Module 5 Worksheet: Reading Charts and Distributions
Scenario
You have been sent a chart to include in a slide deck. You do not have the underlying numbers yet.
Data
Dataset: chart-reading-summary.csv
| chart_id | chart_type | intended_message | sample_size | axis_risk | safe_observation |
|---|---|---|---|---|---|
| CH01 | bar chart | Course B has more completions than Course A | 80 | y-axis starts above zero | Course B appears higher but the axis may exaggerate the difference. |
| CH02 | line chart | Weekly signups increased after a campaign | 12 | no comparison group | Signups rose after the campaign but other causes are still possible. |
| CH03 | histogram | Most delivery times are under 45 minutes | 120 | outlier hidden by wide bins | Most times are below 45 minutes but bin width may hide long delays. |
| CH04 | scatter plot | Study hours and score move together | 60 | no confounder shown | Higher study hours are associated with higher scores in this sample. |
| CH05 | box plot | Group A has a lower median wait time | 45 | small sample per group | Group A's median appears lower but sample size should be checked. |
Your Task
Pick three chart scenarios and write one observation plus one caution for each.
Questions
- What does the vertical axis start at, and why does that matter?
- What is the real difference between the largest and smallest values?
- How much larger does the chart make that difference look?
- What would the chart look like with the axis at zero?
- Is a non-zero axis defensible here?
- What can this chart legitimately be used to say?
- What must the caption state?
Write Your Conclusion
Write the caption you would put under this chart, including whatever the chart itself cannot show.
Self-Check
- Did I check where the axis starts?
- Did I express the difference as a proportion, not just a gap?
- Did I decide whether the axis choice is defensible?
- Does my caption carry the limitation?