]\gt ; 1888 .
] Co-relations and their .
185 Observations , \amp ; c. ( continued ) .
Order .
1884 . .
London 1888 ; DailyWeather Reports .
1888 .
January to June . .
London .
Nautical Almanac Office .
The Nautical Almanac for 1892 . .
London 1888 .
The Office .
Madrid :Observatorio .
Observaciones Meteorologicas .
1883-85 . .
Madrid 1887-88 .
The December 20 , 1888 .
Professor G. G. STOKES , D.C.L. , President , in the Chair .
The Presents received were laid on the table , and thanks ordered for them .
The following Papers were read:\mdash ; I. " " Co-relations and their Measm.ement , chiefly from Anthropometric Data By FRANCIS GALTON , F.R.S. Received Dccember 5 , 1888 .
" " elation or correlation of structure\ldquo ; is a phrase much used in biology , and not loast in that branch of it which refers to heredity , and idea is even more frequently present than the phrase ; but I am not aware of any previous attempt to define it clearly , to trace its mode of actiou in detail , ' to show how to measure its degree .
Two variable organs are said to be co-related when the variation of the one is accompanied on the average by more or less variation of the other , and in the same direction .
Thus the length of the arm is said to be -related with that of the leg , because a person with a long arm has usually a long leg , and conversely .
If the -relation be close , then a person with a very long arm would usually have a very long leg ; if it be moderately close , then the length of his leg would usually be only long , not very long ; and if there were no -relation at all then the length of his leg would on the average be mediocre .
It is easy to see that co-relation must be the consequence of the variations of the two organs being partly dne to common causes .
If they lvere wholly due to common causes , the co-relation would be perfect , as is approximately the case with the symmetrically disposed parts of the body .
If they were in no respect due to common causes , the -relation would be nil .
Between these two extremes an endless number of intermediate cases , and it will be shown how the by a simple nunlber .
To avoid the possibility of misconception , it is well to point out that the subject in hand has nothing whatever to do with the average proportions between the various limbs , in different races , which have beeIl often discussed from early times up to the present day , both by artists and by anthropologists .
The fact that the average ratio between the stature and the cubit is as 100 to 37 , or thereabouts , does not give the slightest information about the nearness with which they vary together .
It wollld be an alliogether erroneous inference suppose their average proportion to be maintained so that when the cubit was , say , one-twentieth longer than the average cubit , the stature might be expected to be one-twentieth greater than the average stature , and conversely .
Such a supposition is easily shown to be contradicted both by and theory .
The relation between the cubit and the stature will be shown to be such that for every inch , centimetre , or other mnit of absolute length that the cubit deviates from the mean length of cubis , the stature will on the a deviate from the mean length of statures to the amount of units , and iu the same direction .
Conversely , for each unit of deviation of stature , the average deviation of the ) will be nnit .
These relations are not numerically reciprocal , but the exactness of the -relation becomes established when we have transmuted the inches or other of the cubit and of the stature into units dependent on their respective scales of variability .
We thus cause a long cubit and an equally long stature , as to the general run of cubits and statures , to be designated by an identical scale-value .
The cular unit that I shall employ is the value of the probable error of any single measure in its own group .
In that of the cubit , the probable error is inch cm .
; in the stature it is inch cm .
Therefore the measured lengtbs of the cubit in inches will be transmuted into terms of a new scale , in which each unit inch , and the measured lengths of the stature will be transmuted into terms of another new scale in which each unit is inch .
After this has been done , we shall find the deviation of the cubit as compared to the mean of the esponding deviations of the stature , to be as 1 to .
Conversely , the deviation of the stature as compared to the mean of the corresponding deviation8 of the cubit will also be as 1 to .
Thus the existence of the -relation is established , and it measure is found to be Now as to the evidence of all this .
The data were obtained at my anthropometric laboratory at South Kensington .
They are of 350 males of 21 years and upwards , but as a large proportion of them were students , and barely 21 years of age , they were not wholly fullgrown ; but neither fact nor the small number of observations 1888 .
] Co-relations and their .
137 reiudicial to the conclusious that will be reached .
They measured in various ways , partly for the purpose of this lnqulry .
lt will be sufficient to give some of them as examples .
The exact number of 350 is llot preserved throughout , as injury to some limb or othel reduced the available number by 1 , 2 , in diffel.ent cases .
