The suggestion amounts to this: that because there are exceptions to dominance in peas; and because by some stupendous coincidence, or still more amazing incompetence, a bungler might have thought he found dominance of one eye-colour whereas really there was none[154]; therefore Professor Weldon is at liberty to suggest there is a fair chance that Mendel and all who have followed him have either been the victims of this preposterous coincidence not once, but again and again; or else persisted in the same egregious and perfectly gratuitous blunder. Professor Weldon is skilled in the Calculus of Chance: will he compute the probabilities in favour of his hypothesis? [154] I have no doubt there is no universal dominance in eye-colour. Is it _quite_ certain there is no dominance at all? I have searched the works of Galton and Pearson relating to this subject without finding a clear proof. If there is in them material for this decision may perhaps be pardoned for failing to discover it, since the tabulations are not prepared with this point in view. Reference to the original records would soon clear up the point. _Ancestry and purity of germ-cells._ To what extent ancestry is likely to elucidate dominance we have now seen. We will briefly consider how laws derived from ancestry stand in regard to segregation of characters among the gametes. For Professor Weldon suggests that his view of ancestry will explain the facts not only in regard to dominance and its fluctuations but in regard to the purity of the germ-cells. He does not apply this suggestion in detail, for its error would be immediately exposed. In every strictly Mendelian case the _ancestry_ of the pure extracted recessives or dominants, arising from the breeding of first crosses, is identical with that of the impure dominants [or impure recessives in cases where they exist]. Yet the posterity of each is wholly different. The pure extracted forms, in these simplest cases, are no more likely to produce the form with which they have been crossed than was their pure grandparent; while the impure forms break up again into both grand-parental forms. Ancestry does not touch these facts in the least. They and others like them have been a stumbling-block to all naturalists. Of such paradoxical phenomena Mendel now gives us the complete and final account. Will Professor Weldon indicate how he proposes to regard them? * * * * * Let me here call the reader’s particular attention to that section of Mendel’s experiments to which Professor Weldon does not so much as allude. Not only did Mendel study the results of allowing his cross-breds (_DR_’s) to fertilise themselves, giving the memorable ratio 1 _DD_ : 2 _DR_ : 1 _RR_, but he fertilised those cross-breds (_DR_’s) both with the pure dominant (_D_) and with the pure recessive (_R_) varieties reciprocally, obtaining in the former case the ratio 1 _DD_ : 1 _DR_ and in the latter the ratio