In many biomedical studies researchers and practitioners are often faced with comparisons between two or more groups using classical parametric methods, such as t test, F test or Chi-square test, although real problems rarely agree with the stringent assumptions required by such methods. When such biomedical studies are multivariate in nature, i.e., they are involved with a set of response variables as it is the case for the majority of the real case studies, the NonParametric Combination (NPC) of Dependent Permutation Test methodology (Pesarin [8]) frees the researcher from stringent assumptions of parametric methods and allows a more flexible analysis both in terms of specification of multivariate hypotheses and in terms of the nature of the variables involved in the analysis. In fact the NPC method can easily takes into account for any type of response variable: numeric, ordered and nominal categorical as well. In this paper we give a short outline of the implementation of NPC methodology and we illustrate its usefulness with an application to a real case study connected with the characterization of which factors are more correlated to the malignity of the ovarian tumour mass. Such observational study has been developed at the Department of Obstetrics and Gynaecology of the Padova University Hospital. We believe that in many biomedical experimental and observational studies the NPC method may offer a significant contribution for a robust statistical analysis.

nonparametric combination, ovarian tumour mass malignity.