Files in this item
|(no description provided)|
|Title:||The use of rank tests in analysis of variance|
|Author(s):||Muyot, Maria Emerita Carmen Tiongson|
|Doctoral Committee Chair(s):||Marden, John I.|
|Department / Program:||Statistics|
|Degree Granting Institution:||University of Illinois at Urbana-Champaign|
|Abstract:||Several nonparametric tests based on ranks have been proposed to handle analysis of variance problems. But questions have been raised about the appropriateness of some procedures that are mere rank transformations of normal theory analysis of variance tests.
An alternative method using the concept of "orthogonal contrasts" is developed and applied to one- and higher-way analysis of variance problems. Tests for main effects as well as interactions are discussed and compared with the classical F-test and other nonparametric rank tests by means of Monte Carlo simulations on Type I error rates and power for different alternatives.
|Rights Information:||Copyright 1993 Muyot, Maria Emerita Carmen Tiongson|
|Date Available in IDEALS:||2011-05-07|
|Identifier in Online Catalog:||AAI9411728|