CEC 434 – Data Visualization – Tutorial - SOLUTIONS
University of Buea
Thursday 25 May 2023
Question 1
The data shown here are the number of visits to a university website for a particular statistics
course. There are 90 students in the class.
1. What are the names (type) of the 2 plots shown?
2. List any 2 interesting features in these data.
SOLUTION
1. The plots are a time-series plot and a sparkline. The sparkline shows exactly the same
data, just a more compact form (without the labelling on the axes).
2. Features shown in the data are:
o A noticeable weekly cycle; probably assignments are due the next day!
o A sustained, high level of traffic in the first week February - maybe a midterm
test.
o Some days have more than 90 visits, indicating that students visit the site more
than once per day, or due to external visitors to the site.
Question 2
What are the names of the axes on a bar plot?
SOLUTION
The category axis and value axis.
Question 3
Which types of features can the human eye easily pick out of a time series plot?
SOLUTION
Features such as sinusoids, spikes, gaps (missing values), upward and downward trends are
quickly picked out by the human eye, even in a poorly drawn plot.
Question 4
Why is the principle of minimizing “data ink” so important in an effective visualization?
Give an scientific or engineering example of why this important.
SOLUTION
It reduces the time or work to interpret that plot, by eliminating elements that are non-
essential to the plot’s interpretation. Situations which are time or safety critical are
examples, for example in an operator control room, or medical facility (operating room).
Question 5
Describe what the main difference(s) between a bar chart and a histogram are.
SOLUTION
The solution is taken directly from:
https://www.forbes.com/sites/naomirobbins/2012/01/04/a-histogram-is-not-a-bar-chart/
• Histograms are used to show distributions of variables while bar charts are used to
compare variables.
• Histograms plot quantitative data with ranges of the data grouped into bins or
intervals while bar charts plot categorical data.
• Bars can be reordered in bar charts but not in histograms.
• There are no spaces between the bars of a histogram since there are no gaps between
the bins. An exception would occur if there were no values in a given bin but in that
case the value is zero rather than a space. On the other hand, there are spaces
between the variables of a bar chart.
• The bars of bar charts typically have the same width. The widths of the bars in a
histogram need not be the same as long as the total area is one hundred percent if
percents are used or the total count if counts are used. Therefore, values in bar charts
are given by the length of the bar while values in histograms are given by areas.
Question 6: Attribute types
What type of attribute are the following? Circle only one of the three choices.
1. Cruise ship length (eg 400 m) categorical ordinal quantitative
2. Movie rating (eg PG-13) categorical ordinal quantitative
3. Narwhal tusk size (eg 10 ft) categorical ordinal quantitative
4. Dinosaur type (eg velociraptor) categorical ordinal quantitative
5. Student number (eg 77283938) categorical ordinal quantitative
6. License plate code (eg AB1 23C) categorical ordinal quantitative
7. Hot drink type (eg tea) categorical ordinal quantitative
8. Hot drink temperature (eg 100 categorical ordinal quantitative
degrees)
Hint: Remember from the Lectures that categorical data, such as favourite fruit or names,
does not have an implicit ordering, but it often has hierarchical structure. All ordered data
does have an implicit ordering, as opposed to unordered categorical data. This type can be
further subdivided. With ordinal data, such as shirt size, we cannot do full-fledged arithmetic,
but there is a well-defined ordering. For example, large minus medium is not a meaningful
concept, but we know that medium falls between small and large.
SOLUTION
What type of attribute is the following? (C=Categorical, O=Ordinal, or
Q=Quantitative)
1. Cruise ship length (eg 400 m) Q
2. Movie rating (eg PG-13) O
3. Narwhal tusk size (eg 10 ft) Q
4. Dinosaur type (eg velociraptor) C
5. Student number (eg 77283938) C
6. License plate code (eg AB1 23C) C
7. Hot drink type (eg tea) C
8. Hot drink temperature (eg 100 degrees) Q
Question 7: True/False Circle only one of the two choices.
1. T F The color channels of luminance and saturation have similar characteristics:
they both convey magnitudes.
