ndividual, as the unit. Since we are forced into
extensive use of this formula by our present and temporary ignorance
of the applicability of Mendel's rule we must get a clear notion of
how the statistical method is applied in this matter.

The method is the same as that employed by the statistician in
measuring the relatedness of any two series of varying phenomena. If
two quantities or characteristics are so related that fluctuations in
the one are accompanied in a regular manner by fluctuations in the
other, the two quantities or characters are said to be correlated. For
instance, the temperature and the rate of growth of sprouting beans
are related in such a way that increase in the former is accompanied
in a regular way by increase in the latter; or the width and height of
the head, or the total stature and the length of the femur similarly
vary regularly together so that they are said to be correlated to a
certain extent which can be measured. This correlation may result from
the fact that one condition is a cause, either direct or indirect, of
the other; or there may be no such causal relation between the two
phenomena, both resulting more or less independently from a common
antecedent condition or cause.

This phenomenon of correlation is not limited among organisms to the
comparison of two or more different characters in a single series of
individuals; it is applicable also to the comparison of two series of
individuals with respect to the same characteristic. Thus we may
compare the stature of a series of fathers with the same measurement
in their sons. It is this form of correlation with which we are
particularly to deal here. While it is not necessary to understand
just how this subject is dealt with by the statistician we should know
one or two of the elementary principles involved, in order to
appreciate the statistical form of many statements about heredity.

The stature of men may be said to vary usually between limits of 62
and 76 inches, the average height being about 69 inches. In the
complete absence of heredity in stature we should find that fathers of
any given height, say 62 or 63 or 76 inches would have sons of no
particular height but of all heights with an average of 69 inches, the
same as in the whole group. Or if stature were completely heritable
from one generation to the next the _total generations being the units
compared_, then 62 or 63 or 76 inch fathers would have respectively
sons a