Karl Pearson 
217 
This difference of distribution between the non-independent and independent 
means is a noteworthy one, and I am not able fully to account for it. The 
determination of the opsonic index by wholly different series of leucocytes shows 
much the same results whether we use a slide and count both due to Sir Almroth 
Wright's Laboratory, or a slide and count both prepared outside it. But the 
actual record of the counts differs in this respect — that the large and small 
numbers of leucocytes alternate more completely in Fleming's than in Greenwood 
Diagbam VI. (Fleming, 400 dependent Samples of 50.) 
70 
60 
50- 
i 1 1 r 
I 1 1 r 
- 1 i — 1 — i r 
^ 40 
30 
20- 
10 
2-8 2-9 3-0 3-1 3-2 3-3 3-4 3-5 3 6 3-7 3 8 3 9 4 0 4-1 4 2 4-3 4 4 4-5 
Mean Number of Bacilli per Leucocyte. 
Diagram VII. (Greenwood and White, 400 dependent Samples of 50.) 
Biometrika vm 
2-5 2-6 2-7 2-8 2-9 3-0 3-1 3-2 3-3 3-4 3 5 3-6 3-7 3-8 3-9 4-0 4-1 4-2 4-3 ; 4-4 
Mean Number of Bacilli per Leucocyte. 
28 
