HOW TO START
THINKING LIKE A DATA
SCIENTIST – BY THOMAS
C REDMAN
INTERESTING INSIGHT
2
You don’t have to be a
data scientist or a
Bayesian statistician to
tease useful insights
from data.
Want to
know
How?
3
he exercise is very much a how-to, each step
also illustrates an important concept in
analytics — from understanding variation to
visualization.
ach step also illustrates an important
concept in analytics — from understanding
variation to visualization.
4
Lets try an exercise that illustrates an important concept in
analytics — from understanding variation to visualization.
Start with something that interests or bothers
you and form it up as a question
5
“Meetings always
seem to start late. Is
that really true?”
EXAMPLE
Write down all the relevant definitions and
protocol for collecting the data.
6
▰ For this particular example,
define when the meeting
actually begins. Is it the time
someone says, “Ok, let’s
begin.”? Or the time the real
business of the meeting starts?
Does kibitzing count?
▰
It is critical that you
trust the data.
7
COLLECT
DATA
Sooner , you’ll be ready to start drawing some
pictures.
▰ Here, a plot
represents the date
and time of a
meeting versus the
number of minutes
late.
▰
8
Now return to the question and develop summary
statistics.
▰ In this case, “Over a two-week period,
10% of the meetings I attended started
on time. And on average, they started
12 minutes late.”
▰
9
DON’T stop here
10
Answer the “so what?” question.
▰ In this case, “If those
two weeks are typical, I
waste an hour a day.
And that costs the
company $X/year.”
▰
11
Get a feel for variation.
12
A few meetings start right on
time, others nearly a full 30
minutes late but the variation is
too great.
““What else does
the data reveal?”
1313
“What else does the data reveal?”
Five meetings that began exactly
on time were called by the
Vice President of Finance.
Evidently, she starts all her
meetings on time.
▰
14
Are your results consistent with
others’ experiences in the
company?
Which starts later: conference
calls or face-to-face
meetings?
Are some days worse than
others?
15
Return to step one, pose
the next group of
questions, and repeat
the process. Keep the
focus narrow — two or
three questions at most.
17
THANKS!
CREDITS
Special thanks to all the people who made and
released these awesome resources for free:
▰ Presentation template by SlidesCarnival
▰ Photographs by Startup Stock Photos
18
PRESENTATION DESIGN
This presentation uses the following typographies and colors:
▰ Titles: Roboto Condensed
▰ Body copy: Roboto Condensed
You can download the fonts on this page:
https://material.io/guidelines/resources/roboto-noto-fonts.html
Navy #3f5378 · Dark navy #263248 · Yellow #ff9800
You don’t need to keep this slide in your presentation. It’s only here to serve you as a design guide if you need to create
new slides or download the fonts to edit the presentation in PowerPoint®
19
SlidesCarnival icons are editable shapes.
This means that you can:
● Resize them without losing quality.
● Change line color, width and style.
Isn’t that nice? :)
Examples:
20
Now you can use any emoji as an icon!
And of course it resizes without losing quality and you can change the color.
How? Follow Google instructions
https://twitter.com/googledocs/status/730087240156643328
✋👆👉👍👤👦👧👨👩👪💃🏃💑❤😂
😉😋😒😭👶😸🐟🍒🍔💣📌📖🔨🎃🎈
🎨🏈🏰🌏🔌🔑 and many more...
😉
21

Presentation 4

  • 1.
    HOW TO START THINKINGLIKE A DATA SCIENTIST – BY THOMAS C REDMAN
  • 2.
    INTERESTING INSIGHT 2 You don’thave to be a data scientist or a Bayesian statistician to tease useful insights from data.
  • 3.
  • 4.
    he exercise isvery much a how-to, each step also illustrates an important concept in analytics — from understanding variation to visualization. ach step also illustrates an important concept in analytics — from understanding variation to visualization. 4 Lets try an exercise that illustrates an important concept in analytics — from understanding variation to visualization.
  • 5.
    Start with somethingthat interests or bothers you and form it up as a question 5 “Meetings always seem to start late. Is that really true?” EXAMPLE
  • 6.
    Write down allthe relevant definitions and protocol for collecting the data. 6 ▰ For this particular example, define when the meeting actually begins. Is it the time someone says, “Ok, let’s begin.”? Or the time the real business of the meeting starts? Does kibitzing count? ▰
  • 7.
    It is criticalthat you trust the data. 7 COLLECT DATA
  • 8.
    Sooner , you’llbe ready to start drawing some pictures. ▰ Here, a plot represents the date and time of a meeting versus the number of minutes late. ▰ 8
  • 9.
    Now return tothe question and develop summary statistics. ▰ In this case, “Over a two-week period, 10% of the meetings I attended started on time. And on average, they started 12 minutes late.” ▰ 9
  • 10.
  • 11.
    Answer the “sowhat?” question. ▰ In this case, “If those two weeks are typical, I waste an hour a day. And that costs the company $X/year.” ▰ 11
  • 12.
    Get a feelfor variation. 12 A few meetings start right on time, others nearly a full 30 minutes late but the variation is too great.
  • 13.
    ““What else does thedata reveal?” 1313
  • 14.
    “What else doesthe data reveal?” Five meetings that began exactly on time were called by the Vice President of Finance. Evidently, she starts all her meetings on time. ▰ 14
  • 15.
    Are your resultsconsistent with others’ experiences in the company? Which starts later: conference calls or face-to-face meetings? Are some days worse than others? 15
  • 16.
    Return to stepone, pose the next group of questions, and repeat the process. Keep the focus narrow — two or three questions at most.
  • 17.
  • 18.
    CREDITS Special thanks toall the people who made and released these awesome resources for free: ▰ Presentation template by SlidesCarnival ▰ Photographs by Startup Stock Photos 18
  • 19.
    PRESENTATION DESIGN This presentationuses the following typographies and colors: ▰ Titles: Roboto Condensed ▰ Body copy: Roboto Condensed You can download the fonts on this page: https://material.io/guidelines/resources/roboto-noto-fonts.html Navy #3f5378 · Dark navy #263248 · Yellow #ff9800 You don’t need to keep this slide in your presentation. It’s only here to serve you as a design guide if you need to create new slides or download the fonts to edit the presentation in PowerPoint® 19
  • 20.
    SlidesCarnival icons areeditable shapes. This means that you can: ● Resize them without losing quality. ● Change line color, width and style. Isn’t that nice? :) Examples: 20
  • 21.
    Now you canuse any emoji as an icon! And of course it resizes without losing quality and you can change the color. How? Follow Google instructions https://twitter.com/googledocs/status/730087240156643328 ✋👆👉👍👤👦👧👨👩👪💃🏃💑❤😂 😉😋😒😭👶😸🐟🍒🍔💣📌📖🔨🎃🎈 🎨🏈🏰🌏🔌🔑 and many more... 😉 21