Miss to Make It

• Author: Tim Chartier
• DOI: http://doi.org/10.1002/jcaf.22193
• Date: 01 October 2016
• Published date: 01 October 2016

87

© 2016 Wiley Periodicals, Inc.

Published online in Wiley Online Library (wileyonlinelibrary.com).

DOI 10.1002/jcaf.22193

C

o

m

m

e

n

t

a

r

y

Miss to Make It

Tim Chartier

In April 2016, I sat in a

packed auditorium at Lenoir-

Rhyne University to hear

award-winning writer Anne

Lamott speak as part of the

college’s Visiting Writers Series.

She offered words of advice on

writing to the gathered crowd.

A recurring point in the evening

was simple: First drafts are ter-

rible but allow us to experience

the “magic of messes.”

Lamott’s speech occurred

in the final days of the NBA

regular season. The Golden

State Warriors were chasing

the historic mark of 73 regular

season wins. Steph Curry was

also setting a record with every

three-point shot. Curry was

smashing the previous record

of 286 that he set in the previ-

ous year. He’d surpassed the

mark of 300 made three-point

shots in March, well over a

month before the end of the

regular season. He’d eventually

shoot just over 400.

Lamott’s characteriza-

tion of the writing process

and Curry’s shooting prowess

underscored how accomplish-

ments can be interwoven with

missed attempts. Michael

Jordan put it this way:

I’ve missed more than

9,000 shots in my

career. I’ve lost almost

300 games. Twenty-

six times, I’ve been

trustedto take the

game-winning shot and

missed. I’ve failed over

and over and over again

in my life. And that is

why Isucceed.

Anne Lamott’s books

received acclaim, not the drafts.

Steph Curry misses from

behind the three-point line

overhalf the time.

How does this apply to

data science? There are gen-

erally no awards or winning

and losing. There are, how-

ever, attempts not at shooting

or writing but at insight. To

write a book, you must sit and

write, even if the result is ini-

tially poorly conceived. Steph

Currymust be willing to shoot

the ball and inevitably miss

over half the time in order to

score. To gain insight from

data, you must form a ques-

tion, gather data, and perform

analysis without a guarantee

of helpful results. Lamott is a

gifted writer. Curry is an MVP

player. Those performing your

data analysis should be trained

and serious in their explora-

tion. Still, missed attempts can

lead to success.

The best-written chapters

in a draft may not make the

final book. Open shots from

behind the three-point line

maynot lead to a score. In data

science, you may have a clear

vision of how to approach a

problem. After tackling the

question, you may find it is

harder than expected—pos-

sibly even unanswerable in its

current form. Such moments

clarify what you know and

don’t know, what you can and

cannot do.

You may, like writing a

draft or shooting on a practice

court, need to step back and do

more background work. You

may need to learn new ideas,

revisit your question, or collect

more data. Failing to attain

actionable, insightful results

can be disappointing but could

be the step that leads to bigger

insight than expected.

Other times, you won’t have

a clear vision for analysis and

could feel stuck in the data

science. When this happens, be

sure, switching to a baseball

analogy, that you are willing to

risk a strikeout. As Babe Ruth

said:

Every strike brings me

closer to the next home run.

If you perform analysis

and don’t gain insight, ask