The Non-Singularity of Generalized Sample Covariance Matrices
Eaton, Morris L. ; Perlman, Michael D.
Ann. Statist., Tome 1 (1973) no. 2, p. 710-717 / Harvested from Project Euclid
Let $X = (X_1, \cdots, X_n)$ where the $X_i: p \times 1$ are independent random vectors, and let $A: n \times n$ be positive semi-definite symmetric. This paper establishes necessary and sufficient conditions that the random matrix $XAX'$ be positive definite w.p.1. The results are applied to cases where $A$ has a particular form or $X_1, \cdots, X_n$ are i.i.d. In particular, it is shown that in the i.i.d. case, the sample covariance matrix $\sigma(X_i - \bar{X})(X_i - \bar{X})'$ is positive definite w.p. 1 $\operatorname{iff} P\lbrack X_1 \in F\rbrack = 0$ for every proper flat $F \subset R^p$.
Publié le : 1973-07-14
Classification:  Independent random vectors,  nonsingularity of random matrices,  sample covariance matrix,  linear manifolds,  flats,  62H10,  60D05,  15A03
@article{1176342465,
     author = {Eaton, Morris L. and Perlman, Michael D.},
     title = {The Non-Singularity of Generalized Sample Covariance Matrices},
     journal = {Ann. Statist.},
     volume = {1},
     number = {2},
     year = {1973},
     pages = { 710-717},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176342465}
}
Eaton, Morris L.; Perlman, Michael D. The Non-Singularity of Generalized Sample Covariance Matrices. Ann. Statist., Tome 1 (1973) no. 2, pp.  710-717. http://gdmltest.u-ga.fr/item/1176342465/