Accession Number : AD0679203

Title :   BAYESIAN ESTIMATION OF LATENT ROOTS AND VECTORS, WITH SPECIAL REFERENCE TO THE BIVARIATE NORMAL DISTRIBUTION.

Descriptive Note : Final technical rept. Sep 67-Apr 68,

Corporate Author : WISCONSIN UNIV MADISON DEPT OF STATISTICS

Personal Author(s) : Tiao,George C. ; Fienberg,Stephen

Report Date : MAY 1968

Pagination or Media Count : 28

Abstract : The paper discusses some aspects of the estimation of latent roots and vectors of the covariance matrix of the bivariate normal distribution from a Bayesian viewpoint. The joint distribution of (1) the angle of the canonical transformation and (2) the ratio of the larger root to the total variance is considered in detail and illustrated by an example. Also discussed is the problem of making inferences about the larger roots, and several simple approximations to its distribution are considered. Finally a generalization of one of the approximation methods to latent roots of higher dimensional convariance matrix is given. (Author)

Descriptors :   (*DISTRIBUTION THEORY, *ANALYSIS OF VARIANCE), STATISTICAL DISTRIBUTIONS, MATRICES(MATHEMATICS), DECISION THEORY, APPROXIMATION(MATHEMATICS), SAMPLING

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE