Interactive Data Visualization

04
Visualization Foundations

IDV 2019/2020
Notice

! Author

" João Moura Pires ([email protected])

! This material can be freely used for personal or academic purposes without

any previous authorization from the author, provided that this notice is kept

with.

! For commercial purposes the use of any part of this material requires the

previous authorisation from the author.

Visualization Foundations - 2
Bibliography

! Many examples are extracted and adapted from

" Interactive Data Visualization: Foundations, Techniques, and Applications,

Matthew O. Ward, Georges Grinstein, Daniel Keim, 2015

" Visualization Analysis & Design,

Tamara Munzner, 2015

Visualization Foundations - 3
Our Agenda

Week Subjects Event

1 2-6 Mars Overview
2 9-13 Mars No class
3 16-20 Mars Team registration: Mars 20th
4 23-27Mars
Mars Introduction to Data
5 30-3 April Visualization
6 6-10 April No class - Holliday
7 13-17 April
8 20-24 April Subject Registration: 25 April
9 27-1 May 24th
Visualization Techniques
10 4-8 May
11 11-15 May Paper: May 15th
12 18-22 May
Advanced Topics
13 25-29 May
14 1-5 Jun Students Support TP Implementation: June 5th
15 8-12 Jun Oral Sessions Oral Sessions

Visualization Foundations - 4
Our Agenda

Week Subjects Event

1 2-6 Mars Overview
2 9-13 Mars No class
3 16-20 Mars Team registration: Mars 20th
4 23-27Mars
Mars Introduction to Data
5 30-3 April Visualization
6 6-10 April No class - Holliday
7 13-17 April
8 20-24 April Subject Registration: 25 April
9 27-1 May 24th
Visualization Techniques
10 4-8 May
11 11-15 May Paper: May 15th
12 18-22 May
Advanced Topics
13 25-29 May
14
15
1-5 Jun
8-12 Jun
Students Support
Oral Sessions
TP Implementation: June 5th
Oral Sessions
?

Visualization Foundations - 4
Our Agenda

Week Subjects Event

1 2-6 Mars Overview
2 9-13 Mars No class
3 16-20 Mars Team registration: Mars 20th
4 23-27Mars
Mars Introduction to Data
5 30-3 April Visualization
6 6-10 April No class - Holliday
7 13-17 April
8 20-24 April Subject Registration: 25 April
9 27-1 May 24th
Visualization Techniques
10 4-8 May
11 11-15 May Paper: May 15th
12 18-22 May
Advanced Topics
13 25-29 May
14
15
1-5 Jun
8-12 Jun
Students Support
Oral Sessions
TP Implementation: June 5th
Oral Sessions
?

Visualization Foundations - 4
Our Agenda

Week Subjects Event

1 2-6 Mars Overview
2 9-13 Mars No class
3 16-20 Mars Team registration: Mars 20th
4 23-27Mars
Mars Introduction to Data
5 30-3 April Visualization
6 6-10 April No class - Holliday
7 13-17 April
8 20-24 April Subject Registration: 25 April
9 27-1 May 24th
Visualization Techniques
10 4-8 May
11 11-15 May Paper: May 15th
12 18-22 May
Advanced Topics
13 25-29 May
14
15
1-5 Jun
8-12 Jun
Students Support
Oral Sessions
TP Implementation: June 5th
Oral Sessions
?

Visualization Foundations - 4
 Interactive Data Visualization

Never Forget

Visualization Foundations - 5
What is the core idea of Interactive Data Visualization?

Introduction to Data Visualization - 6

What is the core idea of Interactive Data Visualization?

Map
ping
to V data
isua
l Va
riab
les

Introduction to Data Visualization - 6

What is the core idea of Interactive Data Visualization?

Map
ping
to V data
isua
l Va
riab
les

Question(s) / Task

Introduction to Data Visualization - 6

What is the core idea of Interactive Data Visualization?

Map
ping
to V data
isua
l Va
riab
les

Interactivity

Question(s) / Task

Introduction to Data Visualization - 6

Table of Contents

! The Visualization Process in Detail

! Semiology of Graphical Symbols

! The Eight Visual Variables

! Historical Perspective

Visualization Foundations - 7
 Interactive Data Visualization

The Visualization Process in Detail

Visualization Foundations - 8
 review the visualization pipeline and then discuss various ways to view the
The Visualization
multitudes Process
of techniques in Detail
and systems that have been developed to date.

. Our reference visualization pipeline. (Image modified from [59].)

Visualization Foundations - 9
139
The Visualization Process in Detail

! Data preprocessing and transformation

" Process the raw data into something usable by the visualization system.

− The first part is to make sure that the data are mapped to fundamental data types

− The second step entails dealing with specific application data issues.

! Mapping for visualizations

" Decide on a specific visual representation.

− This requires representation mappings: geometry, color, and sound, for example.

! Rendering transformations.

" The final stage involves mapping from geometry data to the image

− This stage of the pipeline is very dependent on the underlying graphics library.

Visualization Foundations - 10
The Visualization Process in Detail

! Data preprocessing and transformation

" Process the raw data into something usable by the visualization system.

− The first part is to make sure that the data are mapped to fundamental data types

− The second step entails dealing with specific application data issues.

! Mapping for visualizations

" Decide on a specific visual representation.

− This requires representation mappings: geometry, color, and sound, for example.

! Rendering transformations.

" The final stage involves mapping from geometry data to the image

− This stage of the pipeline is very dependent on the underlying graphics library.

Visualization Foundations - 10
Expressiveness and Effectiveness

Visualization Foundations - 11
Expressiveness and Effectiveness

! Expressiveness

" An expressive visualization presents all the information, and only the information

Visualization Foundations - 11
Expressiveness and Effectiveness

! Expressiveness

" An expressive visualization presents all the information, and only the information

" Mexp = The information that we actually display to the user / information we want

to present to the user

" 0 ≤ Mexp ≤ 1.

Visualization Foundations - 11
Expressiveness and Effectiveness

! Expressiveness

" An expressive visualization presents all the information, and only the information

" Mexp = The information that we actually display to the user / information we want

to present to the user

" 0 ≤ Mexp ≤ 1.

" If Mexp = 1, we have ideal expressiveness

Visualization Foundations - 11
Expressiveness and Effectiveness

! Expressiveness

" An expressive visualization presents all the information, and only the information

" Mexp = The information that we actually display to the user / information we want

to present to the user

" 0 ≤ Mexp ≤ 1.

" If Mexp = 1, we have ideal expressiveness

" If the information displayed is less than that desired, then Mexp < 1.

Visualization Foundations - 11
Expressiveness and Effectiveness

! Expressiveness

" An expressive visualization presents all the information, and only the information

" Mexp = The information that we actually display to the user / information we want

to present to the user

" 0 ≤ Mexp ≤ 1.

" If Mexp = 1, we have ideal expressiveness

" If the information displayed is less than that desired, then Mexp < 1.

" If Mexp > 1, we are presenting too much information.

− Expressing additional information is potentially dangerous, because it may not be

correct and may interfere with the interpretation of the essential information.

Visualization Foundations - 11
Expressiveness and Effectiveness

! Effectiveness

" A visualization is effective when it can be interpreted accurately and quickly and

when it can be rendered in a cost-effective manner.

Visualization Foundations - 12
Expressiveness and Effectiveness

! Effectiveness

" A visualization is effective when it can be interpreted accurately and quickly and

when it can be rendered in a cost-effective manner.

" Effectiveness thus measures a specific cost of information perception.

Visualization Foundations - 12
Expressiveness and Effectiveness

! Effectiveness

" A visualization is effective when it can be interpreted accurately and quickly and

when it can be rendered in a cost-effective manner.

" Effectiveness thus measures a specific cost of information perception.

" Meff = 1 / (1 + timeinterpret + timerender).

Visualization Foundations - 12
Expressiveness and Effectiveness

! Effectiveness

" A visualization is effective when it can be interpreted accurately and quickly and

when it can be rendered in a cost-effective manner.

" Effectiveness thus measures a specific cost of information perception.

" Meff = 1 / (1 + timeinterpret + timerender).

" 0 < Meff ≤ 1.

Visualization Foundations - 12
Expressiveness and Effectiveness

! Effectiveness

" A visualization is effective when it can be interpreted accurately and quickly and

when it can be rendered in a cost-effective manner.

" Effectiveness thus measures a specific cost of information perception.

" Meff = 1 / (1 + timeinterpret + timerender).

" 0 < Meff ≤ 1.

" The larger Meff is, the greater the visualization’s effectiveness.

Visualization Foundations - 12
Expressiveness and Effectiveness

! Effectiveness

" A visualization is effective when it can be interpreted accurately and quickly and

when it can be rendered in a cost-effective manner.

" Effectiveness thus measures a specific cost of information perception.

" Meff = 1 / (1 + timeinterpret + timerender).

" 0 < Meff ≤ 1.

" The larger Meff is, the greater the visualization’s effectiveness.

" If Meff is small, then either the interpretation time is very large, or the rendering

time is large.

Visualization Foundations - 12
Expressiveness and Effectiveness

! Effectiveness

" A visualization is effective when it can be interpreted accurately and quickly and

when it can be rendered in a cost-effective manner.

" Effectiveness thus measures a specific cost of information perception.

" Meff = 1 / (1 + timeinterpret + timerender).

" 0 < Meff ≤ 1.

" The larger Meff is, the greater the visualization’s effectiveness.

" If Meff is small, then either the interpretation time is very large, or the rendering

time is large.

" If Meff is large (close to 1), then both the interpretation and the rendering time are

very small.

Visualization Foundations - 12
Expressiveness and Effectiveness

Visualization Foundations - 13
Expressiveness and Effectiveness

Mexp(a) ≈ Mexp (b)

Visualization Foundations - 13
 Expressiveness and Effectiveness

The information in (b) can be interpreted more accurately or more quickly than that in (a) for
some questions. For example, which car has the best mileage?

Visualization Foundations - 14
 Expressiveness and Effectiveness

The information in (b) can be interpreted more accurately or more quickly than that in (a) for
some questions. For example, which car has the best mileage?

However, if we ask which car has the best mileage under $11,000?

Visualization Foundations - 14
Expressiveness and Effectiveness

Visualization Foundations - 15
Expressiveness and Effectiveness

Visualization Foundations - 16
 Interactive Data Visualization

Semiology of Graphical Symbols

Visualization Foundations - 17
Semiology of Graphical Symbols

Visualization Foundations - 18
Semiology of Graphical Symbols

! The science of graphical symbols and marks is called semiology.

Visualization Foundations - 18
Semiology of Graphical Symbols

! The science of graphical symbols and marks is called semiology.

! Every possible construction in the Euclidean plane is a graphical

representation made up of graphical symbols (diagrams, networks, maps,

plots, and other common visualizations).

Visualization Foundations - 18
Semiology of Graphical Symbols

! The science of graphical symbols and marks is called semiology.

! Every possible construction in the Euclidean plane is a graphical

representation made up of graphical symbols (diagrams, networks, maps,

plots, and other common visualizations).

! Semiology uses the qualities of the plane and objects on the plane to produce

similarity features, ordering features, and proportionality features of the data

that are visible for human consumption.

Visualization Foundations - 18
Semiology of Graphical Symbols

! Discovery of relations or patterns occurs through a mapping between any

relationship of the graphic symbols and the data that these symbols

represent.

Visualization Foundations - 19
Semiology of Graphical Symbols

! Discovery of relations or patterns occurs through a mapping between any

relationship of the graphic symbols and the data that these symbols

represent.

" any pattern on the screen must imply a pattern in the data.

Visualization Foundations - 19
Semiology of Graphical Symbols

! Discovery of relations or patterns occurs through a mapping between any

relationship of the graphic symbols and the data that these symbols

represent.

" any pattern on the screen must imply a pattern in the data.

− If it does not, then it is an artifact of the selected representation (and is

disturbing).

Visualization Foundations - 19
Semiology of Graphical Symbols

! Discovery of relations or patterns occurs through a mapping between any

relationship of the graphic symbols and the data that these symbols

represent.

" any pattern on the screen must imply a pattern in the data.

− If it does not, then it is an artifact of the selected representation (and is

disturbing).

" Similarly, any perceived pattern variation in the graphic or symbol cognitively

implies such a similar variation in the data.

Visualization Foundations - 19
Semiology of Graphical Symbols

! Discovery of relations or patterns occurs through a mapping between any

relationship of the graphic symbols and the data that these symbols

represent.

" any pattern on the screen must imply a pattern in the data.

− If it does not, then it is an artifact of the selected representation (and is

disturbing).

" Similarly, any perceived pattern variation in the graphic or symbol cognitively

implies such a similar variation in the data.

" Any perceived order in graphic symbols is directly correlated with a perceived

corresponding order between the data, and vice versa

Visualization Foundations - 19
Features of Graphics

! Graphics have three (or more) dimensions.

Visualization Foundations - 20
Features of Graphics

! Graphics have three (or more) dimensions.

! Every point of the graphic can be interpreted as a relation between a position

in x and a position in y. The points vary in size, providing a third dimension or

variable to interpret.

