In one line: A valid measure measures what it claims to measure, and not something else.
Reliability asked: is the measure consistent? Validity asks a harder question: is it measuring the right thing at all?
Imagine a "happiness" survey that mostly asks how much money people earn. It might give steady scores. It is still not valid, because it is measuring wealth, not happiness.
Remember: Reliable: the same answer. Valid: the right answer.
A good measure needs both.
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: The first question about any measure: does it capture the idea it is meant to capture?
Three checks on a measure
Construct validity
Does the measure capture the actual idea?
A memory test should test memory, not reading speed or how hard someone tries.
Face validity
Does it look, on the surface, as if it measures the right thing?
A happiness survey full of questions about money does not.
Content validity
Does it cover every part of the idea?
A depression questionnaire that asks only about sleep misses mood.
The idea · The look · The coverage
Construct validity is the one that matters most. A measure can look right and still miss the idea: a "creativity test" that really rewards fast handwriting looks like a test, and measures speed.
Exam tip: Ask what else the measure could be picking up.
"The memory test may really measure reading speed" is a point about construct validity.
Feeling unprepared for exams?
Get a clear study plan, practice with real questions, and know exactly where you stand before exam day. No more guessing.
Key idea: A study can be valid in two more ways: its conclusion about cause can be safe, and its findings can hold outside the study.
Internal validity
- Was the effect really due to what the researcher changed?
- Threat: something else differed between the groups
- Protected by random allocation and controls
External validity
- Do the findings hold beyond this study?
- For other people, and in real-life settings
- Threat: an unusual sample or an artificial task
Take a laboratory study claiming that a drink "boosts focus". If the two groups were treated the same in every way but the drink, internal validity is high.
But would the effect show up during real homework, with a phone buzzing? Whether findings apply to everyday settings is called ecological validity, one part of external validity.
The trade-off: Tight control protects internal validity.
It can also make the situation artificial, which lowers ecological validity. More control is not always better.
How this is asked: Validity belongs to the concept of measurement, one of the four concepts in the 15-mark question on a study you are given.
It also links to causality: internal validity is about whether a claim of cause is safe.
The pattern
- Say what the study claims to have measured, and how it measured it.
- Construct: could the measure be picking up something else?
- Internal: could anything else explain the difference?
- External: would it hold for other people, in real life?
- Conclude: how much of the claim is supported?
The trap: "validity" with no kind and no threat: "The study lacks validity" says nothing.
Name the kind, and say what threatens it.
Discuss the following study with reference to two or more of the following concepts: bias, causality, measurement and/or responsibility.
A sports-drink company tested whether its drink improves concentration. Forty university students were put at random into two groups: one drank the sports drink and the other drank water. Twenty minutes later, in a quiet laboratory, each student did a five-minute computer task, pressing a key whenever a red square appeared. The sports-drink group reacted faster on average, and the difference was statistically significant. The company concluded that its drink helps people to concentrate at school and at work.
Model answer plan
See the answer broken into clear points, with guidance on how each point earns marks.