2. T F Radial layouts are inappropriate for aggregated or filtered data.
3. T F Encoding a network as an adjacency matrix is inappropriate for topological
tasks such as path following.
4. T F Symbol maps are a good alternative to choropleth maps when regions differ in
size.
5. T F Categorical data cannot have cyclic semantics.
6. T F 2D position is perceived much more accurately than 3D position.
7. T F Scatterplots use interlocking area marks.
8. T F It is possible to show attributes for nodes but not for links in node-link
drawing of networks and trees.
9. T F Visualization designers should minimize information density.
10. T F The angle channel can convey sequential or divergent or cyclic data.
11. T F Shape and 2D position are separable visual channels.
12. T F The human perceptual system cannot notice responsiveness delays of less than
one second.
13. T F The human perceptual system responds to hue differently depending on the
hue and luminance of nearby items.
14. T F Containment marks cannot convey information with both hue and luminance
channels simultaneously.
15. T F Animated transitions are a good strategy for avoiding the interference between
color and size channels.
16. T F Linked highlighting shows differences in item distributions between views.
SOLUTION
Choose whether each statement is true or false.
Topic Answer Question
1 Color TRUE
The color channels of luminance and saturation have similar characteristics: they
both convey magnitudes.
2 Aggregation FALSE Radial layouts are inappropriate for aggregated or filtered
data.
3 Networks TRUE
Encoding a network as an adjacency matrix is inappropriate for topological tasks
such as path following.
4 Maps TRUE
Symbol maps are a good alternative to choropleth maps when regions differ in
size.
5 Abstractions TRUE Categorical data cannot have cyclic semantics.
6 Marks & Channels TRUE 2D position is perceived much more accurately than
3D position.
7 Multivariate Tables FALSE Scatterplots use interlocking area marks.
8 Networks FALSE
It is possible to show attributes for nodes but not for links in node-link drawing of
networks and trees.
9 Complexity FALSE Visualization designers should minimize information density.
10 Marks & Channels TRUE The angle channel can convey sequential or
divergent or cyclic data.
11 Marks & Channels TRUE Shape and 2D position are separable visual
channels.
12 Rules of Thumb FALSE
The human perceptual system cannot notice responsiveness delays of less than
one second.
13 Color TRUE
The human perceptual system responds to hue differently depending on the hue
and luminance of nearby items.
14 Marks & Channels FALSE
Containment marks cannot convey information with both hue and luminance
channels simultaneously.
15 Interactive Views FALSE
Animated transitions are a good strategy for avoiding the interference between
color and size channels.
16 Interactive Views TRUE Linked highlighting shows differences in item
distributions between views.
Question 8: Tasks and Visual Encodings: Refugees
Below are two different visual encodings (stacked bars and streamgraph) of the
same dataset (origin of US refugee immigrants 1975-2018). For each approach,
state one abstract task for which this encoding is more suitable than the other and
provide a
rationale for your claim in terms of marks and visual channels.
3.1 Task 1 (stacked bars better):
3.2 Rationale:
3.3 Task 2
(streamgraph
better):
3.4 Rationale:
SOLUTION
3.1 Task 1: Stacked Graph better
● Lookup value, for specific time point for specific category
● Compare totals (height of entire bar), over all time points
● Compare values across segments within each bar, at specific time point
● Compare values across lower segment of each bar, over all time points
● Understand part-to-whole relationship between segment and full bar
3.2 Rationale
● Lookup value: The distinct marks for each year make it easier to find a specific
one and the axis for vertical
position helps provide a more exact value for the # of refugees.
● Compare values across entire bars: Aligned spatial position judgements are
highly effective.
● Compare values across segments within each bar: length channel judgements
are somewhat effective.
● Compare values across lower segment of each bar: Aligned spatial position
judgements are highly effective.
● Part-to-whole between segment and full bar: length channel effective
3.3 Task 2: Streamgraph better
● Discover trends over time / Discover distribution within particular category over all
time points
● Discover extreme maximum values within category
3.4 Rationale
● Discover trends over time. Instead of distinct/discrete marks per year and
category, the area mark allows for
smooth, horizontally contiguous area marks that make it easier to look at trends for
a single category.
