File:Statistical studies in the New York money-market; preceded by a brief analysis under the theory of money and credit, with statistical tables, diagrams and folding chart (1902) (14777566691).jpg

Identifier: statisticalstudi00nort (find matches)
Title: Statistical studies in the New York money-market; preceded by a brief analysis under the theory of money and credit, with statistical tables, diagrams and folding chart
Year: 1902 (1900s)
Authors: Norton, John Pease, 1877-
Subjects: New York Stock Exchange Credit Money
Publisher: New York, MacMillan
Contributing Library: Robarts - University of Toronto
Digitizing Sponsor: University of Toronto

View Book Page: Book Viewer
About This Book: Catalog Entry
View All Images: All Images From Book
Click here to view book online to see this illustration in context in a browseable online version of this book.

Text Appearing Before Image:
each week over eighteen years,according to this system should theoretically end theeighteenth year without loss or gain. These boxes repre-sent the actuarial range. It is perhaps some approximation to exactness when foreighteen years an underwriter would have been safe inbetting that there would be an increase in the second weekof the year between 4.4 and 6.8, or for the eighth week adecrease between 1.5 and 4.5. Suppose we take the secondweek of the year 1901 and estimate the limits of the proba-ble range of increase. The interpolated axis for the secondweek is 217.5 by the equation Log R= 1.823682-I-0.023317 t.The increase should then lie with an even chance between4.4X217.5 and 6.8X217.5, i. e. between an increase of $9.5millions and $14.8 millions. The actual increase for thatweek was $11.8 millions approximately, or 5.4$ change withthe eighteen year average 5.3$. Of course such close pre-diction is by no means always possible. On the other hand, a deviation from the range seldom
Text Appearing After Image:
-\i-a. -3-<i-5-<o-1-8 Diagram w.$. —53— occurs without the bias extending over several weeks andoften over the whole season. Thus the range is capable ofcorrection by the dynamic tendencies of the immediatelypreceding weeks.* The movement with the seasons of the year is apparent bythe band movement of the rectangles. §35. To return to the table of the eighteen year series, aslight correction is necessary before proceeding further. Ifwe add the advances in one column and the declines inanother, the sum of the advances, 38.837, is greater thanthe sum of the declines, 34.843, by 3.994. This disparityoccurs for several reasons,—among which are imperfect inter-polation, a majority of the years recently above the axis andthe omission of the years 1893 and 1894. To form the period curve it is necessary that the sum otthe advances shall equal the sum of the declines. This isreadily accomplished by a distribution of the 3.994 differenceover the 73.670 points of movement by deducti

Note About Images