Visualizing Patterns over Time - Data Points: Visualization That Means Something - page 118

FIGurE 4-32 Added grid lines and filled in values for the value axis
Continuous Data
Visualizing continuous time series data is similar to visualizing discrete
data. You do, after all, still have a discrete number of data points, even if
the dataset is continuous. The structure of continuous and discrete is the
same. The difference between the two is what they represent in the physi-
cal world. As previously covered, continuous data represents constantly
changing phenomena, so to this end, you want to visualize the data in a
way that shows that.
Connect the Dots
You're probably familiar with this one. The time series chart is similar to
drawing points, except you also connect the points with lines. Often, you
don't show the points. Figure 4-33 shows the geometry of the popular
chart type.
You have the nodes, or points, that take on X- and Y-coordinates, and then
the edges, or connecting lines that help you see trends in your data. It's
usually a good idea to start the value axis at zero because starting any-
where else could affect the scale.
How far you stretch the horizontal axis can also affect the appearance of
trends. Squish too much, and an increase from point to point might look
more than it is. Stretch too far out, and you might not see patterns.