DATA VISUALIZATION

EXAMPLES and PRINCIPLES

1
 The pictorial representation of data.
 Uses combinations of shapes, colours, lines, numbers,
words and animation.
 Helps understand and interpret data by revealing
implicit patterns and relationships.
 Helps raise new & relevant questions in the context.
 Is often complimented with numerical calculation.
 Combines art and science by bringing aesthetics and
functionality together.

2
3
 ANSCOMBE’S QUARTET
How graphics reveal data

For all four

datasets

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC 4
 ANSCOMBE’S QUARTET
How graphics reveal data

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC 5
 IDENTIFYING THE WILDSHOT
How graphics reveal data

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC 6
 SILLY THEORY SILLY GRAPHIC
Graphics are only as good as what goes into them

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC 7
 Circles (Country’s size), Red vertical line (Population), Yellow
vertical line (Total taxes collected).
 Playfair used this chart to argue for lower taxes in the UK. 8
9
10
11


12
o

13
st th

14
15
 1819-53

What can explain why mortality among soldiers is significantly

more than that among civilians? 16
17
18
 DATA MAP: A lot of data in a small space

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC
19
 DATA MAP: A lot of data in a small space

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC
20
TIME-SPACE GRAPHICS
Shows pollutants’ levels for 2400
spatial locations (2,400 squares of
5 km x 5 km size). In all 28,800
pollutant readings shown, except
for those masked by peaks.

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC
21
TIME-SPACE GRAPHICS
Life of a Japanese Beetle

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC
22
RELATIONAL
GRAPHICS
The scatter plot

 Helps assess causal

relationships
between two
variables, e.g.
cigarette
consumption &
death by lung
cancer.

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC
23
RELATIONAL GRAPHICS
Different laboratories, different scientific results!

o Thermal
conductivity
vs.
Temperature.
o Differences
owing to
differences in
levels of
impurities in
the Cu.

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC 24
RELATIONAL GRAPHICS
When data points themselves become the data

Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC 25
RELATIONAL GRAPHICS
When data points themselves become the data

Varying sizes of white pine seedlings after growing for one season in sand
containing different amounts of calcium, in parts per million.
Source: Tufte, E, (2001), The visual display of quantitative information, Graphic Press LLC 26
 GRAPHICAL EXCELLENCE
 the well-designed presentation of interesting data – a matter of
substance, of statistics and of design.
 consists of complex ideas communicated with clarity, precision
and efficiency.
 aims to give the viewer the greatest number of ideas in the
shortest time with the least ink in the smallest space.
 nearly always multivariate.

 must be used to tell the truth about the data.

27
 GRAPHICAL EXCELLENCE
Graphical displays should
 show the data.
 induce the viewer to think about the substance rather than
about the methodology, graphic design, the technology of
graphic production, or something else.
 avoid distorting what the data have to say.
 present many numbers in a small place, making large data sets
coherent.
 encourage the eye to compare different pieces of data.
 reveal the data at different levels of detail, from a broad
overview to the fine structure.
28