PROBABLE ERROR 101 



of useful things about the probable error. In the first 

 place its value varies inversely as the square root of 

 the number of variates that is to say, that in such a 

 case as we have just described the probable error varies 

 inversely as the square root of the number of balls 

 drawn each time. We can realize this point more 

 clearly when we remember that the linear dimensions 

 of a curve vary with the square root of its area (the 

 number of variates) ; the accuracy of our determination 

 varies in fact with the quart ile, which is the linear 

 distance from the mode of a certain perpendicular. 



We have seen that it is an even chance whether a 

 single determination differs from the proper value by 

 more or less than the amount of the probable error, 

 an amount which we may denote by the letter e. 

 The chance that any particular determination differs 

 from the true value by more than twice the probable 

 error is 4-5 to i against. 



The chance that it differs by more than 3* is 21 : I against. 

 4* 142 : i 



> > > 5^ > *3*o * > 



This is clearly very valuable information to possess 

 when we are dealing with any kind of statistics. 



We must now pass on to consider what methods are 

 available to the biometrician for dealing with the 

 problems of heredity. His way is to take a large 

 number of pairs of relations, each pair consisting, say, 

 of a father and a son, and to find out how much more 

 like the members of such a pair are to one another on 

 the average than the members of similar pairs of 

 individuals would be, if taken at random and without 



