An analytical problem, which arises in the statistical problem of comparing the means of two normal distributions, the variances of which -as well as their ratio- are unknown, is well known in the mathematical statistics as the Behrens-Fisher problem. One generalization of the Behrens-Fisher problem and different aspect concerning the estimation of the common mean of several independent normal distributions with different variances are considered and one solution is proposed.
@article{urn:eudml:doc:40236,
title = {On the problem of the means of weighted normal populations.},
journal = {Q\"uestii\'o},
volume = {19},
year = {1995},
pages = {93-106},
mrnumber = {MR1376779},
language = {en},
url = {http://dml.mathdoc.fr/item/urn:eudml:doc:40236}
}
Nikulin, Mikhail S.; Voinov, Vassiliy G. On the problem of the means of weighted normal populations.. Qüestiió, Tome 19 (1995) pp. 93-106. http://gdmltest.u-ga.fr/item/urn:eudml:doc:40236/