A researcher wants to determine if a new app reduces screen time. She allows users to choose whether to download the app (treatment group) or not (control group). After one month, she compares screen time between the two groups. The primary reason this is not a valid experiment is:
- AThe control group should have received a fake app.
- BThe groups were self-selected, not randomly assigned, so pre-existing differences (confounding) prevent causal conclusions.Correct
- CScreen time cannot be measured accurately.
- DThe study is too short at one month.
Why B is right
Without random assignment, this is an observational study, not an experiment. Users who choose to download the app may already be more motivated to reduce screen time. This self-selection creates confounding — the observed reduction in screen time could be due to user motivation, not the app. Random assignment would have controlled for this.
Why the other 3 choices miss
- A
- A fake app (active placebo) would be an improvement, but the most fundamental flaw is the lack of random assignment, which allows self-selection bias and confounding.
- C
- Screen time can be measured accurately using phone usage statistics. Measurement accuracy is not the primary concern described.
- D
- Duration is a study design choice but is not the fundamental flaw here. Even a one-month experiment can produce valid causal evidence if random assignment is used.
Which of the following best distinguishes a lurking variable from a confounding variable in observational studies?
- AA confounding variable is tied to both explanatory and response and was measured; a lurking variable was not.Correct
- BA lurking variable is measurable, while a confounding variable is unmeasurable.
- CA lurking variable causes the response directly, while a confounding variable only indirectly affects the response.
- DConfounding variables are only relevant in experiments, while lurking variables are only relevant in observational studies.
Why A is right
While definitions vary slightly by source, in AP Statistics: a lurking variable is one that influences the observed relationship between the explanatory and response variables but was not included in the study (not measured). A confounding variable is similar but is sometimes defined as one that is associated with the explanatory variable and causally related to the response. The key distinction often used is that a confounding variable is accounted for (measured) in the study, while a lurking variable is not.
Why the other 3 choices miss
- B
- Incorrect because lurking variables may be measurable in principle — they simply weren't measured in the study. The distinction is not about measurability but about whether the variable was included in the analysis.
- C
- Incorrect because both lurking and confounding variables can have direct or indirect effects on the response. The distinction is about whether they were included in the study, not about the causal pathway.
- D
- Incorrect because both lurking and confounding variables are relevant concerns in observational studies. Confounding can occur in experiments too if the experiment is not well-controlled, though randomization mitigates it.
A research team studies the effect of tutoring on math achievement. They compare students who voluntarily attended tutoring sessions with students who did not. The tutored students scored higher on the final exam. The researchers report that tutoring causes improved math scores. A statistician identifies a likely confounding variable. Which of the following is the most plausible confounding variable?
- AThe time of day when the exam was administered
- BThe color of the test paper used for the exam
- CStudents' motivation to learn mathCorrect
- DThe number of exam questions
Why C is right
Student motivation is a plausible confounding variable because it is associated with both the explanatory variable (seeking tutoring) and the response variable (test scores). Motivated students are more likely to attend tutoring AND more likely to study harder and score well, regardless of tutoring. Without random assignment, motivation confounds the comparison.
Why the other 3 choices miss
- A
- Incorrect because the time of the exam is presumably the same for all students and would not differentially affect tutored versus non-tutored students.
- B
- Incorrect because test paper color is unlikely to affect performance and is presumably the same for all students.
- D
- Incorrect because the number of exam questions is the same for all students and does not vary between groups.