Page:Graphic methods for presenting facts (1914).djvu/208

 Fig. 158. Cumulative Frequency Curve Study of the Number and the Size of All Orders Handled During One Week in a Certain Kind of Freight-handling Work Carried on in Two Closely-related Departments

Curve "H" shows by small circles the actual number of orders found in each size-of-order-class. Note that at the left of the chart there are numerous orders shown in each class even though here the limits of each class have been purposely made very close together

Curve "B" shows the percentage of the total orders handled which contain more than any given number of packages considered on the horizontal scale of the chart

Curves "A" and "C" are similar to curve "B" and show subdivisions of the total number of orders according to which of two related departments handled the work

Curve "F" corresponds with curve "B" but shows the percentage of the total number of pieces carried by those orders containing more than any given number of pieces considered on the horizontal scale of the chart

Curves "G" and "E" are similar to curve "F" and show subdivisions in the total number of pieces according to which of two related departments handled the work

One sub-department of the business handled the orders portrayed by Curve "A" and Curve "E". The other sub-department handled orders portrayed by Curve "C" and curve "G". The combined work of the two departments is shown by Curve "B" and Curve "F"

The percentage of the total number of orders handled in each of the two different departments, up to any size of order read on the horizontal scale, may be seen by considering the distances on the chart above and below Curve "D"

kind can be of service in a sales analysis for almost any kind of business. A company selling fairly uniform products—shoes, for example—could use for the horizontal scale the actual number of pairs of shoes contained on various orders received for the test period of, say, a week or a month. Companies having a diversified product, as electrical machinery, could best make a chart of this kind by basing the horizontal scale on the actual value in dollars of the various orders received. Thus, the scale could be made for orders in sizes larger than $50, $500, $1,000, etc. If charts are made for different departments, very interesting comparisons could be made which would bring