Visualization Foundations - 20
Rules of Graphics

Visualization Foundations - 21
Rules of Graphics

! The aim of a graphic is to discover groups or orders in x, and groups or

orders in y, that are formed on z-values;

Visualization Foundations - 21
Rules of Graphics

! The aim of a graphic is to discover groups or orders in x, and groups or

orders in y, that are formed on z-values;

Visualization Foundations - 21
Rules of Graphics

! The aim of a graphic is to discover groups or orders in x, and groups or

orders in y, that are formed on z-values;

! (x, y, z)-construction enables in all cases the discovery of these groups;

Visualization Foundations - 22
Rules of Graphics

! The aim of a graphic is to discover groups or orders in x, and groups or

orders in y, that are formed on z-values;

! (x, y, z)-construction enables in all cases the discovery of these groups;

! Within the (x,y,z)-construction, permutations and classifications solve the

problem of the upper level of information;

Visualization Foundations - 22
Rules of Graphics

! The aim of a graphic is to discover groups or orders in x, and groups or

orders in y, that are formed on z-values;

! (x, y, z)-construction enables in all cases the discovery of these groups;

! Within the (x,y,z)-construction, permutations and classifications solve the

problem of the upper level of information;

! Every graphic with more than three factors that differs from the (x, y, z)-

construction destroys the unity of the graphic and the upper level of

information;

Visualization Foundations - 22
Rules of Graphics

! The aim of a graphic is to discover groups or orders in x, and groups or

orders in y, that are formed on z-values;

! (x, y, z)-construction enables in all cases the discovery of these groups;

! Within the (x,y,z)-construction, permutations and classifications solve the

problem of the upper level of information;

! Every graphic with more than three factors that differs from the (x, y, z)-

construction destroys the unity of the graphic and the upper level of

information;

! Pictures must be read and understood by the human.

Visualization Foundations - 22
 Interactive Data Visualization

The Eight Visual Variables

Visualization Foundations - 23
Spatial arrangement of marks

Visualization Foundations - 24
Spatial arrangement of marks

! For the most part, all graphic primitives will be termed marks.

Visualization Foundations - 24
Spatial arrangement of marks

! For the most part, all graphic primitives will be termed marks.

! One way to encode data for display is to map different data values to different

marks and their attributes.

Visualization Foundations - 24
Spatial arrangement of marks

! For the most part, all graphic primitives will be termed marks.

! One way to encode data for display is to map different data values to different

marks and their attributes.

! However, marks by themselves do not define informative displays, since all the

marks would simply obscure all previously drawn marks; it is only through the

spatial arrangement of marks that informative displays are created.

Visualization Foundations - 24
Spatial arrangement of marks

! For the most part, all graphic primitives will be termed marks.

! One way to encode data for display is to map different data values to different

marks and their attributes.

! However, marks by themselves do not define informative displays, since all the

marks would simply obscure all previously drawn marks; it is only through the

spatial arrangement of marks that informative displays are created.

! Once the layout and types of marks are specified, then additional graphical

properties can be applied to each mark.

Visualization Foundations - 24
Spatial arrangement of marks

! For the most part, all graphic primitives will be termed marks.

! One way to encode data for display is to map different data values to different

marks and their attributes.

! However, marks by themselves do not define informative displays, since all the

marks would simply obscure all previously drawn marks; it is only through the

spatial arrangement of marks that informative displays are created.

! Once the layout and types of marks are specified, then additional graphical

properties can be applied to each mark.

" Marks can vary in size, can be displayed using different colors, and can be

mapped to different orientations, all of which can be driven by data to convey

information.

Visualization Foundations - 24
Eight visual variables

! eight visual variables:

" position,

" shape,
It is important to remember that the
" size,
result will be an image that is to be
" brightness,
interpreted by the human visual
" color,
system
" orientation,

" texture,

" motion

Visualization Foundations - 25
Eight visual variables

! eight visual variables:

" position,

" shape,

" size, The first and The first and most

" brightness, important visual variable is that
" color, of position is that of position

" orientation,

" texture,

" motion

Visualization Foundations - 26
Eight visual variables: Position

! The first and most important visual variable is that of position, the placement of

representative graphics within some display space, be it one-, two-, or three-

dimensional.

Visualization Foundations - 27
Eight visual variables: Position

! The first and most important visual variable is that of position, the placement of

representative graphics within some display space, be it one-, two-, or three-

dimensional.

! Spatial arrangement of graphics is the first step in reading a visualization:

" The maximization of the spread of representational graphics throughout the

display space maximizes the amount of information communicated, to some

degree.

Visualization Foundations - 27
Eight visual variables: Position

! The first and most important visual variable is that of position, the placement of

representative graphics within some display space, be it one-, two-, or three-

dimensional.

! Spatial arrangement of graphics is the first step in reading a visualization:

" The maximization of the spread of representational graphics throughout the

display space maximizes the amount of information communicated, to some

degree.

" Worst case positioning scheme maps all graphics to the exact same position

Visualization Foundations - 27
Eight visual variables: Position

! The first and most important visual variable is that of position, the placement of

representative graphics within some display space, be it one-, two-, or three-

dimensional.

! Spatial arrangement of graphics is the first step in reading a visualization:

" The maximization of the spread of representational graphics throughout the

display space maximizes the amount of information communicated, to some

degree.

" Worst case positioning scheme maps all graphics to the exact same position

" Best positioning scheme maps each graphic to unique positions, such that all the

graphics can be seen with no overlaps.

Visualization Foundations - 27
Eight visual variables: Screen resolution

Visualization Foundations - 28
Eight visual variables: Screen resolution

Visualization Foundations - 28
Eight visual variables: Screen resolution

Visualization Foundations - 29
Eight visual variables: Screen resolution

1 764 000
Pixels

Visualization Foundations - 29
Eight visual variables: Screen resolution

! 450.710 geo-referenced accidents between 2001 and 2013 in US

Visualization Foundations - 30
Eight visual variables: Screen resolution

! Preprocessed data: 53% of items from original data set

Visualization Foundations - 31
53%
 Eight
3. The visual
Eight Visual Variablesvariables: Position - Scales 149

(a) (b)

Figure 4.7. Example visualizations: (a) using position to convey information. Displayed here
is the minimum price versus the maximum price for cars with a 1993 model year.
The spread of points appears to indicate a linear relationship between minimum
and maximum price; (b) another visualization using a different set of variables.
This figure compares minimum price with engine size for the 1993 cars data set.
Unlike (a), there does not appear to be a strong relationship between these two
variables.
Visualization Foundations - 33
Eight visual variables: Position - Scales

Linear
Scale

Linear Scale
Visualization Foundations - 34
Eight visual variables: Position - Scales

Log Scale Linear Scale

Visualization Foundations - 35
Eight visual variables: Mark (or shape)

Visualization Foundations - 36
Eight visual variables: Mark (or shape)

! The second visual variable is the mark or shape: points, lines, areas, volumes, and

their compositions.

