In one line: To show a cause, change one thing on purpose and keep everything else the same.
Suppose we want to know whether background music harms revision.
In an experiment we change one thing on purpose: music on, or music off. This is the independent variable (IV).
Then we measure what happens to the test score. This is the dependent variable (DV).
Change one thing
the independent variable
- Music on or music off
Keep the rest the same
the controls
- Same text
- Same time
- Same test
Measure the result
the dependent variable
- Score on the test
If everything else is the same for both groups, a difference in scores can only come from the music. That is what a correlation cannot do: it shows cause.
Remember: Change the IV. Measure the DV. Hold the rest still.
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: Three tools make sure that the IV is the only thing that could explain the difference.
What makes an experiment show cause
A control group
One group gets the music and one does not.
The comparison shows what the music added or took away.
Random allocation
Chance decides who goes into which group, so the groups start out alike.
It spreads out differences nobody thought of, such as sleep, mood or motivation.
Controlled variables
Other things that could affect the score (extraneous variables) are kept the same: the text, the room, the time of day, the test.
Control group · Random allocation · Controlled variables
Internal validity
- Did the IV, and nothing else, cause the change?
- Raised by the three tools above
- What lets an experiment claim cause
External validity
- Does the finding hold outside the study?
- Other people, other places, real life
- Tight control can make a study less lifelike
Exam tip: When a study claims a cause, look for the three tools.
Each one that is missing leaves another explanation open.
Stop wasting time on topics you know
Our AI identifies your weak areas and focuses your study time where it matters. No more overstudying easy topics.
Key idea: People who expect to improve often do. A good experiment separates the treatment from the expectation.
Now test a pill that is meant to calm exam nerves. If one group takes the pill and the other takes nothing, the pill group knows it has been treated. Feeling calmer could come from the pill, or from believing in it.
Three controls for expectations
A placebo
The control group gets a pill that looks the same but has nothing active in it (a placebo).
Both groups now expect to improve, so expectation cannot explain a difference between them.
Double-blind
Neither the participants nor the person measuring them knows who has the real pill.
Nobody's hopes can shape the results.
A waiting list
Some treatments, such as a course of therapy, have no placebo. The control group is told it will get the treatment later (a wait-list control).
Nobody is refused help, and there is still a comparison.
Placebo · Double-blind · Waiting list
Watch out: "They improved after the treatment" is not evidence that the treatment works.
Without a control group, the improvement could be expectation, practice, or time passing.
Key idea: Two groups never score exactly the same. The question is whether the difference is bigger than luck would give.
In the music study, the silent group averages 12 out of 15 and the music group 11.
Is that the music? Or would two groups of people differ by a mark anyway, just by chance?
A difference that could be chance
- Small groups
- A small gap between them
- Scores spread widely within each group
A difference that is probably real
- Larger groups
- A clear gap between them
- Scores close together within each group
Researchers use a statistical test to work out how likely their difference would be if chance were the only thing at work.
When that is very unlikely, fewer than 5 times in 100, the result is called statistically significant.
Remember: Significant means "probably not chance".
It does not mean large, and it does not mean important.
See how examiners mark answers
Answer exam-style questions with model answers. Learn exactly what earns marks and what doesn't.
How this is asked: The 15-mark question gives you a study and asks you to discuss it through two or more of four concepts. Causality is one of them.
When the study is an experiment, check whether it earned its conclusion.
The pattern
- Name the IV and the DV.
- Go through the three tools: a control group, random allocation, controlled variables.
- For each one that is missing, give the other explanation it leaves open.
- Bring in a second concept, such as bias or measurement.
- Conclude: can the study claim a cause?
The trap: "it is an experiment, so it shows cause": Only a well-controlled experiment shows cause.
If the groups differed from the start, the IV is not the only explanation.
Discuss the following study with reference to two or more of the following concepts: bias, causality, measurement and/or responsibility.
A researcher wanted to test whether listening to music while revising lowers test scores. She used two classes at her school. The 25 students in class A revised a text for 20 minutes while listening to music of their own choice. The 27 students in class B revised the same text in silence. Class A did this in the afternoon and class B in the morning. Both classes then took the same 15-question test. Class B scored higher on average, and the researcher concluded that music harms revision.
Model answer plan
See the answer broken into clear points, with guidance on how each point earns marks.