In one line: A correlational study investigates the relationship between two variables as they occur, with no manipulation and no control.
A headline says: "Teenagers who eat breakfast get better grades."
Nobody gave anyone breakfast. Researchers asked thousands of teenagers two questions, whether they eat breakfast and what grades they get, and found that the answers went together.
That is all a correlational study does: it measures two things and reports how they relate.
Three steps
- Pick two variables that can each be given a number.
- Measure both in every participant.
- Calculate how closely the two sets of numbers vary together.
In correlational research there is no independent variable and no dependent variable. Neither variable is set by the researcher.
The method is chosen for questions where manipulation is impossible or wrong. Follow one through this page: do students who work more hours in a part-time job get lower grades?
Remember: Measured, not manipulated. Related, not caused.
Free preview
This is the free notes preview
You're reading the free notes. Aimnova Pro unlocks the full study experience — and you can try it with your first topic free to keep:
- FlashcardsLock in vocabulary and key terms with spaced repetition.
- Practice questionsAnswer exam-style questions and get instant AI marking.
- Mock exams & past-paper vaultSit full mocks and see exactly how examiners award marks.
- Personalised study planA daily plan built around your exam date and weak areas.
Key idea: Two facts describe any correlation: which direction it runs, and how strong it is.
The direction
Positive correlation
The variables move in the same direction.
The more hours a player practises, the more goals she scores.
Negative correlation
The variables move in opposite directions.
The more hours a student works in a job, the lower the grades.
No correlation
The variables are unrelated.
The length of a student's name and their grades.
Same way · Opposite ways · Unrelated
This graph is a scatter plot. Its pattern is summed up by the correlation coefficient, r.
r = +1 is a perfect positive correlation and r = -1 a perfect negative one. The nearer r is to 0, the weaker the relationship and the more scattered the points.
A common slip: Strength is the distance from zero, in either direction.
r = -0.75 describes a closer relationship than r = +0.30.
See how examiners mark answers
Answer exam-style questions with model answers. Learn exactly what earns marks and what doesn't.
Key idea: A correlation says that two variables vary together. It is silent on why.
Three other explanations
A third variable
An unmeasured variable produces both.
Money worries at home could push a student into a job and also pull their grades down.
The direction is unclear
Do long hours at work lower grades? Or do students whose grades are already low choose to work more?
This is called bidirectional ambiguity: the direction of cause and effect is unclear.
Chance
With enough variables, some will line up by accident.
Such a meaningless link is a spurious correlation.
A hidden driver · A reversed arrow · Coincidence
A correlation also holds only within the range of the data.
If the students studied worked between 0 and 15 hours a week, the result says nothing about someone who works 30.
Exam tip: Name the alternative, do not just say "correlation is not causation".
"Money worries at home could explain both the job and the grades" is a point. The slogan alone is not.
Key idea: The method's strength and its weakness are the same fact: nothing is manipulated.
Strengths
- Studies naturally occurring variables where an experiment would be unethical
- Direction and strength shown in a single number
- Existing records give large samples cheaply
- Identifies relationships worth testing by experiment
Limits
- Nothing is manipulated, so no causal conclusion
- Third variables remain as rival explanations
- Bidirectional ambiguity: which variable affects which?
- Readily reported as if it were causal
The two methods complement each other.
A correlation between part-time work and grades, found in school records, raises a question. An experiment cannot assign students to jobs, but a related variable, such as the time available for homework, can sometimes be tested directly.
Choose your words: A correlation is associated with, related to or linked to something.
Only an experiment earns causes, produces or results in.
Study smarter, not longer
Most students waste 40% of study time on topics they already know. Our AI tracks your progress and optimizes every minute.
Your four class practicals
- Your class runs four small studies of its own, called class practicals: an experiment, an interview, an observation and a survey.
- Paper 2 asks about the ones your class ran.
- Keep a short note of each: aim, what you did, who took part, what you found, and the ethics.
How this is asked: No class practical is a correlational study, so the question that fits is a comparison: the method of your class practical against the methodology of a correlational study, for 6 marks.
Unseen studies are often correlational too, and then the point to make is about cause.
The answer pattern
- Two or three similarities, each starting with "Both".
- Two or three differences, each using "whereas".
- Your own practical in every paragraph.
The trap: treating a survey and a correlation as rivals: A survey is a way of collecting data. A correlation is a way of relating two sets of data.
Survey answers are often what a correlational study is built from. Say so.
Your class practical was a survey. Your class asked 45 students in your year how many hours a week they work in a part-time job and what grade they got at the end of last term. Compare and contrast the research methodology of the survey used in your class practical with the research methodology of a correlational study.
Model answer plan
See the answer broken into clear points, with guidance on how each point earns marks.