[ 3*9 ] 
23. The ratio of T)ht¥ to ACFH is greater 
P 9 
than 2 , and lefs than 2 x 1 4 - 2 E a l? 4- 2 E a b • 
n 
For D h t F being greater than R ht Q, the ratio of 
it to ACFH muff be greater than the ratio of 
R^/Q_to ACFH, or greater than 2. Alfo ; 
fince the ratio of R h t Q_to ACFH is equal to 
2 y and the ratio of D £ ^ F to R £ / Qjs lefs than the 
ratio of 1 4 - 2 E atf 4 - _ , E _Jl to 1 y it follows that 
1 n 
the ratio compounded of the ratio of R<6/Q_to 
ACFH, and of Dht¥ to R£/Q, that is, the ratio of 
D/6/F to ACFH mud be lefs than 2 x i-j-2E / 6 
a E a $ 
- • • 
71 . 
24. The ratio of D h t F ~\~ D h J C to A C F H 
(that is, the chance for being right in judging that 
the probability of an event perfectly unknown, which* 
has happened p and failed q times in p q ° r n trials,, 
i> t> 
lies fomewhere between — 4- z and — 2;) is* 
a n J 
greater than — , and lefs than 2 2.- 
1+ 2 E a b q + aE / b q 
The former part of this Art. -has been already proved,. 
Art. 1-2. The latter part is evident from Art. 21. 
For R ht QJpeing greater than the arithmetical mean' 
between T)ht¥ and ’DhJ'C, 2 R Z7/ Q^jnufl be 
greater than DhtF -j” D hf C ; and confequently 
