Data Visualisation

• A. To store large volumes of data efficiently
• B. To communicate patterns, trends, and insights from data visually ✓
• C. To replace statistical analysis entirely
• D. To encrypt sensitive information in datasets

Why: Data visualisation translates raw data into visual form so that patterns, trends, and insights can be understood quickly and clearly.

• A. Pie chart
• B. Scatter plot
• C. Line chart ✓
• D. Histogram

Why: Line charts connect data points in sequence along a time axis, making trends and changes over time easy to see.

• A. Using as many colours as possible to make charts attractive
• B. Including 3D effects to add depth to every chart
• C. Minimising clutter so the data remains the focus ✓
• D. Showing every raw data point regardless of readability

Why: Good visualisations remove unnecessary decoration and clutter so the viewer's attention stays on the data and its message.

• A. Continuous data with many points along a time series
• B. Categorical data compared across distinct groups ✓
• C. Two continuous variables to examine correlation
• D. Geographic coordinates on a map

Why: Bar charts compare quantities across discrete categories, such as sales by product or counts by region.

• A. It is required by law for all published graphics
• B. It increases the file size so the chart looks more professional
• C. It allows the viewer to correctly interpret what the data represents ✓
• D. It converts the chart into a table automatically

Why: Labels and titles provide the context needed to understand what is being measured, in what units, and over what range, preventing misinterpretation.

• A. Pie chart
• B. Line chart ✓
• C. Scatter plot
• D. Bubble chart

Why: Line charts connect data points in time order, making trends and changes over time easy to see at a glance.

• A. Histogram
• B. Line chart
• C. Bar chart ✓
• D. Area chart

Why: Bar charts use length to encode values, which makes it easy to compare the sizes of distinct categories side by side.

• A. Show the share of a whole for a few categories
• B. Compare many categories with similar values ✓
• C. Highlight one dominant category
• D. Show proportions that add up to 100%

Why: People judge angles and areas less accurately than lengths, so with many similar slices a bar chart communicates differences far more clearly.

• A. Scatter plot ✓
• B. Pie chart
• C. Stacked bar chart
• D. Donut chart

Why: Scatter plots place each observation as a point on two numerical axes, revealing correlations, clusters, and outliers.

• A. Show the distribution of a single numerical variable ✓
• B. Compare categories by name
• C. Display part-to-whole relationships
• D. Track changes across time periods

Why: Histograms group continuous values into bins and show how frequently values fall in each range, revealing the shape of the distribution.

• A. Colour hue
• B. Position along a common scale ✓
• C. Area
• D. Shape

Why: Viewers judge positions along a common aligned scale more accurately than lengths, areas, angles, or colour hues. This is why dot plots and bar charts with a shared baseline are effective for comparing values.

• A. Similarity
• B. Continuity
• C. Proximity ✓
• D. Closure

Why: Proximity is the Gestalt principle stating that objects placed near each other are perceived as a group. Designers use spacing deliberately to signal relationships between data points or labels.

• A. Rainbow palettes cannot be printed in greyscale
• B. Rainbow palettes have no natural perceptual ordering and can create false boundaries
• C. Rainbow palettes use too few colours to be useful
• D. Rainbow palettes are only suitable for categorical data

• A. Around 0.5%
• B. Around 2%
• C. Around 8% ✓
• D. Around 25%

Why: Roughly 8% of men and about 0.5% of women have some form of colour vision deficiency, most commonly red-green. Designers should use colour-blind-safe palettes and redundant encodings such as labels or patterns.

• A. The processing of visual information that occurs only after conscious focus
• B. The rapid, automatic detection of visual features such as colour, orientation, or size without deliberate effort ✓
• C. The memorisation of charts before they are viewed
• D. The adjustment of screen brightness to match ambient light

Why: Pre-attentive processing allows the visual system to detect certain features within a few hundred milliseconds without focused attention. Designers exploit this to direct viewers to key data, such as highlighting one bar in a different colour.

• A. Qualitative palette with many distinct hues
• B. Sequential palette that varies in lightness or saturation from light to dark ✓
• C. Diverging palette with two contrasting hues meeting at a neutral midpoint
• D. Random palette assigned to each category

Why: Sequential palettes use a single hue (or a smooth progression) that changes in lightness or saturation, which intuitively maps low values to light colours and high values to dark colours, matching the ordered nature of numerical data.

• A. To show categories with no inherent order
• B. To highlight deviations above and below a meaningful midpoint, such as zero or an average ✓
• C. To display the exact value of every data point
• D. To make charts look more decorative

Why: Diverging palettes use two contrasting hues that intensify away from a neutral central value, making it easy to see which values are above, below, or near the midpoint.

• A. Colour-blind viewers cannot see any colours at all
• B. Around 8% of men have some form of colour vision deficiency, often confusing red and green ✓
• C. Colour-blind viewers only see in black and white by law
• D. Accessibility only matters for printed charts, not screens

Why: Roughly 8% of men and about 0.5% of women have colour vision deficiency, most commonly red-green. Choosing palettes that remain distinguishable for these viewers, such as using lightness differences or colour-blind-safe palettes, makes charts readable for more people.

• A. Using many similar shades of the same hue so categories blend together
• B. Limiting the number of distinct colours to a small set that is easy to tell apart ✓
• C. Assigning a different colour to every single bar regardless of how many there are
• D. Using red and green as the only two colours for all categories

Why: People can reliably distinguish only a limited number of colours at once, so keeping categorical palettes small and clearly distinct improves readability. Similar shades are hard to tell apart, and red-green pairs are problematic for colour-blind viewers.

