ON A NOVEL METHOD OF REGARDING ASSOCIATION 



19 



From Table IV, by interpolation for „ct-,= "0608, 



r = 0-5, logx'=l"9366, 



r = 0-6, log x' = 2-1138, 



whence r=-506, when x'=l'9452. The abac gives us -51. We have to set these 

 values against 



r = -500 + -033, 



and we see that the difference is again not significant. 



Illustration VII. As a last Gaussian material case, I take the following table, 

 namely 2000 distributed so as to give r= -25, 



Here 



These give by Table V 



aCrr = - 



logx' = 1-4526, 

 i(l + aJ = -9, ^(l + a,) = -6. 



X 1-7094 X 1-2680 - -048,467. 



n/2000 



Whence by interpolation we find r=-226 and by the abac -23. We have then to 

 compare the Gaussian 



7- = -25 ±-03, 



with r=*23, and we see that the difference is again less than the probable error 

 of random sampling. 



Illustrations V, VI and VII seem to show that, for truly Gaussian material, the 

 two methods lead to closely similar results. 



Illustration VIII. The following table represents in a fourfold form the corre- 

 lation between the length of left foot and left middle finger in 3000 criminals. It is 

 taken from Macdonell's paper {Biometrika, Vol. i. p. 226). 



3—2 



