Skip to content
AP Statistics · Exploring One-Variable Data and Collecting Data

Case control study

Case control study appears in 8 reviewed AP Statistics questions and sits in Exploring One-Variable Data and Collecting Data. Below are worked examples showing exactly how the exam tests it, with the answer marked and every distractor explained.

How Case control study is tested

Example 1Medium
A researcher studying the association between alcohol consumption and liver disease compares 80 patients with liver disease (cases) to 80 healthy controls matched on age and sex. The researcher looks at patients' past alcohol consumption records. One concern with this study design is 'recall bias.' What does this mean?
  1. AControls may recall their alcohol consumption better than cases because they don't have liver disease.
  2. BCases (with liver disease) may recall or report past alcohol consumption differently than controls — possibly overreporting or more carefully reporting — because they are aware of their diagnosis.Correct
  3. CRecall bias means the study must be repeated to verify the initial findings.
  4. DThe researcher may recall which patients are cases and inadvertently interview them differently.

Why B is right

Recall bias occurs in case-control studies when cases and controls systematically differ in how they recall or report past exposures. Cases (people with liver disease) may think more carefully about past behaviors that could have caused their illness, or may attribute more drinking to themselves than they actually did. This differential recall can bias the estimated association between alcohol and liver disease.
Why the other 3 choices miss
A
Incorrect because this reverses the direction of the recall bias concern. It is the cases (not controls) who are more likely to have biased recall due to their awareness of their disease status.
C
Incorrect because recall bias is not resolved by repeating the study. It is an inherent limitation of retrospective designs where participants are asked to recall past exposures. Prospective designs avoid recall bias.
D
Incorrect because the described scenario is a type of interviewer bias (the researcher's knowledge influencing the interview), not recall bias. Recall bias specifically refers to differential accuracy of self-reported past exposures between cases and controls.

Studied alongside

Other concepts from Exploring One-Variable Data and Collecting Data.