• A. It hides that data point from the viewer
• B. It draws the viewer's attention to that point as the focal element ✓
• C. It indicates that the point is a statistical error
• D. It converts the chart into a sequential palette

Why: Pre-attentive attributes like saturation and contrast guide the eye. Muting most of the chart while highlighting one element with a vivid colour emphasises the key message the designer wants to communicate.

• A. To store raw data in a relational database
• B. To display key metrics and insights from multiple data sources in a single view ✓
• C. To write code that cleans and transforms datasets
• D. To send automated emails to stakeholders about data changes

Why: Dashboards consolidate key metrics and visualisations into one view so users can monitor performance and spot insights quickly, rather than storing data or performing transformations.

• A. A random sample of rows from the dataset
• B. A measurable value that shows progress toward a specific business goal ✓
• C. The file size of the dashboard report
• D. A list of all columns in the data source

Why: A KPI is a quantifiable measure tied to a business objective, such as monthly revenue or customer churn rate, which helps users track performance against goals.

• A. Because dashboards can only contain three charts by design
• B. Because too many visuals create clutter and make it harder for users to find key insights ✓
• C. Because fewer charts always consume less storage space
• D. Because charts with more than five data points cannot be displayed

Why: Overloading a dashboard with visuals overwhelms viewers and dilutes the message. A focused dashboard with a few well-chosen visuals makes insights easier to identify.

• A. To permanently delete rows from the source data
• B. To allow users to narrow down the displayed data by category, date, or other criteria ✓
• C. To change the colour theme of the entire dashboard
• D. To convert numerical data into text

Why: Filters and slicers let users interactively subset the data shown on the dashboard, such as viewing sales for a specific region or time period, without altering the underlying dataset.

• A. Placing the most important information in the bottom-right corner only
• B. Randomly arranging charts so each looks unique
• C. Placing the most important summary metrics at the top-left, where viewers typically begin reading ✓
• D. Hiding all titles and labels to keep the design minimal

Why: Viewers in left-to-right reading cultures typically scan from the top-left, so placing headline metrics there ensures the most critical information is seen first.

• A. Pandas
• B. D3.js ✓
• C. Matplotlib
• D. NumPy

Why: D3.js (Data-Driven Documents) binds data to DOM elements and uses web standards like SVG, HTML and CSS to build interactive visualisations in the browser. Pandas, Matplotlib and NumPy are Python libraries that are not designed for native browser-based interactivity.

• A. To permanently change the chart's underlying dataset
• B. To display additional details about a data point when the user hovers over it ✓
• C. To export the chart as a PDF file
• D. To compress the data for faster loading

Why: Tooltips appear on hover or focus and reveal extra information about a specific mark, such as exact values or labels, without cluttering the default view of the chart.

• A. Brushing ✓
• B. Hovering
• C. Sorting
• D. Rendering

Why: Brushing lets users select a range or region of a visualisation, often by dragging a rectangle, and can be used to filter or zoom into the highlighted data. Hovering only triggers feedback for single elements, while sorting and rendering serve different purposes.

• A. They can only be viewed offline
• B. They run in standard browsers without requiring the viewer to install specialised software ✓
• C. They always display data in three dimensions
• D. They eliminate the need for any data preparation

Why: Because web visualisations run in ordinary browsers, anyone with a link can explore them without installing special software, making them accessible and easy to share widely.

• A. It reacts to user input by immediately deleting data
• B. It automatically adjusts its layout and size to fit different screen sizes and devices ✓
• C. It updates its data every second regardless of the source
• D. It only works when connected to a high-speed server

Why: A responsive visualisation adapts its layout, scale and sometimes its content to suit the viewport of the device, such as a phone, tablet or desktop monitor, so it remains readable and usable.

• A. To display every raw data point so the audience can verify the analysis
• B. To make a key pattern or finding quickly understandable at a glance ✓
• C. To demonstrate the technical complexity of the analysis performed
• D. To include as many chart types as possible on a single slide

Why: Effective visualisations reduce cognitive load by making the main insight immediately clear, rather than overwhelming the audience with raw detail or technical complexity.

• A. Pie chart
• B. Line chart ✓
• C. Scatter plot with no time axis
• D. Bubble chart comparing categories

Why: Line charts place time on the horizontal axis and connect successive values, making trends and changes over time easy to see.

• A. Because descriptive titles are not allowed in professional reports
• B. Because an insight-driven title tells the audience what to take away from the chart ✓
• C. Because it makes the chart larger on the page
• D. Because titles are required to contain the data source only

Why: A title such as 'Sales grew 20% after the campaign' communicates the takeaway directly, whereas 'Monthly sales' only describes what is shown.

• A. Ordering bars from largest to smallest
• B. Using a y-axis that does not start at zero to exaggerate small differences ✓
• C. Labelling each bar with its value
• D. Using a consistent colour for the same category across charts

Why: Bar lengths are read as proportions of the total, so a truncated axis visually exaggerates differences and can mislead the audience about the size of an effect.

• A. It makes the file size smaller
• B. It lets the data and key message stand out without distraction ✓
• C. It is required by all data visualisation software
• D. It converts the chart into a table

Why: Decorative elements compete with the data for attention; removing them keeps the focus on the insight being communicated.