Revision Library
Choose a subject
Menu
GCSE Statistics · Topic guide

Correlation and Causation (Foundation)

Correlation is a relationship between two variables, where a change in one variable tends to go with a change in the other, for example taller people often having a bigger shoe size. Causation means that a change in one variable directly causes the change in the other. In GCSE Statistics it is important to remember that correlation between two variables does not, on its own, prove that one causes the other.

FoundationCorrelation and Time SeriesEdexcelAQACCEA

Before you start

Make sure you're comfortable with these topics first:

Method

  1. Look at a scatter graph to see whether the points show a pattern (correlation) or are scattered with no clear pattern.
  2. Describe the type of correlation: positive (both variables increase together), negative (one increases as the other decreases), or none.
  3. Describe the strength of the correlation: strong (points close to a line) or weak (points more spread out).
  4. Remember that correlation only shows the two variables change together, not that one causes the other.
  5. Consider whether a third variable could be causing both, or whether the link could simply be coincidence, before claiming causation.
  6. Only conclude causation if there is a plausible mechanism linking the variables, ideally supported by other evidence, not the graph alone.

Common mistakes

  • MistakeJudging the strength of correlation by how steep the trend is, so a steep line of scattered points is called strong.

    InsteadStrength depends on how close the points lie to a line, not on its steepness. Points tightly clustered round a shallow line show strong correlation; a widely scattered cloud on a steep slope is weak.

  • MistakeDescribing correlation without naming the two variables or the direction, such as 'it goes up' or 'there is a link'.

    InsteadName both variables and the direction: 'as (first variable) increases, (second variable) tends to increase', then add positive or negative, and strong or weak, to say how the points lie.

  • MistakeTreating a strong-looking pattern from only a few points as reliable evidence of a relationship.

    InsteadWith very few points a pattern can appear by chance. State how many points there are, and say that more data would be needed before relying on the pattern.

Worked examples

Example 1

A study finds a strong positive correlation between the number of ice creams sold and the number of people who go swimming each day in summer. A newspaper claims that eating ice cream causes people to go swimming. (a) Describe the correlation. (b) Explain why the newspaper's claim is not justified. (c) Suggest a more likely explanation.

  1. A strong positive correlation means that as ice cream sales increase, the number of swimmers also tends to increase.
  2. The claim assumes correlation proves causation, but correlation only shows that the two variables change together.
  3. There is no direct mechanism by which eating ice cream would cause someone to go swimming.
  4. A third variable, hot weather, is a more likely cause of both: hot days lead to more ice cream sales and more people swimming.
  5. Final answer: there is a strong positive correlation, but it does not prove causation; hot weather is a more likely common cause of both ice cream sales and the number of swimmers.

Example 2

Eight students recorded their average hours of sleep a night and their score in a concentration test out of 80. Hours (score): 5.5 (41), 6 (46), 6.5 (50), 7 (57), 7.5 (55), 8 (63), 8.5 (66), 9 (70). A student says 'Sleeping more makes you concentrate better.' (a) Describe the correlation. (b) Is the claim fully supported by the data? Give two reasons.

  1. As hours of sleep increase, test score tends to increase, so the correlation is positive.
  2. The points lie close to a rising straight line. The score dips slightly from 57 at 7 hours to 55 at 7.5 hours, but the overall pattern is clear, so the correlation is strong.
  3. A strong positive correlation is consistent with the claim, and it is plausible that tiredness reduces attention, so this is not like a coincidence between unrelated things.
  4. It does not prove the claim. Reason 1: only eight students were tested, so they may not be typical of all students and the pattern might not hold for a larger group. Reason 2: another variable, such as general health or stress, could affect both sleep and concentration, or students who concentrate well might sleep more easily.
  5. Final answer: there is a strong positive correlation between hours of sleep and score. The data are consistent with the claim but do not prove it; a controlled experiment that changes sleep on purpose would be needed to test cause.

Practice questions

Q1[1 mark]A scatter graph shows that as temperature increases, the number of hot drinks sold decreases. What type of correlation is this?Show answer

Answer: Negative correlation.

Got it right?
Q2[1 mark]Define correlation in your own words.Show answer

Answer: A relationship where a change in one variable is associated with a change in another variable.

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q3[1 mark]A study finds a positive correlation between shoe size and reading ability in primary school children. Does having big feet cause better reading?Show answer

Answer: No; this is likely due to a third variable, age (older children have bigger feet and better reading skills), not causation.

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q4[1 mark]What word describes a situation where one variable directly causes a change in another?Show answer

Answer: Causation.

Got it right?
Q5[1 mark]Two variables have a correlation coefficient close to 0. What does this suggest?Show answer

Answer: There is very little or no linear correlation between the variables.

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.
Q6[2 marks]A researcher finds that towns with more fire engines have more fire damage, and concludes that fire engines cause fire damage. Identify the flaw in this reasoning and suggest the true common cause.Show answer

Answer: The flaw is assuming correlation proves causation; the true common cause is likely the size of the fire, since bigger fires need more fire engines and cause more damage.

Got it right?
Your answerWork it out on paper, then show the answer and mark yourself.

Exam-style questions

Written in the style of a GCSE Statistics exam paper, with a full mark scheme.

Exam tips

  • When you suggest a third variable, name it and say how it would affect both measured variables; 'other factors' on its own gives the reader nothing to check.
  • If asked how a causal link could be tested, suggest a controlled experiment in which one variable is changed on purpose while the others are held constant, since a scatter graph alone cannot show cause.
Q1[2 marks]A scatter graph shows a strong positive correlation between a country's number of doctors and its number of hospitals. State what 'strong positive correlation' means, and state whether this proves that having more doctors causes more hospitals to be built.Show mark scheme

Tick each line you got.

Nothing ticked yet - 2 available

Got it right?
Q2[3 marks]A local newspaper reports a positive correlation between the number of umbrellas sold and the number of bus delays in a city, and claims that people buying umbrellas causes buses to be delayed. Explain why this conclusion is flawed, and suggest a more likely common cause.Show mark scheme

Tick each line you got.

Nothing ticked yet - 3 available

Got it right?
Q3[4 marks]A scatter graph of 10 towns shows a positive correlation between the number of cafes and the number of car parking spaces. A student says: 'Building more car parks will cause more cafes to open.' Discuss whether the data supports this claim, referring to correlation, causation and possible other explanations.Show mark scheme

Tick each line you got.

Nothing ticked yet - 4 available

Got it right?

See real GCSE Statistics past-paper questions, with official mark schemes 

This topic in real past papers

We have tagged some boards' past papers question by question (not every board or year yet). This topic comes up in:

Free printable worksheet

Want more practice on paper? Download the Correlation and Causation (Foundation) worksheet pack - 30 pages of exam-style questions with a full mark scheme. Free to download, no card or account. Print it for personal and classroom use.

This topic is chapter 9 of GCSE Statistics Foundation Essentials 2, the whole course as one free printable PDF. Its worksheet is also chapter 1 of GCSE Statistics Foundation Topic Workbook 5 and chapter 9 of GCSE Statistics Foundation 10-Minute Tests 2, free printable practice books.

Other versions of this worksheet:

Keep going

Not quite what you needed?

Tell us what is missing on Correlation and Causation (Foundation), or which topic to write up next.

Build a full practice pack.