Cogito
AP Statistics · Chapter 1 · Lesson 2
Sampling and Study Design
What a study can and cannot claim.
11 problems · about 24 minutes · AP Statistics 3.2, 3.4, 3.5
What this lesson teaches
The student distinguishes observational studies from experiments and identifies sources of bias.
- Random sampling earns the right to generalise; random assignment earns the right to claim cause.
- An observational study reports association, whatever its size.
- A bigger biased sample is a more precise wrong answer.
Warm Up
Straightforward practice. Get the method working first.
4 problemsWhich is required to claim causation? 1 for random sampling, 2 for random assignment.
Answer 2
Why Random assignment.
Sort each study by what it can support.
Answer Association only: Survey of volunteers, Observing two existing groups · Causation: Randomised controlled experiment
Why Ask whether anyone was assigned a treatment.
A voluntary online poll. Is it likely biased? 1 for yes, 0 for no.
Answer 1
Why Who bothers to respond?
Does a larger biased sample fix the bias? 1 for yes, 0 for no.
Answer 0
Why It makes the wrong answer more precise.
Build It Up
The same ideas with more to keep track of.
3 problemsA lurking variable explains an association. Was the study observational? 1 for yes, 0 for no.
Answer 1
Why Random assignment balances lurking variables.
Match each design feature to what it protects against.
Answer Random assignment → Lurking variables; Control group → Having nothing to compare against; Blinding → Expectations changing the result
Why Blinding is about what people know.
A census surveys what fraction of the population? Give it as a decimal.
Answer 1
Why All of it.
Stretch Yourself
Mixed problems. Work out what kind of question it is before you start.
4 problemsConvenience sampling. Is it random? 1 for yes, 0 for no.
Answer 0
Why Whoever is nearest.
An experiment with random assignment but volunteer subjects. Can it claim cause? 1 for yes, 0 for no.
Answer 1
Why Cause comes from assignment; generalising is the separate question.
The Right to Generalise: Which gives the right to generalise to a population? 1 for random sampling, 2 for random assignment.
Answer 1
Why Random sampling.
The Right to Claim Cause: Which gives the right to claim causation? 1 for random sampling, 2 for random assignment.
Answer 2
Why Random assignment.