- Define and explain Scatter diagrams in your own words
- Use key terms such as Correlation accurately
- Apply what you have learned to new examples and questions
- Avoid the common mistakes learners make with this topic
This lesson focuses on Scatter diagrams: plotting paired data, spotting correlation, and drawing a line of best fit.
Plotting paired data, spotting correlation, and drawing a line of best fit.
Key ideas
Correlation is not causation
A strong correlation only shows that two things vary together; a third factor may cause both. A line of best fit drawn through the middle of the points shows the trend and can estimate values within the data range, but never extrapolate far beyond it.
Reading charts carefully
Check the axes first: a bar chart that starts above zero can exaggerate small differences, and a pie chart must show sectors proportional to the data. Frequency diagrams need equal class widths, or frequencies must be scaled by width.
Key term — Correlation: A pattern in a scatter diagram where two variables move together — positive, negative or none — which does not by itself prove causation.
A scatter diagram shows points rising left to right. What type of correlation is this?
Positive correlation.
Answer: Positive correlation.
- Finding the median without ordering the data Always sort the values first; the median is the middle of the ordered list, not the middle of the original list.
- Forgetting that an even count has no single middle value With an even number of values, the median is halfway between the two middle values, e.g. (6 + 8) ÷ 2 = 7.
Practice
The median (7.5); the mean (12.5) is distorted by the outlier 40.
Sum = 50; mean = 50 ÷ 5 = 10.
Ordered: 2, 4, 7, 9, 11; median = 7.
Mode = 6; range = 6 − 2 = 4.
Quick check
Which of these best defines "Correlation"?
Why might a bar chart with a y-axis starting at 50 be misleading?
- Scatter diagrams: plotting paired data, spotting correlation, and drawing a line of best fit.
- Correlation is not causation: A strong correlation only shows that two things vary together; a third factor may cause both.
- Median: The middle value when data is ordered from smallest to largest; a robust average unaffected by extreme values.
- Watch out for: finding the median without ordering the data