Exploring Data Visually - Data Points: Visualization That Means Something - page 531

An alternative to the parallel coordinates plot, a scatter plot matrix, as shown
in Figure 4-49, can show similar relationships. The relationships between
variables are often easier to see in the matrix than with parallel coordinates
because you can compare pairwise correlations instead of trying to decipher
relationships between multiple variables at once. The latter is often compli-
cated and hard to see.

It's also often useful to look at data with different views at the same time. For
example, Figure 4-50 shows data as a heat map, bar chart, and star plot, for
several players. The heat map provides detailed information about where the
players shoot from; the bar graph provides an overview of the aggregates;
and the star plot shows values for additional variables. Together, the views
represent the playing style of several individuals, or more generally speaking,
a detailed overview of several categories.

WHAT TO LOOK FOR

There are a lot of visualization methods that help you explore various aspects
of your data, whether it is categories, time, space, or a combination of these.
You can visualize the data all at once, but you can also make use of simpler,
more straightforward views, which can help extract relationships. Sometimes
the relationships are straightforward between two variables, but usually the
relationship is complex, especially when you introduce more than two vari-
ables. Don't make assumptions as you explore relationships, and keep in mind
there are variables not captured in the data that might contribute to changes.
Finally, when it comes to correlation and causation, you need to take in all the
context you can before you assign the latter.

DISTRIBUTIONS

You often hear or read about means and medians. They're used to describe
a group of people, places, or things, and these measurements typically imply
what is “normal” or “average,” and anything that is far away from these mea-
surements is abnormal or above or below average. However, what qualifies
as extremely above average or just slightly below average? Is something 10
percent greater than the median a lot or a little? To answer these questions,
you must know more about the data than just where the middle is. You have
to know the spread.

FIGURE 4-49 (following page)
Scatter plot matrix