zbMATH — the first resource for mathematics

Multivariate rank tests. (English) Zbl 0946.62060
Ghosh, Subir (ed.), Multivariate analysis, design of experiments, and survey sampling. A tribute to Jagdish N. Srivastava. New York, NY: Marcel Dekker. Stat., Textb. Monogr. 159, 401-431 (1999).
Fom the introduction: Rank-based nonparametric procedures have served statisticians well, providing easy-to-use, intuitive, efficient, and robust alternatives to the common normal theory procedures. The original rank procedures were univariate. Multivariate procedures, in which each variable is ranked separately, immediately affords practitioners many of the benefits of the univariate procedures in more complicated situations. In recent years, there has been development of other methods of multivariate ranking that use the variables together rather than separately. This paper shows how to use particular definitions of multivariate sign and rank to generate a multitude of multivariate procedures that not only mimic the popular univariate ones, but go beyond to treat genuinely multivariate problems.
For the entire collection see [Zbl 0927.00053].

62H15 Hypothesis testing in multivariate analysis
62G10 Nonparametric hypothesis testing
PDF BibTeX Cite