Welcome

The Science of Data Visualization

# T C 1 8

Larry Silverstein

Strategic Sales Consultant

Tableau

Start Your (Visualization) Engines

Agenda

The science of data visualization

Best practices for building dashboards and visualizations

The Science of Data Visualization

Share of Worldwide Urban Population Growth 2010–2050

Share of Worldwide Urban Population Growth 2010–2050

I II III IV

x y x y x y x y

10 8.04 10 9.14 10 7.46 8 6.58

8 6.95 8 8.14 8 6.77 8 5.76

13 7.58 13 8.74 13 12.74 8 7.71

9 8.81 9 8.77 9 7.11 8 8.84

11 8.33 11 9.26 11 7.81 8 8.47

14 9.96 14 8.1 14 8.84 8 7.04

6 7.24 6 6.13 6 6.08 8 5.25

4 4.26 4 3.1 4 5.39 19 12.5

12 10.84 12 9.13 12 8.15 8 5.56

7 4.82 7 7.26 7 6.42 8 7.91

5 5.68 5 4.74 5 5.73 8 6.89

I II III IV

x y x y x y x y

10 8.04 10 9.14 10 7.46 8 6.58

8 6.95 8 8.14 8 6.77 8 5.76

13 7.58 13 8.74 13 12.74 8 7.71

9 8.81 9 8.77 9 7.11 8 8.84

11 8.33 11 9.26 11 7.81 8 8.47

14 9.96 14 8.1 14 8.84 8 7.04

6 7.24 6 6.13 6 6.08 8 5.25

4 4.26 4 3.1 4 5.39 19 12.5

12 10.84 12 9.13 12 8.15 8 5.56

7 4.82 7 7.26 7 6.42 8 7.91

5 5.68 5 4.74 5 5.73 8 6.89

Property Value

Mean of x in each case 9 (exact)

Variance of x in each case 11 (exact)

Mean of y in each case 7.50 (to 2 decimal places)

Variance of y in each case4.122 or 4.127 (to 3 decimal

places)

Correlation between x and

y

in each case

0.816 (to 3 decimal places)

Linear regression line in

each case

y = 3.00 + 0.500x (to 2 and 3

decimal places, respectively)

Cerebral CortexThinking

Visual CortexSeeing

Thinking is Slow. Seeing is FAST.

Preattentive Attributes

Have we gained or lost customers over the last 4 years?

Which city has grown the fastest?

Memory Limits

Total # of Registered Customers

2009 2010 2011 2012

New York 402 498 502 335

Seattle 302 355 297 459

Boston 485 432 403 390

Austin 361 482 585 595

Total 1550 1767 1787 1779

How do each of our locations compare?

Visual Representation vs. Table

Memory Limits

16 Numbers

4 Patterns

Use familiar chart types

Don’t make people remember views

Avoid large legends

Use intuitive colors and shapes

Overcoming Memory Limits

Familiar Chart Type? Intuitive Encoding?

Familiar Chart Type? Intuitive Encoding?

Familiar Chart Type. Intuitive Encoding.

Visual Interruptions Make People Slow

Visual Interruptions Make People Slow

Color, Data Types, ChartTypes and Layouts

Best Practices for Color

Color Vision Deficiency (CVD)

Bars and Colors—Caution!

Be thoughtful when applying color to bars

Bars and Colors—Caution!

Be thoughtful when applying color to bars

This is OK

Color perception is relative, not absolute

Color Perception

Provide a consistent background

Color Perception

Humans can only distinguish ~8 colors

Too Many Colors

This is not helpful.

Humans can only distinguish ~8 colors

Right Number of Colors

This is helpful.

Types of Data

Qualitative (nominal)Arizona, New York, TexasSarah, John, MariaCoors, Bud Light, Stella Artois

Qualitative (ordinal)Gold, silver, bronzeExcellent health, good health, poor healthLove it, like it, hate it

QuantitativeWeight (10 lbs, 20 lbs, 5000 lbs)Cost ($50, $100, $0.05)Discount (5%, 10%, 12.8%)

How Do Humans Like Their Data?

Position

Color

Size

Shape

More important

Less important

1. Position

1. Position

What Goes Where?

Emphasized

Neither emphasized

nor de-emphasized De-emphasized

Neither emphasized

nor de-emphasized

Emphasized

What Goes Where? Research…

• https://www.tableau.com/about/blog/2017/6/eye-tracking-study-5-key-learnings-data-designers-everywhere-72395

Best Practices forBuilding Dashboards and Visualizations

Tables

Graphs > Tables for Spotting Trends

Chart Type Generalizations

Time: on an x-axis

Location: on a map

Comparing values: bar chart

Exploring relationships: scatter plot

Relative proportions: treemap

ShowMe: Visual Best Practices - Automatically

Pies vs. Bars (An Unfair Fight, IMO)

A Tip for Using Stacked Bars

Bullet Chart > Gauges

Background fill colors that encode qualitative ranges like bad, satisfactory and good

Text Label

Quantitative Scale

Symbol marker that encodes the comparative measure

Bar that encodes the performance measure

Use line graphs to encode trends over time

Bars vs. Lines

Avoid Food Graphs

Tastier Solutions—Part 1

Tastier Solutions—Part 1

Tastier Solutions—Part 2

Tastier Solutions—Part 2

Tastier Solutions—Part 3

Tastier Solutions—Part 3

Making a Point—About Lines

Making a Point—About Lines

Making a Point—About Lines

Be Careful Using Dual Axes

http://www.tylervigen.com/spurious-correlations

3D?!? Make Mine Small Multiples!

Use maps when location is relevant

Mapping to Insight

“Choropleth” Maps

“Choropleth” Maps

Symbol Maps

A Strike Zone is a Map?!?

Tell the Truth!

So This Is What Really Happened

Sometimes, the Default isn’t Best

Experiment—You Won’t “Break” your Data

Let’s Talk About Dashboards

Are All Dashboards the Same?

http://graphics-info.blogspot.hk/2012/09/malofiej-20-look-at-our-participation.html

http://graphics-info.blogspot.hk/2012/09/malofiej-20-look-at-our-participation.html

Iraq: Deaths on the decline

Which One to Use?

The Same Goals

Make better, data-driven decisions

Make changes for the better

The 5 Second Test

Dashboarding for the 5 Second Test

Most important view goes on top or top-leftLegends go near their viewsAvoid using multiple color schemes on a single dashboard

Use 5 views or fewer in dashboardsProvide interactivity

Dashboarding for the 5 Second Test

Use your words!

Titles

Axes & Units

Key facts and figures

Remove extra digits in numbers

Great tooltips

Dashboarding for the 5 Second Test

Dashboarding for the 5 Second Test

Is Beautiful Design Important?

Recommended Resources

https://www.tableau.com/learn/classroom/virtual?course=2346

Thank you!

#TC18

Larry Silverstein

lsilverstein@tableau.com

Please complete the

session survey from the My

Evaluations menu

in your TC18 app