The correlation and grouping of mineral waters from different regions of Sao Paulo state was carried out using exploratory analysis of pH values and Ba, Ca, K, Mg, Na and V contents. By using principal components analysis (PCA) and hierarchical cluster analysis (HCA) was possible to evaluate the similarity of mineral water samples through group formation that was directly correlated with their sources. Employing scores, loadings and dendogram graphics was possible to observe the formation of two groups and the separation of Ibira and Itu mineral water samples. The first group is composed by samples from Serra da Mantiqueira region (Aguas da Prata, Campos do Jordao and Lindoia) and the other one is formed by samples from cities located above the Guarani Aquifer (Aguas de Santa Barbara, Palmares Paulista, Presidente Prudente, Sao Carlos, Sao Simao e Santa Rosa do Viterbo). The segregation of Ibira samples was due to predominant presence of Na and V in their mineral composition, while for Itu samples it was observed higher contribution of Ba, Ca and Mg elements. The application of exploratory analysis enabled to correlate the chemical composition with the geographical source of the mineral water samples producing useful results for establishing of classification and prevision, models.27SI91102