MS-DS Master of Data science Data Visualization and Communication 3 — Questions and Answers
Question 1: Pre-attentive attributes are visual properties processed by the human visual system before conscious attention. Which of the following is NOT a pre-attentive attribute?
- Color hue
- Length
- 3D perspective depth cues (Correct answer)
- Orientation
Correct answer: 3D perspective depth cues
3D perspective requires cognitive processing to interpret; hue, length, and orientation are detected in parallel by low-level vision.
Question 2: What is the main advantage of a slope chart over a grouped bar chart when showing change between two time periods?
- It can display more than two groups
- It directly encodes the direction and magnitude of change through line slope (Correct answer)
- It requires less whitespace
- It supports logarithmic axes natively
Correct answer: It directly encodes the direction and magnitude of change through line slope
Slope charts use the angle and direction of a line to communicate change intuitively, whereas bar charts require the viewer to subtract bar heights mentally.
Question 3: A choropleth map colors US states by average income. What is a known bias introduced by this approach?
- Color interpolation artifacts
- Large low-population states dominate visual attention disproportionately (Correct answer)
- Missing data is indistinguishable from zero
- It cannot show continuous variables
Correct answer: Large low-population states dominate visual attention disproportionately
Geographic area ≠ population or importance, so sparsely populated states like Montana dominate the map visually while dense states like Rhode Island are barely visible.
Question 4: Which of the following best describes the principle of 'small multiples' in data visualization?
- Using many small icons instead of bars
- Repeating the same chart structure across subsets of data for easy comparison (Correct answer)
- Reducing chart size to fit on a mobile screen
- Displaying multiple KPIs in a single gauge chart
Correct answer: Repeating the same chart structure across subsets of data for easy comparison
Small multiples (trellis/facet charts) replicate a chart layout across partitions of the data, leveraging consistent axes so the viewer can compare patterns across subgroups.
Question 5: When designing a visualization for a colorblind audience, which color pair should be avoided most carefully?
- Blue and yellow
- Red and green (Correct answer)
- Purple and orange
- Teal and pink
Correct answer: Red and green
Red-green color blindness (deuteranopia/protanopia) is the most common form, affecting ~8% of males, making red/green distinction impossible.
Question 6: In the grammar of graphics (ggplot2/Vega-Lite), what does 'aesthetic mapping' refer to?
- The color palette selected for the chart theme
- Mapping data variables to visual channels such as x, y, color, size, or shape (Correct answer)
- The arrangement of chart elements on the canvas
- Choosing between serif and sans-serif fonts
Correct answer: Mapping data variables to visual channels such as x, y, color, size, or shape
Aesthetic mappings bind data columns to visual properties (encodings), forming the core of the grammar-of-graphics abstraction.
Question 7: A data journalist uses a dual-axis line chart to show revenue (left axis) and customer satisfaction score (right axis) on the same plot. What is the primary risk?
- The chart will not render correctly in web browsers
- Manually chosen axis scales can create misleading apparent correlations or divergences (Correct answer)
- Line charts cannot share an x-axis
- Dual axes require a logarithmic scale
Correct answer: Manually chosen axis scales can create misleading apparent correlations or divergences
By adjusting the y-axis ranges independently, the designer can make any two series appear correlated or anti-correlated, misleading the audience about their true relationship.
Pre-attentive attributes are visual properties processed by the human visual system before conscious attention.
Which of the following is NOT a pre-attentive attribute?