Permutation methods. A distance function approach (Q5943007)

This monograph presents a fresh approach to statistical ideas based on permutation procedures. The focus is not on elaborating a mathematical theory in a theorem - proof framework. Rather it is the authors' goal to give an overview how permutation methodology may be applied to quite different statistical questions. Most of the issues are illustrated by real data examples. Computer programs are available at the authors' web site. The monograph consists of eight chapters. After a brief introduction, in chapter two multiresponse permutation procedures are introduced as a generalization of one-way analysis of variance. These statistics are weighted sums of quantities which, for a given permutation, measure the homogeneity of a group through a given distance function. \(P\)-values are computed by counting, resampling or fitting a parametric distribution via moments. The choice of a distance function as to robustness properties of the tests is discussed through data examples. In chapter three permutation methods are applied to multivariate autoregressive pattern detection, asymmetric two-way contingency table analysis, runs tests and rank order statistics. Chapter 4 is on multivariate randomized block permutation procedures, while chapter five discusses permutation based methods for regression analysis and prediction. Finally, chapters 6-8 deal with goodness-of-fit techniques, contingency tables and tests for homogeneity, respectively. The monograph is recommended for a special course or seminar on applied statistics. The text can be understood without deep measure-theoretic background.