Visualization Foundations - 36
 Eight visual variables: Mark (or shape)

! The second visual variable is the mark or shape: points, lines, areas, volumes, and

their compositions.
50 4. Visualization Foundations
! Marks are graphic primitives that represent data:

Figure 4.8. Several examples of different marks or glyphs that can be used.

4.3.2 Mark
" When using marks, it is important to consider
The second visual variable is the mark or shape: points, lines, areas, volumes,
how well one mark can be differentiated from
and their compositions. Marks are graphic primitives that represent data.
For example, both visualizations in Figure 4.7 use the default point to display
other marks
individual values. Any graphical object can be used as a mark, including
symbols, letters, and words (see Figure 4.8). When working purely with
marks, it is important not to consider differences in sizes, shades of intensity,
or orientation, as these are additional visual variables that will be described
later.
When using marks, it is important to consider how well one mark can
be differentiated from other marks. Within a single visualization there can
be hundreds or thousands of marks to observe; therefore, we try not to se-
lect marks that are too similar. For example, a set of marks that provides
easy reading is shown in Figure 4.8 and used in a scatterplot in Figure 4.9. Visualization Foundations - 36
 Eight visual variables: Mark (or shape)

! The second visual variable is the mark or shape: points, lines, areas, volumes, and

their compositions.
Tableau
50 4. Visualization Foundations
! Marks are graphic primitives that represent data:

Figure 4.8. Several examples of different marks or glyphs that can be used.

4.3.2 Mark
" When using marks, it is important to consider
The second visual variable is the mark or shape: points, lines, areas, volumes,
how well one mark can be differentiated from
and their compositions. Marks are graphic primitives that represent data.
For example, both visualizations in Figure 4.7 use the default point to display
other marks
individual values. Any graphical object can be used as a mark, including
symbols, letters, and words (see Figure 4.8). When working purely with
marks, it is important not to consider differences in sizes, shades of intensity,
or orientation, as these are additional visual variables that will be described
later.
When using marks, it is important to consider how well one mark can
be differentiated from other marks. Within a single visualization there can
be hundreds or thousands of marks to observe; therefore, we try not to se-
lect marks that are too similar. For example, a set of marks that provides
easy reading is shown in Figure 4.8 and used in a scatterplot in Figure 4.9. Visualization Foundations - 36
 Eight visual variables: Mark (or shape)

! The second visual variable is the mark or shape: points, lines, areas, volumes, and

their compositions.
Tableau
50 4. Visualization Foundations
! Marks are graphic primitives that represent data:

Figure 4.8. Several examples of different marks or glyphs that can be used.

4.3.2 Mark
" When using marks, it is important to consider
The second visual variable is the mark or shape: points, lines, areas, volumes,
how well one mark can be differentiated from
and their compositions. Marks are graphic primitives that represent data.
For example, both visualizations in Figure 4.7 use the default point to display
other marks
individual values. Any graphical object can be used as a mark, including
symbols, letters, and words (see Figure 4.8). When working purely with
marks, it is important not to consider differences in sizes, shades of intensity,
or orientation, as these are additional visual variables that will be described
later.
When using marks, it is important to consider how well one mark can
be differentiated from other marks. Within a single visualization there can
be hundreds or thousands of marks to observe; therefore, we try not to se-
lect marks that are too similar. For example, a set of marks that provides
easy reading is shown in Figure 4.8 and used in a scatterplot in Figure 4.9. Visualization Foundations - 36
Eight visual variables: Mark (or shape)

Visualization Foundations - 37
 Interactive Data Visualization

10 Min Interval

Visualization Foundations - 38
Eight visual variables

! The position and marks, are required to define a visualization. Without these

two variables there would not be much to see !

! The remaining visual variables affect the way individual representations are

displayed;

! These are the graphical properties of marks other than their shape.

Visualization Foundations - 39
 4.3. The Eight Visual Variables 1
Eight visual variables: Size

Figure 4.10. Example sizes to encode data.

Another is the set (T and L) or (+ and −), that harnesses our perceptu
systems (see examples in Chapter 3). The goal is to be able to easily dist
guish between different marks quickly, while maintaining an overall view
the projected data space. Also, different mark shapes in a given visuali
tion must have similar area and complexity, to avoid visually emphasizi
one or more of them inadvertently.

4.3.3 Size (Length, Area, and Volume)

The previous two visual variables, position and marks, are required to defi
a visualization. Without these two variables there would not be much to s
The remaining visual variables affect the way individual representations a
displayed; these are the graphical properties of marks other than their sha
Visualization
The third visual variable and first graphic propertyFoundations
is size.- 40Size d
termines how small or large a mark will be drawn (see Figure 4.10). S
 4.3. The Eight Visual Variables 1
Eight visual variables: Size

Figure 4.10. Example sizes to encode data.

! Size easily maps to interval and continuous data variables, because that property
Another is the set (T and L) or (+ and −), that harnesses our perceptu
supports gradual increments over some range.
systems (see examples in Chapter 3). The goal is to be able to easily dist
guish between different marks quickly, while maintaining an overall view
the projected data space. Also, different mark shapes in a given visuali
tion must have similar area and complexity, to avoid visually emphasizi
one or more of them inadvertently.

4.3.3 Size (Length, Area, and Volume)

The previous two visual variables, position and marks, are required to defi
a visualization. Without these two variables there would not be much to s
The remaining visual variables affect the way individual representations a
displayed; these are the graphical properties of marks other than their sha
Visualization
The third visual variable and first graphic propertyFoundations
is size.- 40Size d
termines how small or large a mark will be drawn (see Figure 4.10). S
 4.3. The Eight Visual Variables 1
Eight visual variables: Size

Figure 4.10. Example sizes to encode data.

! Size easily maps to interval and continuous data variables, because that property
Another is the set (T and L) or (+ and −), that harnesses our perceptu
supports gradual increments over some range.
systems (see examples in Chapter 3). The goal is to be able to easily dist
! It is more difficult to distinguish
guish between
between different marks
marks of near
quickly, similar
while size, and an
maintaining thus size view
overall
the projected data space. Also, different mark shapes in a given visuali
can only support categories with very small cardinality.
tion must have similar area and complexity, to avoid visually emphasizi
one or more of them inadvertently.