After the measures of each limb in the order of their magnltudes , I noted the measures in each sel.ies that occupied respcctively the positions of the first , second , and third quarterly divisions .
Calling these measures in any one series , , and , I take , which is the median or middlemost value , as that hence the deviations are to be measured , and , as the probable error of any single measul'e in the series .
This is practically the same as saying that one-half of the deviations fall within the distance of from the mean value , because the series run with fair symmetry .
In this way I obtained the Collowing values of and , in which the second decimal must be taken as only approximate .
The and of any particulax series may be identified by a suffix , thus stand for those of the cubit , and for those of the Table I. NoTn.lead length is its maximum length measured from the notch betwcen and just below the eyebrows .
The cubit is measured with the prone und without taking otf the coat ; it is the distan between the elbow of bent left arm nnd the tip of the middle finger .
The height of the kncc is taken itting when the knec is bent at right angles , less the measured thickuess of the heel of boot .
ables were then constructed , each referring to a different pair of the above elements , like Tables II and , which suffice as examples of the whole of them .
It will be understood that the value is a universal unit applicable to the most varied measurements , such as breathing capacity , strength , memol.y , keenness of eyesight , and enables them to be compared together on equal terms notwithstanding their intrinsic diversity .
It does not only refer to measures of extend the limits of Table Tr , as it includes every line and column in my MS .
table that contains not less than twenty entries .
None of the entries lying within the flanking lines and columns of Table II ere used .
II .
The measures were made and recol'ded to the nearest tenth of an inch .
The heading of 70 inches of stature includes all records 1888 .
] Co-relations and their Measurement . .
F. Galton .
) between and inches ; that of 69 includes all between and , and so on .
The values derived from Table II , and from other similar tables , are entered in Table III , where they occupy all the columns up to the three last , the first of which is headed " " smoothed These smoothed values were obtained by plotting the observed values , after transmuting them as above described into their respective units , upon a diagram such as is shown in the figure .
The deviations of the " " subject\ldquo ; are measured parallel to the axis of the figure , and those of the mean of the corresponding values of the " " relative\ldquo ; are measured ] to the axis of .
Whem the ture is taken as the subject , the median positions of the corresponding cubits , which are given in the successive lines of Table III , are marked small circles .
When the cubit is the subject , the mean positions of the corresponding statures marked with crosses .
The firm line in the figure is to represent the general run of the circles and crosses .
It is here seen to be a straight line , and it was found to be straight in every other figure drawn from the ferent pairs of -related variables that I have as yet tried .
But the inclination of the line to the vertical differs considerably in different cases .
In the present one the inclination is such that a deviation of 1 on the part of the subject , whether it be stature or cubit , is accompanied by a mean deviation on the part of the relative , whetber it be cubit or stature , of .
This decimal fraction is consequently measure of the closeness of i , he co-relation .
We easily retransmute it into inches .
If the stature be taken as the subject , then is associated with ; that is , a deviation of inches in the one with of the other .
This is the same as 1 inch of stature being associated with a mean length of cubit equal to inch .
Conversely , if the cubit be taken as the subject , then is associated with ; that is , a deviation of 0.56 inch in the one with of the other .
This is the same as 1 inch of cnbit being associated with a mean length of inches of stature .
If centimetre be read for inch the same holds true .
Six other tables are now given in a summary form , to show how well calculation on the above principle agrees with observation .
1888 .
] Co-relations and their Measurement .
Table No. of ases .
No. of cases .
No. of cases .
.37 Mr. F. Galton .
Table continued .
[ Dec. From Table the deductions given in Table can be made ; but may be made directly from tables of the form of Table III , whence Table was itseIf derived .
When the deviations of the subject and those of the mean of the relatives are severally measured in units of their own , there is always a regression in the value of the latter .
This is Co-relations and their Measurement .
Table analogous to what was observed in , as I showed in my paper read before this Society on " " Hereditary Stature\ldquo ; ( ' Roy .
Soc. Proc. 40 , 1886 , p. .
The statures of kinsmen arc co-related variables ; thus , the of the father is co1Telated to that of the adult son , and the stature of the aduIt son to that of the father ; the ture of the uncle to that of the adult nephew , and the stature of the adult nephcw to that of the uncle , and so on ; but the indcx of co-relation , whioh is what I there called ' ' regl'ession , \ldquo ; is diifercnt in diiferent cases .
