Chart choice follows the question
The question and the variable types decide the chart. Keep the natural order of ordered categories, and make overlapping points visible.
Variable type narrows the options; the comparison you need selects the design (W6 p. 6).
| Question | Variables | Useful starting point |
|---|---|---|
| How many in each category? | Categorical + count | Bar chart |
| How are grades distributed? | One numerical variable | Histogram or box plot |
| Do two scores vary together? | Two numerical variables | Scatter plot |
| How does activity change? | Time + numerical variable | Line chart |
| How do groups differ? | Group + numerical variable | Grouped plot or small multiples |
Category order carries meaning (W6 p. 9). Ordered categories such as Very low, Low, Medium, High, Very high (counts 4, 8, 14, 10, 4; total 40) keep their natural sequence, so the reader can see that responses peak at Medium. Unordered categories such as programmes or subjects can be sorted by count to make ranking easy. Sorting an ordinal scale by count would destroy its shape.
Overlapping observations (W6 p. 16). Six students sit at only three positions: three at (50,60), two at (60,70) and one at (70,80). A plain scatter plot shows three dots and hides half the records. Jitter adds small, disclosed random offsets for display only so all six marks become visible. The stored values and every statistic stay unchanged; label the axis "offset for display only". Transparency, labelled counts or size-by-count are alternatives when jitter would mislead.
Source: W6 PDF pp. 1-37. Most numbers in the lecture are illustrative or constructed for teaching; pp. 26-27 reuse the Week 5 synthetic registration counts. The Week 6 lab manual (L6) practises Week 5 EDA reasoning and is worked through section by section in Lab work.
Week 2 summaries meet Week 6 histograms: one extreme value moves the mean but not the median, and bin edges change the picture but not the data.
Scatter plots show what a single r can hide: a perfect U-shape has zero linear correlation, and a plotted subset is not the population behind a reported statistic.
Practice problems
Supplementary study questions on the lecture concepts — not verbatim exam questions. Each answer counts toward spaced review.
1. Conceptual understanding
Definitions and distinctions.
Which chart is the useful starting point for “How does activity change over weeks?”
Six students occupy three positions in a scatter plot. What does jitter do?
2. Application
Apply the concept to a case or calculation.
Which chart suits “How are grades distributed?”
Survey counts are 4, 8, 14, 10, 4 for Very low to Very high. How should the bars be ordered?
3. Interpretation and limitations
Evaluate assumptions and justify conclusions.
Programme counts have no natural order. What ordering often helps?
How should jitter be disclosed?
Explain it in writing
Self-checked, not marked. Write a few sentences, then compare with the example answer. Your writing is saved as you type.
Show an example answer
A scatter plot, because both variables are numerical and each point shows one student's pair of values, revealing direction, form and unusual points.
Check: did you answer the question, use evidence or working, and avoid claiming more than the evidence supports?
Show an example answer
They are ordered categories. Keeping Very low to Very high in order shows the shape of the responses; sorting by count would break that order.
Check: did you answer the question, use evidence or working, and avoid claiming more than the evidence supports?