A lightning quick An Andrew Heiss, Ph PhD Brigham Young - - PowerPoint PPT Presentation

a lightning quick
SMART_READER_LITE
LIVE PREVIEW

A lightning quick An Andrew Heiss, Ph PhD Brigham Young - - PowerPoint PPT Presentation

A lightning quick An Andrew Heiss, Ph PhD Brigham Young University introduction to data West Coast Nonprofit Data Conference visualization April 27, 2018 Plan for today Why visualize data? Types of visualizations Aesthetics and design


slide-1
SLIDE 1

A lightning quick introduction to data visualization

An Andrew Heiss, Ph PhD Brigham Young University West Coast Nonprofit Data Conference April 27, 2018

slide-2
SLIDE 2

Why visualize data?

Plan for today

Aesthetics and design Types of visualizations How do I do all this? Take a sad plot and make it better

slide-3
SLIDE 3

talks.andrewheiss.com/wcnpd18

slide-4
SLIDE 4

Why visualize data?

slide-5
SLIDE 5

Theories are only stories until you have some data. Data alone cannot tell stories or prove theories.

slide-6
SLIDE 6
slide-7
SLIDE 7
slide-8
SLIDE 8

Never trust summary statistics alone

slide-9
SLIDE 9

Humans are visual creatures

@FacesPics

slide-10
SLIDE 10
slide-11
SLIDE 11
slide-12
SLIDE 12

The War of 1812 (the European one)

Long distance!

slide-13
SLIDE 13

The War of 1812 (the European one)

Very cold!

  • 35
  • 30
  • 25
  • 20
  • 15
  • 10
  • 5

01-Oct 01-Nov 01-Dec

slide-14
SLIDE 14

The War of 1812 (the European one)

Very sad!

Napoleon’s Grande Armée

Died Survived

slide-15
SLIDE 15
slide-16
SLIDE 16

Characteristics of graphical excellence

  • 1. “... the well-designed presentation of interesting

data—a matter of substance, statistics, and design.”

  • 2. Complex ideas communicated with

clarity, precision, and efficiency.

  • 3. That which gives the viewer the greatest

number of ideas in the shortest time with the least ink in the smallest space.

  • 4. Nearly always multivariate.
  • 5. Requires telling the truth about the data.
slide-17
SLIDE 17

What makes Minard’s graph so great?

slide-18
SLIDE 18

We forget this!

slide-19
SLIDE 19
slide-20
SLIDE 20
slide-21
SLIDE 21
slide-22
SLIDE 22
slide-23
SLIDE 23

Types of visualizations

slide-24
SLIDE 24

Exploratory visualizations

Academic-ish Quick scatterplots, histograms, other charts to help understand your data

Explanatory visualizations

Publishable Consumable by the general public; Vox, NYT, Washington Post, FiveThirtyEight, etc.

slide-25
SLIDE 25

Exploratory Explanatory

slide-26
SLIDE 26

Exploratory data analysis

Visualize every variable individually

slide-27
SLIDE 27

Exploratory data analysis

Visualize relationships between each variable

slide-28
SLIDE 28

Explanatory data analysis

Annotate and tell a story

slide-29
SLIDE 29

Explanatory data analysis

Annotate and tell a story

slide-30
SLIDE 30

Which chart type do I use? datavizcatalogue.com

slide-31
SLIDE 31

Dataviz gotchas: multiple y-axes

slide-32
SLIDE 32

Dataviz gotchas: multiple y-axes

slide-33
SLIDE 33

Dataviz gotchas: multiple y-axes

It’s okay if both axes measure the same thing

slide-34
SLIDE 34

Dataviz gotchas: truncated y-axes

slide-35
SLIDE 35

Truncation is okay sometimes!

…when small movements matter

slide-36
SLIDE 36

Truncation is okay sometimes!

…when zero values are impossible

slide-37
SLIDE 37

Truncation is okay sometimes!

…but never on bar charts!

slide-38
SLIDE 38

Aesthetics and design

slide-39
SLIDE 39

Fonts

Nice sans serif fonts; move away from Arial

Design principles

Co Contrast Re Repeti titi tion Al Alignment Pr Proxi ximity

slide-40
SLIDE 40

Colors

Be aware of colorblind users!

slide-41
SLIDE 41

Choose universally accessible palettes

slide-42
SLIDE 42

How do I do all this?

slide-43
SLIDE 43

Ba Barri rrier er to en entry ry (a (amount of coding req required red) Fl Flexibility an and power

slide-44
SLIDE 44

Take a sad plot and make it better

slide-45
SLIDE 45

talks.andrewheiss.com/wcnpd18