S3 Maths Scatter Graphs Retry: Correlation versus Causation and Misreading r
- 2026-11-22
S3 Maths Scatter Graphs Retry: Correlation versus Causation and Misreading r
Fix the usual mistakes: treating r as a share of points, reading r = 0 as no relationship, and flipping the sign of a residual.
Fix the usual mistakes: treating r as a share of points, reading r = 0 as no relationship, and flipping the sign of a residual. Fix the usual mistakes: treating r as a share of points, reading r = 0 as no relationship, and flipping the sign of a residual.
01 Paper details (check answers afterwards)
| Item | Detail |
|---|---|
| Questions | 10 questions |
| Suggested time | 25 min |
| Difficulty mix | Foundation 4 · Intermediate 3 · Challenge 2 · Error redo 1 |
| Chapter | Chapter: S3 Maths – Probability and Tree Diagrams |
| Level | S3 . scatter retry |
02 Questions (10 items)
- FoundationPoints on a scatter graph run from bottom left to top right, but a student answers negative correlation. What is correct?
- FoundationWith r = 0.5 a student says half the points lie on the trend line. What is the correct reading?
- FoundationSeeing r = 0, a student concludes the two variables are completely unrelated. What is the flaw?
- FoundationFor the data (1,4), (2,6), (3,8) a student answers slope 3. What is the correct slope?
- IntermediateThe data stop at x = 6 but a student predicts y at x = 50. Why is this unreliable?
- IntermediateA trend line has slope 3 yet r is only 0.2. Why is the relationship not strong?
- IntermediateA student claims the trend line need not pass through any particular point. What is correct?
- ChallengeA data set has r = -0.98 but a student answers weak correlation. What is correct?
- ChallengeAt x = 2 the trend line predicts 8.0 while the actual value is 7.4. A student answers residual +0.6. What is correct?
- Error redoSeeing that ice cream sales correlate positively with temperature, a student says eating ice cream makes people feel hot. What is wrong?
03 Answers and one-line notes
| # | Answer | One-line note |
|---|---|---|
| 1 | Positive correlation | Both variables rising together is positive correlation, while a downward tilt is negative. |
| 2 | Moderate positive correlation, with r squared = 0.25, so 25% of the variation is explained | r squared is 0.5 x 0.5 = 0.25, a share of variation rather than a count of points. |
| 3 | r = 0 means no linear relationship, but a curved relationship may still exist | Always plot the scatter graph first to judge the shape of any relationship. |
| 4 | 2 | y rises by 4 while x rises by 2, so (8 – 4) / (3 – 1) = 2, not 3. |
| 5 | It is extrapolation far outside the data, where the trend may not hold | Extrapolation is only a rough guide and should not be treated as a conclusion. |
| 6 | Slope depends on units, while r shows strength, and r = 0.2 is weak | Finer units inflate the slope while r stays the same. |
| 7 | The line of best fit must pass through the mean point | The least squares line always passes through the mean point, a quick check on any sketch. |
| 8 | Strong negative correlation | The sign gives the direction while 0.98 near 1 means the link is strong. |
| 9 | -0.6 (the prediction is above the actual value) | Residual is actual minus predicted, so 7.4 – 8.0 = -0.6, and the sign gives the direction. |
| 10 | Confusing correlation with causation, since both may be driven by temperature | Correlation only describes moving together, while causation needs experiments or other evidence. |
04 What to do after marking
- After marking, redo only the wrong items and write down which step went wrong (formula, unit, or misread number).
- Repeat the same item two days later; move to the next paper only when both attempts are correct.
- Parents only need the answer and note columns; there is no need to explain every item.
Join our S3 Maths courseTutor Registration →
Questions and answers are written originally by the TutorZone team and are not taken from any school, publisher or examination authority paper. Every value is checked by computer.



