Alternative Estimators for the Scale Parameter of the Exponential Distribution with Unknown Location
Brewster, J. F.
Ann. Statist., Tome 2 (1974) no. 1, p. 553-557 / Harvested from Project Euclid
Let $X_1, X_2,\cdots, X_n$ be independent observations from an exponential distribution with an unknown location-scale parameter $(\mu, \sigma)$. Let $\bar{X} = n^{-1} \sum X_i$ and $M = \min X_i$. Under squared error loss the best location-scale equivariant estimator of $\sigma$ is $\bar{X} - M$, which agrees with the maximum likelihood estimator. Arnold (J. Amer. Statist. Assoc. 65 (1970) 1260-1264) and Zidek (Ann. Statist. 1 (1973) 264-278) have shown that $\bar{X} - M$ is inadmissible but the dominating estimator which they produce is probably inadmissible as well. In this paper a "smoother" dominating procedure is presented, and the risk functions of the various alternatives are plotted. Similar results are obtained for strictly bowl-shaped loss functions.
Publié le : 1974-05-14
Classification:  Exponential scale estimators,  improving estimators,  bowl-shaped loss functions,  62C15,  62F10
@article{1176342715,
     author = {Brewster, J. F.},
     title = {Alternative Estimators for the Scale Parameter of the Exponential Distribution with Unknown Location},
     journal = {Ann. Statist.},
     volume = {2},
     number = {1},
     year = {1974},
     pages = { 553-557},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176342715}
}
Brewster, J. F. Alternative Estimators for the Scale Parameter of the Exponential Distribution with Unknown Location. Ann. Statist., Tome 2 (1974) no. 1, pp.  553-557. http://gdmltest.u-ga.fr/item/1176342715/