Collecting Data review games for AP Statistics.
This unit covers sampling methods, observational studies, experiments and bias — essential concepts for AP Statistics. Use our interactive study games to test your understanding, or review questions in traditional format below.
Pick a mode. Play.
Answer questions as fast as you can. 2 minutes on the clock. Build streaks for bonus points!
Don't want to play?
Review the questions traditionally. Click to expand.
Questions loading...
Focus on understanding.
Focus on understanding core concepts before memorizing details. Use the game modes to test yourself repeatedly — spaced repetition is proven to boost long-term retention.
Ready for college?
This unit covers sampling methods, observational studies, experiments and bias — essential concepts for AP Statistics. Use our interactive study games to test your understanding, or review questions in traditional format below.
Key Concepts Breakdown
1 Sampling Methods
Students must be able to identify and distinguish between simple random sampling (SRS), stratified random sampling, cluster sampling, systematic sampling, and convenience sampling. The exam tests whether students can recognize which method was used in a scenario and explain why a method does or does not produce a representative sample. Understanding that only probability-based sampling methods allow valid inference to the population is critical.
Key Points
- SRS: every individual and every group of size n has an equal chance of selection — use a random number table or generator
- Stratified: population divided into homogeneous groups (strata), then SRS taken from each; reduces variability
- Cluster: population divided into heterogeneous groups (clusters), then entire clusters randomly selected; used for practicality
- Convenience and voluntary response samples are biased and cannot support inference — always identify these as flawed
A principal wants to survey 60 students about cafeteria food. She divides the school into grade levels (9, 10, 11, 12) and randomly selects 15 students from each grade. What sampling method is this, and what is its advantage over SRS?
This is stratified random sampling because the population is divided into subgroups (grades) and an SRS is drawn from each stratum. The advantage is that it guarantees representation from every grade level, which reduces sampling variability compared to SRS, which might by chance under-represent a grade. On the exam, you must name the method AND justify why it is appropriate or advantageous.
2 Observational Studies
In an observational study, researchers measure variables without imposing any treatment — they simply observe. Because no random assignment occurs, observational studies cannot establish causation; they can only identify associations. The exam frequently asks students to distinguish observational studies from experiments and to explain why causation cannot be concluded.
Key Points
- No manipulation of variables — researcher observes and records naturally occurring behavior
- Confounding variables (lurking variables) are always a threat; an observed association may be explained by a third variable
- Retrospective studies look backward at existing records; prospective studies follow subjects forward in time — both are observational
- Correct language: 'there is an association between X and Y,' never 'X causes Y' for observational data
Researchers examine hospital records and find that patients who received more frequent nurse check-ins had shorter hospital stays. A student concludes that frequent check-ins cause faster recovery. Is this conclusion justified?
No — this is an observational study because no treatment was randomly assigned; the researchers simply examined existing records. The conclusion of causation is not justified because confounding variables exist: for example, less severely ill patients may naturally recover faster AND receive more routine check-ins. On the exam, you must identify the study type, name a plausible confounding variable, and use the word 'association' rather than 'causation.'
3 Experiments
A well-designed experiment must include random assignment of treatments to experimental units, which is the only design feature that allows a cause-and-effect conclusion. Students must know the three principles of experimental design — control, randomization, and replication — and must be able to identify and explain control groups, placebo effects, blinding, and blocking. The exam will ask students to design an experiment or critique a flawed one.
Key Points
- Random assignment (not random sampling) is what allows causal inference — it balances confounding variables across treatment groups
- Control group provides a baseline; placebo controls for the psychological effect of receiving treatment
- Double-blind: neither subjects nor evaluators know treatment assignment — eliminates response bias and evaluator bias
- Blocking: group experimental units by a known source of variability (e.g., sex, age) before random assignment — reduces variability within blocks, analogous to stratification in sampling
A researcher wants to test whether a new study app improves SAT math scores. She randomly assigns 50 students to use the app for 8 weeks and 50 students to use no supplemental tool. Both groups take a pre-test and post-test. Identify the experimental units, explanatory variable, response variable, and one improvement to the design.
Experimental units are the 50+50 students; the explanatory variable is app use (app vs. no app); the response variable is change in SAT math score. One improvement would be to use a placebo — have the control group use a 'sham' app with no educational content — so that any improvement from merely using an app (Hawthorne effect) is controlled. Alternatively, blocking by initial math ability would reduce variability. Exams often award points for identifying the improvement AND explaining why it strengthens the study.
4 Bias
Bias is a systematic tendency for a sample statistic to over- or underestimate the population parameter. Students must be able to identify sources of bias by name, explain the direction of the bias (will responses be too high or too low?), and distinguish bias from variability. Increasing sample size does not reduce bias — only changing the design does.
Key Points
- Sampling bias: non-probability samples (voluntary response, convenience) systematically exclude parts of the population
- Response bias: question wording, social desirability, or interviewer presence causes subjects to answer inaccurately
- Undercoverage bias: some groups in the population have little or no chance of being selected (e.g., online survey excludes those without internet)
- Nonresponse bias: individuals selected for the sample who do not respond likely differ systematically from those who do — cannot be fixed by selecting more people
A magazine publishes an online poll asking readers: 'Do you agree that violent video games are destroying America's youth?' Of the 10,000 people who responded, 84% agreed. Identify two sources of bias and explain how each affects the results.
First, voluntary response bias: only readers who feel strongly (likely those who agree) bother to respond, inflating the percentage who agree. Second, response bias from question wording: the loaded phrase 'destroying America's youth' nudges respondents toward agreement, further inflating the 'agree' percentage. Both biases push the estimate in the same direction — upward — making 84% a severe overestimate of the true population proportion. On the exam, always state the name of the bias, identify the mechanism, and specify the direction of distortion.
Questions, answered.
What is Collecting Data?
Collecting Data is Unit 3 of AP Statistics, covering sampling methods, observational studies, experiments and bias.
How to study for AP Statistics Unit 3?
Start with the Quick Summary above, review the Key Concepts, then test yourself with our interactive study games. Aim for 80%+ accuracy before moving on.
How many questions are in this unit?
This unit has 27+ review questions across 5 different game modes.