In dealing with kinships there is usually no need to reduce the measures to units of , becauss values are alike in all the smen , being of the same value as of the population at large .
It howevcr happened that the very first case analysed was different in this rehpect .
It the relation between the statures of what I called the " " mid-parcnt \ldquo ; and the son .
mid-pnrcnt is all idcal progenitol , whose the avcrage of that of the falher on one halld and of that of the mother on the after her stature had been traYlsmuted into its malc equivalent by the multiplication of the factor of .
The of the mid-parental statures was found to be , that of the population dealt with was .
Again , the mean deviation measured in inches of tho statures of sons was tion of the sons .
Here the regression , when calculated in units , is in the case from to to , and in the second from to I to , which is practicalIy the same .
The ration of all this will be found discussed in the paper on ' ' Hereditary Stature to which reference has already been made , and in the appendix to it by Mr. J. D. Halnilton Dickson .
The entries in any table , sucl ] as Table II , may be looked upon as the values of the vertical ordinates to a surface of frequency , whose mathematical properties were discussed the above-mentioned appendix , there .
fore I need not repeat them here .
But there is always room for legitimate doubt whether conclusions based on the strict properties of the ideal law cf would be sufficiently correct to be serviceable in actual cases of co-relation between variables that conform only approximately to that law .
It is therefore exceedingly desirable to put the theoretical conclusions to frequent test , as has been done with these anthropometric data .
The resuIt is that anthropologists may have much less hesitation than before , in availing themselves of the properties of the law of frequency of error .
I have given in Table a column headed .
The meaning of is explained in the paper on\ldquo ; Hereditary Statul.e.\ldquo ; It is the value of the distribution of any system of values , as \amp ; c. , round the mean of all of them , which we may call X. The knowledge of enables dotted lines to be drawn , as in the figure above , parallel to the line of values , between which one half of the observations , for each value of , will be included .
This value of has much anthropological interest of its own , especially in connexion with M. Bertillon 's system of anthropometric identification , to which I will not call attention now .
It is not necessary to extend the list of examples to show how to measure the degree in which one variable may be -related with the combined effect of other variables , whether these be themselves -related or not .
To do so , we begin by educing each measure into others , each having the of its own system for a unit .
We thus obtain a set of values that can be treated exactly in the same as the meaSUl.es of a single variable were treated in Tables II and onwal'ds .
Neither is it necessary to give examples of a method by which the degree may be ured , in which the variables in a series each member of which is the summed effect of variables , may be modified by their partial -relation .
After transmuting the separa measures as above , and then summing them , we hold find the obat ) error of any one of them to be if the variables were 1888 .
] On the Maximum Discharge a Pipe .
145 perfectly independent , and if they were rigidly and perfectly corelated .
The observed value would be almost always somewhere intermediate between these extremcs , and would give the tiou that is wanted .
To conclude , the prominent characteristics of any two co-related variables , so far at least as I have as yet tested them , are four in number .
It is supposed that their respective measures have been first transmuted into others of which the unit is in each case equaI to the error of a sing-le measure in its own series .
Let deviation of the subject , whichever of the two variables may be taken in that capacity ; and let , \amp ; c. , be the corresponding deviations of the relative , and Jet the mean of these be X. Then we find : ( 1 ) that for all of ; ( 2 ) that is the , whichever of the two val'iabl es is taken for the subject ; ( 3 ) that is always less than 1 ; ( 4 ) that measures the closeness of -relation .
II .
" " On the Maximum Discharge rough a Pipe of Circular Section when the effective Head ; due only to the Pipe 's \ldquo ; By HENRY HENNESbY , F.R.S. , Professor of Applied llathcmatics in the Royal College of Science for Irelaud .
Received Novembcr 15 , 1888 .
In the papel on ' ' Hydrnulic Problems the -secbions of Pipes was shown that the greatest hydraulic mcftn depth was that for a channel formed by a segmen of a circle , and by an arc of .
It is easy to find by a similar process the wetted perimeter of a circular pipe to the maximm disc.harge when the velocity of the liquid is due only to the of the pipe .
Among formulae adopted by hydraulic engincers for , the velocity of liquid in a pipe whose ulic mean depth is , we select Darcy 's : which ves l ) where and are constauti cocfficients and I a quantity .
on the cliuation of pipe .
But as the discharge is the product of the velocity by the area of cross-secbion , have * ' Rov .
Soc. Proc