4.3.3 Size (Length, Area, and Volume)

The previous two visual variables, position and marks, are required to defi
a visualization. Without these two variables there would not be much to s
The remaining visual variables affect the way individual representations a
displayed; these are the graphical properties of marks other than their sha
Visualization
The third visual variable and first graphic propertyFoundations
is size.- 40Size d
termines how small or large a mark will be drawn (see Figure 4.10). S
 4.3. The Eight Visual Variables 1
Eight visual variables: Size

Figure 4.10. Example sizes to encode data.

! Size easily maps to interval and continuous data variables, because that property
Another is the set (T and L) or (+ and −), that harnesses our perceptu
supports gradual increments over some range.
systems (see examples in Chapter 3). The goal is to be able to easily dist
! It is more difficult to distinguish
guish between
between different marks
marks of near
quickly, similar
while size, and an
maintaining thus size view
overall
the projected data space. Also, different mark shapes in a given visuali
can only support categories with very small cardinality.
tion must have similar area and complexity, to avoid visually emphasizi
one or more
! A confounding problem withofusing
themsize
inadvertently.
is the type of mark.

" For points, lines, and curves the use of size works well
4.3.3 Size (Length, Area, and Volume)
" when marks are represented with graphics that contain sufficient area, the
The previous two visual variables, position and marks, are required to defi
quantitative aspects of size fall, and the differences between marks becomes more
a visualization. Without these two variables there would not be much to s
qualitative. The remaining visual variables affect the way individual representations a
displayed; these are the graphical properties of marks other than their sha
The third visual variable and first graphic Visualization
propertyFoundations
is size.- 40Size d
termines how small or large a mark will be drawn (see Figure 4.10). S
 4.3. The Eight Visual Variables 1
Eight visual variables: Size

Figure 4.10. Example sizes to encode data.

! Size easily maps to interval and continuous data variables, because that property
Another is the set (T and L) or (+ and −), that harnesses our perceptu
supports gradual increments over some range.
systems (see examples in Chapter 3). The goal is to be able to easily dist
! It is more difficult to distinguish
guish between
between different marks
marks of near
quickly, similar
while size, and an
maintaining thus size view
overall
the projected data space. Also, different mark shapes in a given visuali
can only support categories with very small cardinality.
tion must have similar area and complexity, to avoid visually emphasizi
one or more
! A confounding problem withofusing
themsize
inadvertently.
is the type of mark.

" For points, lines, and curves the use of size works well
4.3.3 Size (Length, Area, and Volume) Stevens’ Law
" when marks are represented with graphics that contain sufficient area, the
The previous two visual variables, position and marks, are required to defi
quantitative aspects of size fall, and the differences between marks becomes more
a visualization. Without these two variables there would not be much to s
qualitative. The remaining visual variables affect the way individual representations a
displayed; these are the graphical properties of marks other than their sha
The third visual variable and first graphic Visualization
propertyFoundations
is size.- 40Size d
termines how small or large a mark will be drawn (see Figure 4.10). S
Eight visual variables: Size

3. Human Perception and Information Processing

Illustration of Stevens’ Law. The size ratio for each pair is 1:4. This magnitude
is readily apparent in the lines, but it is easily underestimated in the squares and
cubes.

This seems to support the idea that bar charts and scatterplots are ef-
fective tools for communicating quantitative data, as they both depend on
Visualization Foundations - 41
position along a common scale. It also suggests that pie charts are probably
Eight visual variables: Size

3. Human Perception and Information Processing

Stevens’ Law

Illustration of Stevens’ Law. The size ratio for each pair is 1:4. This magnitude
is readily apparent in the lines, but it is easily underestimated in the squares and
cubes.

This seems to support the idea that bar charts and scatterplots are ef-
fective tools for communicating quantitative data, as they both depend on
Visualization Foundations - 41
position along a common scale. It also suggests that pie charts are probably
 4. Visualization Foundations
Eight visual variables: Size

This is a visualization of the 1993 car models data set, showing engine size versus
fuel tank capacity. Size is mapped to maximum price charged.

Visualization Foundations - 42
to provide relative difference for large interval and continuous data vari-
Eight visual variables: Brightness (ou luminance)

! Brightness is the second visual variable used to modify marks to encode additional

data variables.

Visualization Foundations - 43
Eight visual variables: Brightness (ou luminance)

! Brightness is the second visual variable used to modify marks to encode additional

data variables.

! While it is possible to use the complete numerical range of brightness values, human

perception cannot distinguish between all pairs of brightness values.

Visualization Foundations - 43
Eight visual variables: Brightness (ou luminance)

! Brightness is the second visual variable used to modify marks to encode additional

data variables.

! While it is possible to use the complete numerical range of brightness values, human

perception cannot distinguish between all pairs of brightness values.

! Brightness can be used to provide relative difference for large interval and

continuous data variables,

Visualization Foundations - 43
Eight visual variables: Brightness (ou luminance)

! Brightness is the second visual variable used to modify marks to encode additional

data variables.

! While it is possible to use the complete numerical range of brightness values, human

perception cannot distinguish between all pairs of brightness values.

! Brightness can be used to provide relative difference for large interval and

continuous data variables,

! or for mark distinction for marks drawn using a reduced sampled brightness scale.

Visualization Foundations - 43
t Visual Variables 153
Eight visual variables: Brightness (ou luminance)

Another visualization of the 1993 car models data set, this time illustrating the use
of brightness to convey car width (the darker the points, the wider the vehicle).

Visualization Foundations - 44
Eight visual variables: Color

! Color maps are useful for handling both interval and continuous data variables, since

a color map is generally defined as a continuous range of hue and saturation values

Visualization Foundations - 45
Eight visual variables: Color

! When working with categorical or interval data with very low cardinality, it is generally

acceptable to manually select colors for individual data values, which are selected to

optimize the distinction between data types

Visualization Foundations - 46
Eight visual variables: Color

Visualization Foundations - 47
Eight visual variables: Color

! Check and try with: www.colorbrewer2.org

Visualization Foundations - 48
Eight visual variables: Orientation

! Orientation is a principal graphic component behind iconographic stick figure

displays, and is tied directly to preattentive vision.

Visualization Foundations - 54
Eight visual variables: Orientation

! Orientation is a principal graphic component behind iconographic stick figure

displays, and is tied directly to preattentive vision.

! The best marks for using orientation are those with a natural single axis; the graphic

exhibits symmetry about a major axis.

Visualization Foundations - 54
Eight visual variables: Orientation

Visualization Foundations - 55
Eight visual variables: Texture

! Texture can be considered as a combination of many of the other visual variables,

including marks (texture elements), color (associated with each pixel in a texture

region), and orientation (conveyed by changes in the local color).

Visualization Foundations - 56
Eight visual variables: Texture

! Texture can be considered as a combination of many of the other visual variables,

including marks (texture elements), color (associated with each pixel in a texture

region), and orientation (conveyed by changes in the local color).

