Hello Sacha,

Assuming that you're confident that the DVs are metric (interval strength), then your best bet is to use bootstrap/resampling option for analysis in SPSS. SPSS at present has no genuine, nonparametric alternative to mancova.

There are multivariate tests for ordinal data, however. Here's a couple of resources you may find helpful:

1. https://www.tandfonline.com/doi/abs/10.1080/01621459.1997.10473680

2. https://www.jstor.org/stable/23238594?seq=1

3.

Chapter Multivariate Median and Rank Sum Tests

4. Sheu, C-F. & O'Curry, S. (1996).

Implementation of nonparametric multivariate statistics with S.

Behavior Research Methods, Instruments & Computers, 28(2), 315-318

Good luck with your work.

If you are concerned about outliers in continuous data. There are approaches developed in Robust Statistics by Rand R. Wilcox. The easiest place to find them is by looking in the z-library. Best wishes, David Booth

Thanks David Morse and David Eugene Booth