Karl Pearson and David Heron 
187 
TABLE III. 
Table for Eye-Colour in Father and Son equalised, or put into 
Mr Yide's " Natural " Groups. 
Eye-Colour of Father. 
a 
o 
m 
3 
"3 
■ 
H 
1+2 
3 
4 
5 + 6 
7 + 8 
Totals 
1+2 
448-88 
212-23 
153-14 
80-30 
105-45 
1000 
201-60 
394-65 
160-75 
121-76 
121-24 
1000 
4 
110-24 
196-44 
391-47 
187-02 
114-83 
1000 
5 + 6 
125-09 
72-85 
142-09 
428-73 
231 -24 
1000 
7 + 8 
114-19 
123-83 
152-55 
182-19 
427-24 
1000 
Totals 
1000 
1000 
1000 
1000 
1000 
5000 
In this case the Q was not constant for all divisions at starting, and therefore 
there is no general standard. But Mr Yule tells us that his method of pseudo- 
ranks is the best known to him for such a table. The Yulean for this table before 
equalisation was "403, after equalisation it is "166 ! Q can change as much as from 
"52 to '43. It is only an " unnatural " equalisation which keeps Q constant. 
Let us consider another case of this, taken from the one field to which Mr Yule 
in his present paper ventures to apply his coefficient, that of vaccination*. 
TABLE IV. 
Severity of Small Pox. 
Haemorrhagic 
Confluent 
Abundant 
Sparse 
Very 
Sparse 
Totals 
Vaccinated, [in og 
Years since \ , r 
vaccination Ti 
'.Over /ft 
Unvaccinated 
0 
5 
29 
1 
37 
155 
35 
61 
6 
114 
299 
48 
41 
11 
165 
268 
33 
7 
12 
136 
181 
28 
2 
30 
457 
932 
155 
115 
Totals 
49 
289 
508 
484 
359 
1689 
The equalisation factors are : 
For Rows : 
For 
Columns : 
= 6-1300, 
X x = 
11-0816, 
= -3631, 
x 2 = 
1-5125, 
= -1496, 
x s = 
10000, 
2/4 
= -6923, 
10113, 
= 1-0697, 
{J0 5 = 
1-1659, 
reckoning rows and columns from the left-hand top corner. 
* See Biometrika, Vol. vn. p. 257. 
24—2 
