ON THE STATISTICAL VIKW OF NATURK. 567 



once be seen how all arrangements which are based 

 upon these three conceptions — viz., probability, co- 

 operation, and equitable distribution — lead us away 

 from the study of individual cases to that of totals 

 and averages ; how they merge the interests of single 

 persons and the peculiarities of single cases in those 

 of the aggregate of a large number and the properties 

 of the average event or the " mean " man. Their 

 value and success depend on the consideration and 

 participation of large numbers, and they have accord- 

 ingly only arisen during the latter days which have 

 witnessed the steady growth of modern populations 

 and the bewildering complication of modern business. 

 The moral or social aspect which has simultaneously 

 been evolved during our period does not for the 

 moment concern us. We are concerned at present 

 only with the fact that statistics as the science of 

 large numbers and of averages has been increasingly 

 drawn into use. In fact, we might call our century 

 — in distinction from former centuries — the statistical 

 century. 



The necessity of having recourse to elaborate countings, 

 to registrations of births, deaths, and marriages, to lists 

 of exports and imports, to records of consumption and pro- 

 duction of food-stuffs and many other items, forced upon 

 those who were entrusted with the gathering and using of 

 these data the observation that all such knowledge is in- 

 complete and inaccurate. Owing to the variability, within 

 certain limits, of recurring events and the errors of count- 

 ing and registration, we have to content ourselves always 

 with approximation instead of certainty. Error bulks 



