Publication Date

1981

Document Type

Dissertation/Thesis

First Advisor

Laud, Purushottam, 1948-

Degree Name

M.S. (Master of Science)

Legacy Department

Department of Mathematical Sciences

LCSH

Statistics; Scale analysis (Psychology)

Abstract

In this thesis several two-sample and multisample nonparametric tests £or scale with both known and unknown location parameters are reviewed. A nonparametric multiple comparison test for differences in location is also studied. A new nonparametric multiple comparison test for differences in scale parameters is suggested. Its small sample and asymptotic properties are investigated. The test suggested is a modification of a nonparametric multiple comparison test for differences in location. The test is distribution- free and has reasonable power for small samples. The asymptotic distribution of the test statistic is that of the minimum of the components of a multivariate normal vector. Modifications of the test when the location parameters are unknown and unequal are suggested. This modified test is not asymptotically distribution-free for all underlying location-scale parameter families. However, we give sufficient conditions on the families under which the test is asymptotically distribution-free.

Comments

Includes bibliographical references.

Extent

57 pages

Language

eng

Publisher

Northern Illinois University

Rights Statement

In Copyright

Rights Statement 2

NIU theses are protected by copyright. They may be viewed from Huskie Commons for any purpose, but reproduction or distribution in any format is prohibited without the written permission of the authors.

Media Type

Text

Download

Share

COinS