APRIL 26, 1901.] 
$10,000 has enabled the Academy this last year 
to bring out Volume VII., containing 316 pages 
and seventeen full-page plates. 
PROPOSED JOURNAL FOR THE STATISTICAL 
STUDY OF BIOLOGICAL PROBLEMS. 
It is proposed to established a Journal of 
Biological Statistics which may serve as a means 
not only of collecting under one title biological 
data of a kind not systematically collected or 
publisHed in any other periodical, but also of 
spreading a knowledge of such statistical theory 
as may be requisite for their scientific treatment. 
The following remarks are offered in justifica- 
tion of this proposal : 
A very few years ago, all those problems 
which depend for their solution on a study of 
the differences between individual members of 
a race or species were neglected by most biolo- 
gists. The complexity of organic structure is 
so great, and the number of distinguishable 
forms so enormous, that morphologists were 
obliged to simplify their conceptions by con- 
structing for every species an ideal type, to 
which the individuals composing it conform 
with more or less exactness, and to neglect 
those deviations from the type which actually 
occur. Such simplificatian was not only justi- 
fiable, but absolutely necessary for many pur- 
poses; it has rendered enormous service to 
biology in the past, it does so still and will 
continue to do so; nevertheless, there are 
many problems which can not be dealt with by 
its aid. 
The starting point of Darwin’s theory of evo- 
lution is precisely the existence of those differ- 
ences between individual members of a race or 
species which morphologists for the most part 
rightly neglect. The first condition necessary, in 
order that any process of natural selection may 
occur among a race or species, is the existence 
of differences among its members ; and the first 
step in an enquiry into the possible effect of a 
selective process upon any character of a race 
must be an estimate of the frequency with which 
individuals, exhibiting any degree of abnor- 
mality in respect to that character, occur. The 
unit, with which such an enquiry must deal, is 
not an individual but a race, or a statistically 
respresentative sample of a race ; the result must 
SCIENCE. 
67 
take the form of a numerical statement, show- 
ing the relative frequency with which the 
various kinds of individuals composing the race 
occur. 
As it is with the fundamental phenomenon of 
variation, so it is with heredity and with selec- 
tion. The statements that certain characters 
are selectively eliminated from a race can only 
be demonstrated by showing statistically that 
the individuals which exhibit that character die 
earlier, or produce fewer offspring, than their 
fellows: while the phenomena of inheritance 
are only by slow degrees being rendered cap- 
able. of expression in an intelligible form as 
numerical statements of the relation between 
parent and offspring, based upon statistical ex- 
amination of large series of cases, are gradually 
accumulated. 
These, and many other problems, involve the 
collection of statistical data on a large scale. 
That such data may be rendered intelligible to 
the mind, it is necessary to find some way of 
expressing them by a formula, the meaning of 
which can be readily understood, while its sim- 
plicity makes it easy to remember. The recent 
development of statistical theory, dealing with 
biological data on the lines suggested by Mr. 
Francis Galton, has rendered it possible to deal 
with statistical data of very various kinds ina 
simple and intelligible way, and the results 
already achieved permit the hope that simple 
formule, capable of still wider application, may 
soon be found. 
The number of biologists interested in these 
questions, and willing to undertake laborious 
statistical enquiries, is already considerable, and 
is increasing. It seems, therefore, that a useful 
purpose would be served by a journal especially 
devoted to the publication of statistical data, 
and of papers dealing with statistical theory. 
Many persons are deterred from the collection 
of such data, by the difficulty of finding such 
a means of publishing their results as this jour- 
nal would afford, and those results which are 
published frequently lose much of their value 
because the data on which they are based are 
withheld, or because they are isolated in publi- 
cations largely devoted to other forms of in- 
vestigation. 
Itis suggested that ‘ Biometrika, a Journal for 