! Texture is most commonly

associated with a polygon,

region, or surface.

Visualization Foundations - 56
Eight visual variables: Texture

Visualization Foundations - 57
Eight visual variables: Motion

! Motion can be associated with any of the other visual variables, since the way a

variable changes over time can convey more information.

Visualization Foundations - 58
Eight visual variables: Motion

! Motion can be associated with any of the other visual variables, since the way a

variable changes over time can convey more information.

! One common use of motion is in varying the speed at which a change is occurring

(such as position change or flashing, which can be seen as changing the opacity).

Visualization Foundations - 58
Eight visual variables: Motion

! Motion can be associated with any of the other visual variables, since the way a

variable changes over time can convey more information.

! One common use of motion is in varying the speed at which a change is occurring

(such as position change or flashing, which can be seen as changing the opacity).

! The other aspect of motion is in the direction for position, this can be up, down, left,

right, diagonal, or basically any slope, while for other variables it can be larger/

smaller, brighter/dimmer, steeper/shallower angles, and so on.

Visualization Foundations - 58
Effects of Visual Variables

Visualization Foundations - 59
Effects of Visual Variables

! Selective visual variables:

" After coding with such variables, different data values are

spontaneously divided by the human into distinguished groups (e.g.,

for visualizing nominal values).

Visualization Foundations - 59
Effects of Visual Variables

! Selective visual variables:

" After coding with such variables, different data values are

spontaneously divided by the human into distinguished groups (e.g.,

for visualizing nominal values).

! Associative visual variables:

" All factors have same visibility (e.g., for visualizing nominal values).

Visualization Foundations - 59
Effects of Visual Variables

! Selective visual variables:

" After coding with such variables, different data values are

spontaneously divided by the human into distinguished groups (e.g.,

for visualizing nominal values).

! Associative visual variables:

" All factors have same visibility (e.g., for visualizing nominal values).

! Ordinal visual variables:

" After coding with such variables, different data values are

spontaneously ordered by the human into distinguished groups (e.g.,

for visualizing ordinal and quantitative data).

Visualization Foundations - 59
Effects of Visual Variables

! Check the slides by Sheelagh Carpendale, University of Calgary

" https://pages.cpsc.ucalgary.ca/~saul/hci_topics/pdf_files/visual-variables.pdf

! For each graphic attribute evaluates its use for each visual variable:

Visualization Foundations - 60
Effects of Visual Variables

! Check the slides by Sheelagh Carpendale, University of Calgary

" https://pages.cpsc.ucalgary.ca/~saul/hci_topics/pdf_files/visual-variables.pdf

! For each graphic attribute evaluates its use for each visual variable:

" selective (is a change enough to allow us to select it from a group?)

Visualization Foundations - 60
Effects of Visual Variables

! Check the slides by Sheelagh Carpendale, University of Calgary

" https://pages.cpsc.ucalgary.ca/~saul/hci_topics/pdf_files/visual-variables.pdf

! For each graphic attribute evaluates its use for each visual variable:

" selective (is a change enough to allow us to select it from a group?)

" associative (is a change enough to allow us to perceive them as a group?)

Visualization Foundations - 60
Effects of Visual Variables

! Check the slides by Sheelagh Carpendale, University of Calgary

" https://pages.cpsc.ucalgary.ca/~saul/hci_topics/pdf_files/visual-variables.pdf

! For each graphic attribute evaluates its use for each visual variable:

" selective (is a change enough to allow us to select it from a group?)

" associative (is a change enough to allow us to perceive them as a group?)

" quantitative (is there a numerical reading obtainable from changes in this

variable?)

Visualization Foundations - 60
Effects of Visual Variables

! Check the slides by Sheelagh Carpendale, University of Calgary

" https://pages.cpsc.ucalgary.ca/~saul/hci_topics/pdf_files/visual-variables.pdf

! For each graphic attribute evaluates its use for each visual variable:

" selective (is a change enough to allow us to select it from a group?)

" associative (is a change enough to allow us to perceive them as a group?)

" quantitative (is there a numerical reading obtainable from changes in this

variable?)

" order (are changes in this variable perceived as ordered?)

Visualization Foundations - 60
Effects of Visual Variables

! Check the slides by Sheelagh Carpendale, University of Calgary

" https://pages.cpsc.ucalgary.ca/~saul/hci_topics/pdf_files/visual-variables.pdf

! For each graphic attribute evaluates its use for each visual variable:

" selective (is a change enough to allow us to select it from a group?)

" associative (is a change enough to allow us to perceive them as a group?)

" quantitative (is there a numerical reading obtainable from changes in this

variable?)

" order (are changes in this variable perceived as ordered?)

" length (across how many changes in this variable are distinctions

perceptible?)

Visualization Foundations - 60
Effects of Visual Variables

! Check the slides by Sheelagh Carpendale, University of Calgary

" https://pages.cpsc.ucalgary.ca/~saul/hci_topics/pdf_files/visual-variables.pdf

! For each graphic attribute evaluates its use for each visual variable:

" selective (is a change enough to allow us to select it from a group?)

" associative (is a change enough to allow us to perceive them as a group?)

" quantitative (is there a numerical reading obtainable from changes in this

variable?)

" order (are changes in this variable perceived as ordered?)

" length (across how many changes in this variable are distinctions

perceptible?)

Visualization Foundations - 60
Effects of Visual Variables (by Sheelagh Carpendale)

Visualization Foundations - 61
Effects of Visual Variables (by Sheelagh Carpendale)

Visualization Foundations - 62
Effects of Visual Variables (by Sheelagh Carpendale)

Visualization Foundations - 63
Effects of Visual Variables (by Sheelagh Carpendale)

(Brightness)

Visualization Foundations - 64
Effects of Visual Variables (by Sheelagh Carpendale)

Visualization Foundations - 65
Effects of Visual Variables (by Sheelagh Carpendale)

Visualization Foundations - 66
Effects of Visual Variables (by Sheelagh Carpendale)

Visualization Foundations - 67
Effects of Visual Variables (by Sheelagh Carpendale)

Visualization Foundations - 68
Effects of Visual Variables (by Sheelagh Carpendale)

! Check the slides by Sheelagh Carpendale, University of Calgary

" https://pages.cpsc.ucalgary.ca/~saul/hci_topics/pdf_files/visual-variables.pdf

! For each graphic attribute evaluates its use for each visual variable:

" selective (is a change enough to allow us to select it from a group?)

" associative (is a change enough to allow us to perceive them as a group?)

" quantitative (is there a numerical reading obtainable from changes in this

variable?)

" order (are changes in this variable perceived as ordered?)

