Along with bar charts, scatter plots are probably the most common type of graph to help managers make decisions based on data. When you have a data set consisting of pairs of numbers, such as counts of lawyers in a law firm and locations of that firm, you can display the data in a scatter plot and learn from it. On a so-called Cartesian grid, each point represents the paired numbers of one firm. Using precisely such a data set, this article highlights a number of choices available when crafting insightful scatter plots.

Plot Paired Numbers on a Grid: The scatter plot comes from 2015 data that was assembled by the author. It shows for 176 U.S. law firms that had between 200 and 1,000 lawyers how many office locations each firm had. Those pieces of information are the variables represented on the scatter plot, which is the fundamental choice: what kind of plot to create to present data most effectively.


Plot by Rees Morrison

The horizontal x axis tells how many lawyers practiced at the firm at that time while the left, vertical y axis tells you how many offices the firm had according to its website. Each point represents a pair of numbers for a firm—lawyers and offices—plotted on a grid. The horizontal axis is sorted from low on the left to high on the right, but that is a default that can be changed.