8 
1 + 
Editorial 
s{s + l)(\ 1\ s(s + l)(s + 2)/l 
273 
1.2 V«„ 
N. 
1.2.3 
2 
+ 
s(s+l)(5 + 2)(s+S)^l _ 1 
: N. 
1.2.3.4 
■9(g+ l)(g + 2 ) (s + 3) (g + 4) 
.1.2.3.4.5 
3 1- 
10 
1 \-/l 
2 
, ^(^+l)(g + 2)(g + 3)(^ + 4)(6' + 5) _ /J_ _ J_ Y _ 
1.2.3.4.5.6 
as far as terms of ctibic order in the curled brackets. 
Hence we find 
1 
S 
1 V 
s 
1 
o 4 5 
3 + ^ + ^. 
n.-).5o 
1^' 
, 1 + 
10 15 
•(I) 
It will be seen that these values agree to the first term in \^ with those 
P 
1 \ = 
given by either hypothesis (i) or (ii). For the terms — ^y-j they appear to 
be intermediate between (i) and (ii). The additional terms which do not occur in 
either (i) or (ii) ax'e those in powers of in the second- and third-order terms. 
Using these results we deduce : 
pMa = mean (S/i/)- 
n 
1 /-, 3 \ 
1 1 
.(J). 
Thus the probable error of the mean of an array of mean size tip in a sample 
of i\r is : 
•67449 ^ 
1 + 
1 / 1 
2 \np N. 
1\/, 1 M 1/1 l\V^ 22\ 41/1 1\ 
.(J^'O. 