" length (across how many changes in this variable are distinctions

perceptible?)

Visualization Foundations - 69
 Interactive Data Visualization

10 Min Interval

Visualization Foundations - 70
 Interactive Data Visualization

Marks and Channels by Tamara Munzner

Visualization Foundations - 71
Channel
102 Rankings 5. Marks and Channels

Channels: Expressiveness Types and Effectiveness Ranks

Magnitude Channels: Ordered Attributes Identity Channels: Categorical Attributes

Position on common scale Spatial region

Position on unaligned scale Color hue

Length (1D size) Motion

Tilt/angle Shape

Area (2D size)

Depth (3D position)

Color luminance

Color saturation

Curvature

Volume (3D size)

Figure 5.6. Channels ranked by effectiveness according to data and channel type. Ordered data should be shown
with the magnitude channels, and categorical data with the identity channels.

Visualization Foundations - 72
! The limitations and ben- types. This primacy of spatial position applies only to 2D positions
efits of 3D are covered in in the plane; 3D depth is a much lower-ranked channel. These
Channel
102 Rankings 5. Marks and Channels

Channels: Expressiveness Types and Effectiveness Ranks

Magnitude Channels: Ordered Attributes Identity Channels: Categorical Attributes

Position on common scale Spatial region

Position on unaligned scale Color hue

Length (1D size) Motion

Tilt/angle Shape

Area (2D size)

Depth (3D position)

Color luminance

Color saturation

Curvature

Volume (3D size)

Figure 5.6. Channels ranked by effectiveness according to data and channel type. Ordered data should be shown
with the magnitude channels, and categorical data with the identity channels.

Visualization Foundations - 73
! The limitations and ben- types. This primacy of spatial position applies only to 2D positions
efits of 3D are covered in in the plane; 3D depth is a much lower-ranked channel. These
Accuracy 5. Marks and Channels

Figure 5.7. Stevens showed that the apparent magnitude of all sensory channels
follows a power law S = I n , where some sensations are perceptually magnified
compared with their objective intensity (when n > 1) and some compressed (when
n < 1). Length perception is completely accurate, whereas area is compressed
and saturation is magnified. Data from Stevens [Stevens 75, p. 15].

Visualization
brightness results in a perception that is considerably Foundations -
less than 74
twice as bright. The superlinear phenomena are magnified: dou-
Error rates (Cleveland and McGill [Cleveland and McGill 84a]. After [Heer and Bostock])
5.5. Channel Effectiveness 105

Cleveland & McGill’s Results

Positions
1.0 1.5 2.0 2.5 3.0
Log Error

Crowdsourced Results

Angles

Circular
areas

Rectangular
areas
(aligned or in a
treemap)

1.0 1.5 2.0 2.5 3.0

Log Error

Visualization
Figure 5.8. Error rates across visual channels, with recent crowdsourced results replicating and Foundations
extending seminal - 75
work from Cleveland and McGill [Cleveland and McGill 84a]. After [Heer and Bostock 10, Figure 4].
 Cleveland & McGill’s Results

Positions
1.0 1.5 2.0 2.5 3.0
Log Error

Crowdsourced Results

Angles

Circular
areas

Rectangular
areas
(aligned or in a
treemap)

1.0 1.5 2.0 2.5 3.0

Log Error
Discriminability
5.5. Channel Effectiveness 10

Figure 5.9. Linewidth has a limited number of discriminable bins.

Visualization Foundations - 77
is obvious that the third channel precludes the use of the first two.
Separability 5.5.Marks
Marksand
andChannels
Channels

Position
Position Size
Size Width
Width Red
Red
Hue (Color)
Hue (Color) Hue
Hue(Color)
(Color) Height
Height Green
Green

Fully
Fully separable
separable Someinterference
Some interference Some/significant
Some/significant Major
Majorinterference
interference
interference
interference

Figure 5.10. Pairs of visual channels fall along a continuum from fully separable
Figure 5.10. Pairs of visual channels fall along a continuum from fully separable
to intrinsically integral. Color and location are separable channels well suited to
to intrinsically integral. Color and location are separable channels well suited to
encode different data attributes for two different groupings that can be selectively
encode different
attended data attributes
to. However, for two
size interacts withdifferent
hue, whichgroupings
is harderthat can be selectively
to perceive for small
attended
objects.to.TheHowever, size
horizontal interacts
size and andwith hue,size
vertical which is harder
channels to perceive for
are automatically small
fused
objects.
into anThe horizontal
integrated size andofand
perception vertical
area, sizethree
yielding channels are automatically
groups. Attempts to codefused
intoseparate
an integrated perception
information along theof red
area,
andyielding
green axesthree
of groups.
the RGB Attempts
color space to fail,
code
separate
becauseinformation along the
we simply perceive red
four and green
different hues. axes
After of the 13,
[Ware RGB color5.23].
Figure space fail,
because we simply perceive four different hues. After [Ware 13, Figure 5.23].
Visualization Foundations - 78
The third example shows an integral pair. Encoding one vari-
 Interactive Data Visualization

Historical Perspective

Visualization Foundations - 79
Historical Perspective

! Bertin (1967) Semiology of Graphics

! Mackinlay (1986) APT

! Bergeron and Grinstein (1989) Visualization Reference Model

! Wehrend and Lewis (1990)

! Robertson (1990) Natural Scene Paradigm

! Roth (1991) Visage and SAGE

! Casner (1991) BOZ

! Beshers and Feiner (1992) AutoVisual

Visualization Foundations - 80
Historical Perspective

! Senay and Ignatius (1994) VISTA

! Hibbard (1994) Lattice Model

! Golovchinsky (1995) AVE

! Card, Mackinlay, and Shneiderman (1999) Spatial Substrate

! Kamps (1999) EAVE

! Wilkinson (1999) Grammar of Graphics

! Hoffman (2000) Table Visualizations

Visualization Foundations - 81
Historical Perspective

! In 1967, Jacques Bertin, possibly the most important figure in

visualization theory, published his Sémiologie Graphique.

Visualization Foundations - 82
Historical Perspective

! Mackinlay (1986) introduced a design for an automated graphical

presentation designer of relational information, named APT (A

Presentation Tool)

! Mackinlay went on to describe graphical languages, defining graphical

presentations as sentences of these languages. Two graphic design

criteria: expressiveness criterion, the effectiveness criterion,

! The important aspect of Mackinlay’s work pertains to his composition

algebra, a collection of primitive graphic languages and composition

operators that can form complex presentations.

