On the Presentation of Data

1
On the Presentation of Data

• Christian Ritter
• Institut de Statistique, UCL
• and
• Monnet Centre International Laboratories
• Louvain-la-Neuve, Belgium

2
Abstract

• In this talk I shall speak about two issues,
• a theory about human perception,
• a system of principles and techniques.
• Applied consciously, these insights, principles
  and techniques allow creating beautiful,
  truthful, and illuminating displays which enhance
  discovery and communication in graphs, tables and
  slide shows.
• Moreover, they help understand why certain
  presentations do not work and what can be done to
  improve them.
• The talk will be followed by a graph and table
  clinic.

3
Perception and Mind (1) Operation of the Brain
4
Perception and Mind (2) Rates of Information Flow
Main Brain
CentralProcessing Unit
2-4º
long term memory, reasoning,
working memory, input organization, pattern
recognition, comparisons, arithmetic
5
Perception and Mind (3) Accuracy and Speed
6
Example of a Graph
Source a sales presentation
7
Table 1 Quarterly sales of sugar to six locations
source a sales report
8
Perception and Mind (4) Mission Impossible
We cannot judge accurately vertical distance
between curves of varying slope. The eye
sees orthogonal distance.
9
Nothing of this is new ...
Information, that is imperfectly acquired, is
generally as imperfectly retained and a man who
has carefully investigated a printed table,
finds, when done that he has only a very faint
idea of what he has read and that like a figure
imprinted on sand, is soon totally erased and
defaced. The amount of mercantile transactions
on money, and of profit or loss, are capable of
being as easily represented in drawing, as any
part of space, or as the face of a country
though, till now, it has not been attempted.
Upon that principle these charts were made
and, while they give a simple and distinct idea,
they are near perfect accuracy as in any way
useful. On inspecting any of these Charts
attentively, a sufficiently distinctimpression
will be made, to remain unimpaired for a
considerable time, and the idea whichdoes remain
will be simple and complete, at once including
the duration and amount. Playfair, The
Commercial and Political Atlas, 1786
10
Principles (1) Fidelity
Original data should be presented in a way that
will preserve the evidence in the original data
for all predictions assumed to be useful. W
Shewhart
11
Principles (2) Honesty
Visual increase 800(18-2)/2
Lie factor 15800/53
Actual increase 53(27.5-18)/18
source Tufte, The Graphical Display of
Quantitative Information
12
Principles (3a) Sobriety
13
Principles (3b) Sobriety
14
Principles (4) Purpose

• Nothing you do in a data presentation should be
  without your intention.
• Do we need
• Axes?
• Colors and styles?
• Background/Frame?
• Gridlines?
• Should we use
• Points or bars?
• Separate points or points joined by lines?
• Alphabetical or different order?
• Suggestion First turn all color and style
  options off
• Then add in options as needed, at each time
  think
• Why am I doing this?
• What is the purpose?
• For whom?

15
Principles (5) Perspective

• One of the principal objects of theoretical
  research in any department of knowledge is to
  find the point of view from which the subject
  appears in its greatest simplicity.
• Josiah Willard GIBBS, 1881

16
Techniques (1) Visual Grouping (create tokens
for working memory)
Objective At most 4 groups (at any layer).
17
Techniques (2) Proximity(facilitate comparisons)
Put small differences as close together as
possible. Big differences are also visible from a
distance.
18
Techniques (3) Choice of display
dimensions(create focus on whats important)
19
Techniques (4) Matrushka(create hierarchy of
interpretation)

• Data General pattern Departures from the
  general pattern

20
Techniques (5) Small multiples(hierarchy, use
long term memory)
21
General Advice for Graphs and Tables

• When you analyze data and in particular before
  any inferential statistical analysis, make graphs
  and look at them.
• Make time charts if time plays a role
• Add value to your graphs
• if you show a scatterplot and you have a third
  variable, add it using labels, color, or markers,
  on tables add a summary level
• use categorized graphs (same graph type, scale,
  close together)
• minimize ink used for decoration (frames, grids,
  background), focus on the data you want to show
• read and interpret carefully the graphs and
  tables you create, note what you see, note what
  is expected and what is unexpected
• separate what is shared by the data (model) from
  what is individual (residual)
• (in particular for any graph/table you want to
  show to others) think about how it will be
  perceived

22
Graphics Clinic Example
23
Reminder Efficient Design for Perception

• Improve
• work with four tokens in short term memory
• minimize perceptive noise
• focus attention
• minimize acquisition time and distance
• maximize parallel treatment
• maximize accuracte judgement by representing
  quantities by position and length

• Mess up
• require more than four tokens in short term
  memory
• add noise
• divert attention
• separate information which has to be treated
  together
• force sequential treatment
• maximize inaccurate judgement by representing
  quantities by angle, volume and lengths which do
  not share a common axis

24
Messing up a Graph Original
10000.0
Low D
High D
1000.0
high C
Defects
100.0
A
Low C
Low C
10.0
a
b
high C
B
1.0
0.0
10.0
20.0
30.0
40.0
50.0
60.0
70.0
80.0
Color
This graph shows the effect of four experimental
factors A, B, C, and D on two responses, Color
and Defects. A (dashed) always increases
Defects. When D is high(right), A reduces color.
B (solid) reduces both Defects and Color. C and
D show a strong interaction. At high C (bold
arrows), the effect of D (reducing Defects and
increasing Color) is much stronger than at low C
(thin arrows).
25
Break the groups
10000.0
Cd
1000.0
cd
cD
100.0
A
CD
10.0
a
b
B
1.0
0.0
10.0
20.0
30.0
40.0
50.0
60.0
70.0
80.0
26
Add Noise
10000.0
Cd
1000.0
100.0
Defucts
A
cd
cD
CD
10.0
a
b
B
1.0
0.0
10.0
20.0
30.0
40.0
50.0
60.0
70.0
80.0
Color
27
Divert Attention
10000.0
Cd
1000.0
Defucts
100.0
A
cd
cD
CD
10.0
a
b
B
1.0
0.0
10.0
20.0
30.0
40.0
50.0
60.0
70.0
80.0
Color
28
References

• Edward R. Tufte (Graphics Press, Cheshire
  Connecticut)
• The Visual Display of Quantitative Information
• Envisioning Information
• Visual Explanations
• A.S.C. Ehrenberg
• Reading a Table An Example (Applied
  Statistics,1986,35(3) 237-244)
• The Problem of Numeracy (American Statistician,
  1981, 35(2) 67-71)
• Stephen M. Kosslyn
• Elements of Graph Design, 1993, Freeman Co.
• W. S. Cleveland and R. McGill. Graphical
  Perception Theory, Experimentation, and
  Application to the Development of Graphical
  Methods. Journal of the American Statistical
  Association, 79531554, 1984.
• Approache Graphique en Analyze des Données,
  Jean-Paul Valois, Journal de la Societe Francaise
  de Statistique, 141, 43-44.