What you’ll work on
- Evaluate reports by examining sampling, implementation, graphs and the claims supported by evidence.
- Explain a method and check the reasonableness of a result.
Start with the idea
A study report should identify its target population, sampling frame, recruitment method, sample size, missing responses and measurement procedure. A large sample can still be systematically biased if some groups are excluded or participation depends on the topic.
Compare each headline with the actual design and numerical results. Inspect graph scales, denominators and time periods. Random sampling helps population representation, while random allocation to treatments addresses a different question about comparable groups. Observational associations require care about confounding and causal claims.
A worked example
A website reports that 90% of 200 volunteers support a policy and claims that 90% of all residents support it. Evaluate the claim.
- The volunteers may differ from residents who did not visit or respond.
- The sample proportion describes these respondents; it is not automatically a representative population estimate.
- A clearer report gives the recruitment method and population limits.
Answer: The population claim is not justified by the volunteer sample alone.
Try one question
A school surveys only students present at a lunchtime sports club to estimate all students’ interest in sport. Identify a likely bias.
Show answer and explanation
Selection or coverage bias towards sports participants
Students who do not attend the club are excluded and may have different interests.
Inside the collection
| Resource | Length | Practice | Answers |
|---|---|---|---|
| Learn and practise | 4 pages | 4 questions | Included |
| Apply and extend | 4 pages | 4 questions | Included |
| Topic checkpoint | 3 pages | 4 questions | Included |
Read on a device and work in an exercise book, or print the A4 PDFs. These files are not auto-marked digital quizzes.