A COMPUTER PACKAGE FOR THE MULTIVARIATE NONPARAMETRIC RANK TEST IN COMPLETELY RANDOMIZED EXPERIMENTAL-DESIGNS

When research data are measured on at least an ordinal scale and the a ssumptions required in the theory underlying parametric statistical me thods are in question, nonparametric procedures based on the ranks pro vide a sound approach to statistical analysis. Biomedical investigatio ns, especially clinical trials, typically involve multivariate respons e and therefore multivariate statistical methods are called for in the interpretation of results. We discuss applications of the nonparametr ic multivariate rank test for completely randomized designs. Large sam ple theory can be used to support these statistical methods for assess ing group differences in location. In small samples, randomization tes ts provide a basis for inferences. The execution of the procedure is f acilitated by a computer program developed by the authors.