160 



Testing Milk and Its Products. 



way may not be the correct average test of the entire 

 quantity of milk. The accuracy of such an average 

 figure will depend on the uniformity in the composition 

 and weights of the ten lots of milk. When there is no 

 uniformity, the weights of the different lots of milk as 

 well as their tests must be considered. The following 

 example illustrates the difference between the arithmet- 

 ical average of a number of single tests and the true 

 average test of the various lots. 



Methods of calculating average percentages. 



1 56.2X100 



=4.73. 



49.8X100 



=4.22. 



1187 1187 



195. The figures given in the table show that when 

 the different lots of milk vary in test and weight, as in 

 the first case, the correct average test of the 1187 Ibs. of 

 milk is not found by dividing the sum of these tests by 

 five, which would give 4.14 per cent.; but the percentage 

 which 56.2 (the total amount of fat in the mixed milk, 

 in Ibs. ) is of 1187 (the total amount of milk in Ibs. ) is 



