Database Reference
In-Depth Information
dimension. Perhaps it is a student, who is performing well in some classes
but struggling in others, or a customer service call that took too long and
resulted in some unhappy comments. You'll find that as you read each row, a
small character study emerges.
Columns Give the Bigger Picture
If the rows are the trees, the columns help you understand the forest. Start by
removing columns that aren't helpful. Data tables straight from a data source
are often littered with fields that are empty, redundant, or hold no useful
information. Find those columns that you can relate to your experience in
the real world. Separate the interesting columns into two buckets: dimensions
(the who, what, where, and when of the elements) and metrics (how much).
To understand dimensions, ask these questions:
How many unique values are there?
⬛
What are the most common values?
⬛
What proportion of all the elements are represented by the top few
dimensional values?
⬛
Analyzing the metrics in your data will focus more on summarizing
values:
⬛
⬛
What is the average value?
What are the minimum and maximum values?
⬛
What causes the outliers?
⬛
What is the distribution of values?
⬛
Answering these types of questions can build a familiarity with the data and
reveal insights about the real world behind that data.
uNDERSTANDING CHARTS AND VISuALIZATIONS
We have an inbuilt ability to manipulate visual metaphors in ways we cannot
do with the things and concepts they stand for—to use them as malleable,
conceptual Tetris blocks or modeling clay that we can more easily squeeze,
stack, and reorder. And then—whammo!—a pattern emerges, and we've arrived
someplace we would never have gotten by any other means.
David Byrne, from the introduction to
The Best American Infographics
3
Search WWH ::
Custom Search