Visualisation & Storytelling · Lesson 61

Chart Selection

Chart Selection is about matching a visual encoding to an analytical question and then presenting the evidence without distortion.

ConceptWorked examplePracticeKnowledge check

Textbook walkthrough

What Chart Selection actually means

Chart Selection is about matching a visual encoding to an analytical question and then presenting the evidence without distortion. Position and length are generally easier to compare precisely than area, angle or decorative effects.

Chart Selection matters because visual encodings determine what comparisons a reader can perceive quickly and accurately. Good storytelling does not decorate evidence; it selects and labels the representation that best supports the analytical question.

Deeper walkthrough

Read Chart Selection as a mechanism, not a recipe

Treat this as a sequence of observable decisions rather than one opaque command. Stage 1: Identify variable types and the comparison the viewer must make. Stage 2: Choose the simplest chart whose encodings match that comparison. Stage 3: Use truthful scales and meaningful ordering. Final checkpoint: Remove non-data decoration that competes with the evidence.

Mechanism

Follow the transformation

Identify variable types and the comparison the viewer must make.

Choose the simplest chart whose encodings match that comparison.

Use truthful scales and meaningful ordering.

Evidence

Know what would convince you

Reconcile plotted marks/bars/bins/lines with a few source values and the intended aggregation.
Check axis limits, units, category order and any binning/smoothing choices explicitly.

Useful distinctionBar: Category magnitudes.

How it works

Trace the mechanism step by step

Identify variable types and the comparison the viewer must make.
Choose the simplest chart whose encodings match that comparison.
Use truthful scales and meaningful ordering.
Label units/categories directly when possible.
Use colour sparingly and accessibly; do not rely on colour alone.
Remove non-data decoration that competes with the evidence.

Worked demonstration

Make the concept concrete

Demonstration

Text example

Question: compare categories → bar chart.
Question: distribution of one numeric variable → histogram/box plot.
Question: change over ordered time → line chart.
Question: relation between two numeric variables → scatter plot.

Expected / illustrative result

Choose the visual from the analytical comparison, not from aesthetic preference.

Interpret the result.

For Chart Selection, identify which source values create each important mark/position, then check whether scale, ordering, aggregation or binning could change the visual conclusion.

Distinctions & related ideas

Know what this is — and what it is not

BarCategory magnitudes.

LineOrdered/time trend.

HistogramNumeric distribution.

ScatterNumeric relationship.

Box/violinDistribution comparison across groups.

Use deliberately

When it is appropriate

Use Chart Selection when its visual encoding matches the variable types and the comparison/pattern the reader needs to see.

Boundary conditions

When to stop or reconsider

Choose a different chart or representation when this encoding hides distribution, order, uncertainty or observation-level structure, or when overplotting/scale choices would make the display misleading.

Common mistakes

Failure modes to recognise

Using a chart type whose marks/axes do not match the data types or analytical question.
Allowing scale, binning, category order or aggregation to create a visual impression the raw values do not support.
Adding colour, labels or decoration without a clear encoding purpose or accessible alternative.

Verification

How to check the result

Reconcile plotted marks/bars/bins/lines with a few source values and the intended aggregation.
Check axis limits, units, category order and any binning/smoothing choices explicitly.
Change one data value or filtering rule and predict which visual element should move before regenerating the figure.

Hands-on practice

Demonstrate understanding

Try this:

Build a tiny, inspectable example of Chart Selection. First identify variable types and the comparison the viewer must make. Then choose the simplest chart whose encodings match that comparison. Write the expected result before running it, and explain one condition that would make the result misleading or invalid.

Use a handful of values and label the axes/units. Point to each visual mark and identify the source value or aggregation that created it.

Knowledge check

Check reasoning, not memorisation

Before trusting a result from Chart Selection, which check provides the strongest evidence that you understand and applied it correctly?

Reconcile plotted marks/bars/bins/lines with a few source values and the intended aggregation. Use the largest available dataset and accept the result if the command finishes without an error. Memorise the syntax or formula and skip inspecting the inputs, intermediate state and assumptions.

Quick reference

Keep the important distinctions visible

Step 1Identify variable types and the comparison the viewer must make.

Step 2Choose the simplest chart whose encodings match that comparison.

Step 3Use truthful scales and meaningful ordering.

Step 4Label units/categories directly when possible.

Lesson summary

What to remember

Chart Selection is about matching a visual encoding to an analytical question and then presenting the evidence without distortion. Position and length are generally easier to compare precisely than area, angle or decorative effects.
Identify variable types and the comparison the viewer must make.
Using a chart type whose marks/axes do not match the data types or analytical question.
Reconcile plotted marks/bars/bins/lines with a few source values and the intended aggregation.