Asymptotic distribution of the reduced rank regression estimator under general conditions
Anderson, T. W.
Ann. Statist., Tome 27 (1999) no. 4, p. 1141-1154 / Harvested from Project Euclid
In the regression model $\mathbf{Y} = \eta + \mathbf{BX} + \mathbf{Z}$ with $\mathbf{Z}$ unobserved, $\mathscr{E}\mathbf{Z} = \mathbf{0}$ and $\mathscr{E}\mathbf{ZZ}' = \mathbf{\Sigma}_{ZZ}$, the least squares estimator of $\mathbf{B}$ is $\hat{\mathbf{B}} = \mathbf{S}_{YX}\mathbf{S}_{XX}^{-1}$. If the rank of $\mathbf{B}$ is known to be $k$ less than the dimensions of $\mathbf{Y}$ and $\mathbf{X}$, the reduced rank regression estimator of $\mathbf{B}$, say $\mathbf{B}_k$, depends on the first $k$ canonical variates of $\mathbf{Y}$ and $\mathbf{X}$. The asymptotic distribution of $\hat{\mathbf{B}}_k$ is obtained and compared with the asymptotic distribution of $\hat{\mathbf{B}}$. The advantage of $\hat{\mathbf{B}}_k$ is characterized.
Publié le : 1999-08-14
Classification:  Canonical variates,  reduced rank regression,  maximum likelihood estimators,  62H10,  62E20,  62H12
@article{1017938918,
     author = {Anderson, T. W.},
     title = {Asymptotic distribution of the reduced rank regression estimator
			 under general conditions},
     journal = {Ann. Statist.},
     volume = {27},
     number = {4},
     year = {1999},
     pages = { 1141-1154},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1017938918}
}
Anderson, T. W. Asymptotic distribution of the reduced rank regression estimator
			 under general conditions. Ann. Statist., Tome 27 (1999) no. 4, pp.  1141-1154. http://gdmltest.u-ga.fr/item/1017938918/