236 G. Udny Yule 
x \ + *'o> x\ -f x 2 » + *\ 2 , the mean of which is precisely f 
(x x + x \ + x -j + x 'o) i>e. the mean of the two parent forms. 
If dominance still hold good the result is not quite so obvious, but 
it seems correct to state that so long as the greater and the lesser 
values of the pairs like x x x\ are the dominants with about equal 
frequency, the inheritance will be blended, while otherwise blends 
will only occur in a proportion of the results. 
This possible mode of the occurrence of blending was noted long 
ago by Mr. Galton. He found that the. inheritance of stature was 
strictly blended, as tested by the fact that the offspring of a tall mother 
with a short father, or vice versa , shewed no more divergence inter se 
than the offspring of two mediocre parents. The inheritance of eye- 
colour on the other hand he found to be exclusive , the offspring generally 
resembling the one parent or the other, and intermediate tints being 
rare. “The blending in Stature,” he remarks ( 2 , p. 139) “is due 
to its being the aggregate of the quasi-independent inheritances of 
many separate parts, while Eye-colour appears to be much less 
various in its origin.” Blending then must occur with compound 
characters, it may occur for all we know in some cases of unit 
characters. It would be easier to gauge the probabilities, if 
Mendel’s followers had made some experiments with a view to 
elucidating the nature of “exclusive ” inheritance in general, and of 
the very curious phenomenon of “dominance” in particular. 
1 must apologise for the length to which these remarks have 
extended, but the subject is a large one, and even as it is I have 
been compelled to pass over many subsidiary points. It is, how ever, 
essential, if progress is to be made, that biologists—statistical or 
otherwise—should recognise that Mendel’s Laws and the Law' 
of Ancestral Heredity are not necessarily contradictory statements, 
one or other of which must be mythical in character, but are 
perfectly consistent the one with the other and may quite w’ell form 
parts of one homogeneous theory of heredity. To make my own 
position clear, let me repeat with regret, that I cannot include under 
the same heading the special law s as to the operation of Ancestral 
Heredity which were formulated by Galton and Pearson. These 
law’s have, beyond question, been of service in suggesting lines of 
research and possible methods of study, but the fixity of the 
numerical constants involved, which they imply, has not stood the 
test of time. Selective mating, natural selection, reproductive 
selection, the effect of circumstance, had all in turn to be recognised 
