An admissibility condition of the least square estimator within the class of polynomial estimators
Teoriâ veroâtnostej i ee primeneniâ, Tome 23 (1978) no. 1, pp. 210-215
Voir la notice de l'article provenant de la source Math-Net.Ru
It is proved that, in the standard scheme (1.1) of linear regression, the admissibility of the least square estimator within the class of the polynomial equivariant estimators (4) is equivalent to the coincidence of $k+1$ first moments of the errors $\varepsilon_i$ with the corresponding moments of a normal distribution.
@article{TVP_1978_23_1_a22,
author = {A. V. Kakosyan},
title = {An admissibility condition of the least square estimator within the class of polynomial estimators},
journal = {Teori\^a vero\^atnostej i ee primeneni\^a},
pages = {210--215},
publisher = {mathdoc},
volume = {23},
number = {1},
year = {1978},
language = {ru},
url = {http://geodesic.mathdoc.fr/item/TVP_1978_23_1_a22/}
}
TY - JOUR AU - A. V. Kakosyan TI - An admissibility condition of the least square estimator within the class of polynomial estimators JO - Teoriâ veroâtnostej i ee primeneniâ PY - 1978 SP - 210 EP - 215 VL - 23 IS - 1 PB - mathdoc UR - http://geodesic.mathdoc.fr/item/TVP_1978_23_1_a22/ LA - ru ID - TVP_1978_23_1_a22 ER -
A. V. Kakosyan. An admissibility condition of the least square estimator within the class of polynomial estimators. Teoriâ veroâtnostej i ee primeneniâ, Tome 23 (1978) no. 1, pp. 210-215. http://geodesic.mathdoc.fr/item/TVP_1978_23_1_a22/