A STATISTICAL METHOD FOR MEASURING ‘MARGINAL UTILITY’ 159 
The private account books, . . . are all full. . . . But it is chiefly 
a want of method and completeness in this vast mass of informa- 
tion which prevents our employing it in the scientific investiga- 
tions of the natural laws of Economics.” * 
It has long seemed to me that just such records of consumption 
as Jevons mentioned ought, on proper analysis, to yield a real 
statistical measurement of this most elusive of magnitudes. If 
this cannot yet be done for the individual, or even for the 
individual family, it may be that it can be done for a “typical” 
family, an imaginary family, consisting of a given number of 
people and having a given income. That is to say, we may 
possibly be able to make use of mass statistics somewhat as the 
physicist measures the pressure of a gas without measuring the 
impulses of individual molecules, though it is really the bombard- 
ment of these against the containing walls which really consti- 
tutes the gaseous pressure. We can often gauge a mass effect 
when we cannot gauge its constituent parts. As my old master in 
mathematical physics, J. Willard Gibbs, used to say, “The whole 
is simpler than its parts.” 
The records from which I hope we may succeed in distilling out 
the desired psychological essense, the want-for-one-more, are (1) 
retail prices, and (2) family budgets. Through such mass sta- 
tistical measurements we may succeed in gauging average or 
typical human emotions even better than any individual who 
feels them, just as a clever editor, or advertiser, or salesman, 
knows what the mass of people want better than any person in 
that mass itself. 
Specifications Re Budgets and Prices 
The method consists, in a word, of so utilizing data of family 
budgets and prices as to compare the wants of two typical families 
of different incomes, in the same community, by using as a yard- 
stick or criterion, a third typical family having identical tastes, 
but differing in the amount of income, and living under a different 
scale of prices for foods, rents, clothing and other items of 
consumption. 
Let us, then, imagine three typical workingmen’s families, each 
consisting, say, of five people, the man himself, his wife, and 
three typical children. 
2 0p. Cit. pp. 10, 11.