Invariant Tests on Covariance Matrices
Marden, John I.
Ann. Statist., Tome 9 (1981) no. 1, p. 1258-1266 / Harvested from Project Euclid
Minimal complete classes of invariant tests are presented for modifications of the problem of testing the independence of $Y$ and $X$, where $(Y, X) \equiv (Y, X_1, \cdots, X_p)$ is a multivariate normal random vector. One modification involves having extra independent observations on $Y$. Others involve extra variates $Z \equiv (Z_1, \cdots, Z_q)$ such that $(Y,X,Z)$ is multivariate normal. Among other results, locally most powerful invariant tests and asymptotically most powerful invariant tests are found; it is shown that for some problems the likelihood ratio test is admissible among invariant tests only for levels less than a specified one; and it is shown that for the problem of testing the independence of $Y$ and $X$ when it is known that $Y$ and $Z$ are independent, the test based on the sample multiple correlation coefficient of $Y$ and $(X, Z)$ is inadmissible.
Publié le : 1981-11-14
Classification:  Multivariate normal distribution,  invariant tests,  multiple correlation coefficient,  complete class,  admissible tests,  likelihood ratio tests,  62C07,  62C10,  62C15,  62H15,  62H20
@article{1176345642,
     author = {Marden, John I.},
     title = {Invariant Tests on Covariance Matrices},
     journal = {Ann. Statist.},
     volume = {9},
     number = {1},
     year = {1981},
     pages = { 1258-1266},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176345642}
}
Marden, John I. Invariant Tests on Covariance Matrices. Ann. Statist., Tome 9 (1981) no. 1, pp.  1258-1266. http://gdmltest.u-ga.fr/item/1176345642/