist.},
     volume = {17},
     number = {1},
     year = {1989},
     pages = { 890-906},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176347149}
}
Lu, K. L.; Berger, James O. Estimation of Normal Means: Frequentist Estimation of Loss. Ann. Statist., Tome 17 (1989) no. 1, pp.  890-906. http://gdmltest.u-ga.fr/item/1176347149/