A class of nonparametric procedures in one-factor experiments



Journal Title

Journal ISSN

Volume Title


Texas Tech University


This thesis analyzes and develops an algorithm for the adaptive distribution-free procedure for testing ordered alternatives and multiple comparisons. in one-way analysis of variance, including treatment of ties and demonstrates the supremacy of these procedures over typical parametric procedures based on sample means and the well-known Wilcoxon nonparametric procedure based on ranks.

Initial data classifies the underlying distribution by tail-weight and amount of skewness. The preliminary classification determines the tailoring of specific scores from where all the inferences are based. The adaptive procedure performs well for a wide range of distributions rather than performing with optimal properties for any of the particular distributions.

The preliminary selection of an adaptive procedure should affect characteristics of the final inference. Testing a null hypothesis at a nominal significance level of a after selecting a model wiU frequently result in an overall significance level much greater than a. The model should be selected by determining which corresponding test will produce the largest observed significance level.



Distribution, Mathematical optimization, Nonparametric statistics