Exploring Data Visually - Data Points: Visualization That Means Something - page 165

WHAT TO LOOK FOR

Generally speaking, look for changes over time. More specifically, note the nature
of the changes. Are the changes relatively a lot or are they small? If they're small,
is the change still significant? Think of possible reasons for what you see over
time or sudden blips and if they make sense. The change itself is interesting,
but more importantly, you want to know the significance of a change.

V ISUALIZ I N G S PAT IAL DATA

Spatial data is easy to relate to because at any given moment—as you read
this sentence—you have a sense of where you are. You know where you live,
where you've been, and where you want to go.

There is a natural hierarchy to spatial data that allows, and often requires,
you to explore at different granularities. Far out into space, Earth looks like a
small, blue dot with little to see, but as you zoom in, you see land and large
bodies of water. There are continents and oceans. Zoom in again, and you get
countries and seas, then provinces and states, counties, districts, cities, towns,
neighborhoods, all the way down to an individual household.

Global data is often categorized by country and national data by states, prov-
inces, or territories. However, if you have questions about variation across
blocks or neighborhoods, such high-level aggregates won't do you much
good. So again, the exploration route you choose depends on the data you
have or the data you can get.

The most obvious way to explore spatial data is with maps, which place val-
ues within a geographic coordinate system. Figure 4-26 shows some of your
options, of which there are many.

If you care only about individual locations, you can place
dots on a map, as shown in Figure 4-27. The map simply
shows the 30 busiest airports in the United States, based
on the number of outgoing flights in 2011. As you might
expect, the busy airports are in or near major cities such
as Los Angeles, Washington, DC, New York, and Atlanta.

Note: A map isn't always the most informa-
tive way to visualize spatial data. Often, you
can treat regions as categories, and a bar graph
might be more useful than seeing a location.