Visualization Foundations - 83
Historical Perspective

Visualization Foundations - 84
Keller and Keller (1994) Taxonomy of Visualization Goals

! Task list

" identify: establish characteristics by which an object is recognizable

" locate: ascertain the position (absolute or relative);

" distinguish: recognize as distinct or different (identification is not needed);

" categorize: place into divisions or classes;

" cluster: group similar objects

" rank: assign an order or position relative to other objects

" compare: notice similarities and differences;

" associate: link or join in a relationship that may or may not be of the same type;

" correlate: establish a direct connection, such as causal or reciprocal.

Visualization Foundations - 85
 Interactive Data Visualization

Further Reading and Summary

Q&A

Visualization Foundations - 86
Further Reading
! Pag 139 - 180 from Interactive Data Visualization: Foundations, Techniques, and
Applications, Matthew O. Ward, Georges Grinstein, Daniel Keim, 2015

! Pag 42 - 64 from Visualization Analysis & Design, Tamara Munzner

! Check the slides by Sheelagh Carpendale, University of Calgary

− https://pages.cpsc.ucalgary.ca/~saul/hci_topics/pdf_files/visual-variables.pdf

Further Reading and Summary Visualization Foundations - 87

What you should know

! The Visualization Process

! Expressiveness and Effectiveness

! The fundamental ideas of Semiology of Graphical Symbols

! data -> (x, y, z*)

! The eight visual variables(VV)

! position, shape - Why they are the most important !

! the others VVs

! Effects of Visual Variables

! selective, associative, quantitative, order

! Tasks list(s)

! Why it is important to consider a task; Why it is important to consider a taxonomy

Visualization Foundations - 88
 Interactive Data Visualization

One more thing !

Visualization Foundations - 89
 Interactive Data Visualization

General Rules for Exploratory Data Analysis

Visualization Foundations - 90
 Interactive Data Visualization

General Rules for Exploratory Data Analysis

Exploratory Data Analysis with R

Roger D. Peng

Visualization Foundations - 90
Principles of Analytic Graphics

! Principle 1: Show comparisons

" Evidence for a hypothesis is always relatives another competing hypothesis

" Always ask “Compared to What?"

Visualization Foundations - 91
Principles of Analytic Graphics

! Principle 1: Show comparisons

" Evidence for a hypothesis is always relatives another competing hypothesis

" Always ask “Compared to What?"

Testing whether an air cleaner installed in a child’s home improves

their asthma-related symptoms.
This study was conducted at the Johns Hopkins University School of
Medicine and was conducted in homes where a smoker was living for at
least 4 days a week.
Each child was assessed at baseline and then 6-months later at a second
visit. The aim was to improve a child’s symptom-free days over the 6-
month period. In this case, a higher number is better, indicating that they
had more symptom-free days.

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 91
Principles of Analytic Graphics

! Principle 1: Show comparisons

" Evidence for a hypothesis is always relatives another competing hypothesis

" Always ask “Compared to What?"

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 92
Principles of Analytic Graphics

! Principle 1: Show comparisons

" Evidence for a hypothesis is always relatives another competing hypothesis

" Always ask “Compared to What?"

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 93
Principles of Analytic Graphics

! Principle 1: Show comparisons

" Evidence for a hypothesis is always relatives another competing hypothesis

" Always ask “Compared to What?”

" Principle 2: Show causality, mechanism, explanation, systematic structure

" What is your causal framework for thinking about a question?

Visualization Foundations - 94
Principles of Analytic Graphics

Air quality standards in the U.S. concerns the

long-term average level of fine particle
pollution, also referred to as PM2.5

The standard says that the “annual mean,

averaged over 3 years” cannot exceed 12
micrograms per cubic meter.

Visualization Foundations - 95
Principles of Analytic Graphics

" Principle 2: Show causality, mechanism, explanation, systematic structure

" What is your causal framework for thinking about a question?

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 96
Principles of Analytic Graphics

! Principle 1: Show comparisons

! Principle 2: Show causality, mechanism, explanation, systematic structure

! Principle 3: Show multivariate data

" Multivariate = more than 2 variables

" The real world is multivariate

" Need to “escape flatland"

Visualization Foundations - 97
Principles of Analytic Graphics

! Principle 3: Show multivariate data

it seems that there is a slight negative

relationship between the two variables.
That is, higher daily average levels of PM10
appear to be associated with lower levels of
mortality (fewer deaths per day).

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 98
Principles of Analytic Graphics

! Principle 3: Show multivariate data

mortality tends to be higher in the
winter than in the summer

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 99
Principles of Analytic Graphics

! Principle 3: Show multivariate data

PM10 levels tend to be high in the
summer and low in the winter.

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 100

Principles of Analytic Graphics

! Principle 3: Show multivariate data There is a slight positive

relationship between the two
variables in each season

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 101

Principles of Analytic Graphics

! Principle 1: Show comparisons

! Principle 2: Show causality, mechanism, explanation, systematic structure

! Principle 3: Show multivariate data

! Principle 4: Integration of evidence

! Completely integrate words, numbers, images, diagrams

! Data graphics should make use of many modes of data presentation

! Don’t let the tool drive the analysis

Visualization Foundations - 102

Principles of Analytic Graphics

! Principle 4: Integration of evidence

Ideally, a plot would have all of the necessary

descriptions attached to it.
You might think that this level of documentation
should be reserved for “final” plots as opposed to
exploratory ones, but it’s good to get in the habit
of documenting your evidence sooner rather than
later.

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 103

Principles of Analytic Graphics

! Principle 1: Show comparisons

! Principle 2: Show causality, mechanism, explanation, systematic structure

! Principle 3: Show multivariate data

! Principle 4: Integration of evidence

! Principle 5: Describe and document the evidence with appropriate labels,

scales, sources

Visualization Foundations - 104

Principles of Analytic Graphics

! Principle 5: Describe and document the evidence with appropriate labels,

scales, sources
Defaults

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 105

Principles of Analytic Graphics

! Principle 1: Show comparisons

! Principle 2: Show causality, mechanism, explanation, systematic structure

! Principle 3: Show multivariate data

! Principle 4: Integration of evidence

! Principle 5: Describe and document the evidence with appropriate labels,

scales, sources

! Principle 6: Content is King

! Analytical presentations ultimately stand or fall depending on the quality,

relevance, and integrity of their content.

Visualization Foundations - 106

Principles of Analytic Graphics

! Principle 1: Show comparisons

! Principle 2: Show causality, mechanism, explanation, systematic structure

! Principle 3: Show multivariate data

! Principle 4: Integration of evidence

! Principle 5: Describe and document the evidence with appropriate labels,

scales, sources Edward Tufte (2006). Beautiful Evidence,

Graphics Press LLC.
! Principle 6: Content is King www.edwardtufte.com

Reference: Butz AM, et al., JAMA Pediatrics, 2011.

Visualization Foundations - 107