Vera Hofer asks: " Dear colleagues, has anyone an idea how to carry out a nonparametric manova for comparing 3 groups? Thank you for your help. Vera" One approach would be to carry out a permutation test, randomly reassigning the vector observations among groups under the null hypothesis that the three multivariate distributions sampled are identical. The 'work' could be carried out using the boot function (in package boot) but would require writing a not very involved function to compute the manova test statistic. ********************************************************** Cliff Lunneborg, Professor Emeritus, Statistics & Psychology, University of Washington, Seattle cliff at ms.washington.edu