Page 44 - The Real Work Of Data Science Turning Data Into Information, Better Decisions, And Stronger Organizations by Ron S. Kenett, Thomas C. Redman (z-lib.org)_Neat

7

Make It Easy for People

to Understand Your Insights

Most of us learn more from our mistakes than we do from our successes. One of us, Redman,
learned a lesson that has stuck with him for 30 years.* The story concerns his first big presen-
tation at AT&T headquarters. He completed his preparation well in advance and rehearsed
carefully. Then off to the big meeting.
It could not have gone worse! The only impressions he left were bad ones. Young hothead
that he was, he blamed everyone but himself, including the audience: “The average manager
up here can’t even understand a pie chart!”
An established veteran of many such presentations looked him square in the eye and said,
“Of course not, Tom. It’s your job to make it so they don’t have to.”
The lesson is not simply about Redman being immature. As a data scientist, you face a tall
order in getting decision‐makers to comprehend and believe data, your results, and their impli-
cations. You have to think through their background and present in ways that advance their
understanding. This takes more time than you may think. It helps to be a good writer and
speaker. But more than anything, great visuals (e.g. graphics) and great stories carry the day!
Visualization has a storied past – see Fienberg (1979). Communication is the eighth dimension
in the information quality framework introduced in Chapter 13; see also Kenett and Shmueli
(2014, 2016a) and Appendix C.

First, Get the Basics Right
At a minimum, you must make your plots and the accompanying explanations easy to under-
stand. As Edward Tufte advises (Tufte 1997), clearly label the axes, keep chart junk to a
minimum, and don’t distort the data.
Consider this example. The plot in Figure 7.1 is a typical result of a well‐conceived and well‐
executed data quality program. But it features too many unfamiliar terms, such as “accuracy
rate” and “fraction perfect records.” Without additional explanation, you’ll lose your audience.
1

*This Chapter is based, in part, on a Harvard Business Review digital article by Redman (2014).
The Real Work of Data Science: Turning Data into Information, Better Decisions, and Stronger Organizations,
First Edition. Ron S. Kenett and Thomas C. Redman.
© 2019 Ron S. Kenett and Thomas C. Redman. Published 2019 by John Wiley & Sons Ltd.
Companion website: www.wiley.com/go/kenett-redman/datascience