Admissibility of the estimate of least squares. Unusual property of the normal law
Matematičeskie zametki, Tome 6 (1969) no. 1, pp. 81-89
Cet article a éte moissonné depuis la source Math-Net.Ru
It is shown that in the linear-regression scheme, the estimates of the squares of parametric vector-functions are admissible in the class of unbiased estimates if and only if the observations obey a normal law. Here, the covariation matrix (non-negative definite) serves as a measure of the quality of the estimate.
@article{MZM_1969_6_1_a9,
author = {A. M. Kagan and O. V. Shalaevskii},
title = {Admissibility of the estimate of least squares. {Unusual} property of the normal law},
journal = {Matemati\v{c}eskie zametki},
pages = {81--89},
year = {1969},
volume = {6},
number = {1},
language = {ru},
url = {http://geodesic.mathdoc.fr/item/MZM_1969_6_1_a9/}
}
A. M. Kagan; O. V. Shalaevskii. Admissibility of the estimate of least squares. Unusual property of the normal law. Matematičeskie zametki, Tome 6 (1969) no. 1, pp. 81-89. http://geodesic.mathdoc.fr/item/MZM_1969_6_1_a9/