Accession Number : AD0676727

Title :   NONPARAMETRIC CONFIDENCE REGIONS FOR SOME MULTIVARIATE LOCATION PROBLEMS.

Descriptive Note : Technical rept.,

Corporate Author : NEW YORK UNIV N Y COURANT INST OF MATHEMATICAL SCIENCES

Personal Author(s) : Puri,Madan Lal ; Sen,Pranab Kumar

Report Date : JUN 1968

Pagination or Media Count : 16

Abstract : Nonparametric methods of constructing confidence regions for the location vectors in the multivariate one-sample and two-sample problems are provided. These methods are based on a class of rank order statistics. Specifically, nonparametric confidence regions based on Bonferroni inequality, the maximum modulus, and Scheffe's method are studied. The results obtained are nonparametric generalizations of some of the results of Dunn and Sidak. Certain optimality properties of the proposed methods are also established. (Author)

Descriptors :   (*CONFIDENCE LIMITS, *MULTIVARIATE ANALYSIS), STATISTICAL DISTRIBUTIONS, STATISTICAL TESTS, OPTIMIZATION, SAMPLING, INEQUALITIES

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE