A new derivation of eigenvalue inequalities for the multinomial distribution

Jacques Bénasséni (1)

1 IRMAR - Institut de Recherche Mathématique de Rennes

We consider the covariance matrix of the multinomial distribution. We suggest a new derivation of inequalites for the eigenvalues of this matrix using a classical result on the product of two positive semi-definite matrices.

Mots clés: covariance matrix; eigenvalue; inequalities; multinomial distribution

Domaines: Statistiques [math.ST]; Théorie [stat.TH]

Jacques Bénasséni. A new derivation of eigenvalue inequalities for the multinomial distribution. Journal of Mathematical Analysis and Applications, 2012, 393 (2), pp.697-698. ⟨10.1016/j.jmaa.2012.03.029⟩. ⟨hal-00715173⟩