Abstract
For the characteristic values T1 of the matrix V:=Diag(p)-ppT with p=(p1,...,pk), p1≥p2≥...≥pk≥pk+1>0 and p1+p2+...+pk+pk+1=1 the inequalities p1≥τ1≥p2≥τ2≥...≥pk≥τk>0 are given by RONNING (1982). These inequalities give, if p and pk+1 are unknown, the upper bound 1≥T1. However, in this note the bound 1/2≥T1 is derived. V is proportional to the covariance matrix for multinomial, Dirichlet and multivariate hypergeometric distributions. A statistical application for the multinomial distribution is given.
Similar content being viewed by others
References
BASILEVSKY A (1983) Applied Matrix Algebra in the Statistical Sciences, North-Holland: New York
BERGMANN R, FRITSCHE B, RIEDEL M (1984) Determination of sample sizes in point estimation. Mathematische Operationsforschung und Statistik. Ser. Statistics 15: 73–89
FARNELL A B (1944) Limits for the characteristic roots of a matrix. Bull. Am. Math. Soc. 50: 789–794
HUSCHENS S (1990) Necessary sample sizes for categorial data. Statistische Hefte 31: 47–53
RONING G (1982) Characteristic values and triangular factorization of the covariance matrix for multinomial, Dirichlet and multivariate hypergeometric distributions, and some related results. Statistische Hefte 23: 152–176
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Huschens, S. On upper bounds for the characteristic values of the covariance matrix for multinomial, dirichlet and multivariate hypergeometric distributions. Statistical Papers 31, 155–159 (1990). https://doi.org/10.1007/BF02924685
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02924685