This article is inspired by the second experiment executed by Mendel on three joint characters (shape, color, seed-coat). Through various experiments he managed to isolate plants which differed by more than one character and noted that they were transmitted indipendently from one another, following a relationship 1:2:1 (dominant: hybrid: recessive). Such relationship togheter with the hypothesis of indipendence, to be verified on the basis of empirical data, represent the basis for estimating the theoretical frequencies. Among the various indeces which may be used to describe the difference between theoretical and observed frequencies, we have chosen G2, which was calculated for each of the nine tables conditioned to the three modalities of every character. The partition by addition of G2 allows the definition of three hypotheses on the characters and a total hypothesis. The latter, defined by the intersection of its components, would seem to be the less supported. We defined as anomalous the situation in which, for a special table the total hypothesis results more acceptable than that of one of the components. We have applied a simulation procedure to 100, 000 tables 3x3x3 constructed with the probability relationships theorized by Mendel. The most interesting result is that anomalies are very frequent, as they regard more than 96% of the examined tables.