Multi-Focus on Practices 1 and 2

Design a causal school study: AP Stats FRQ practice

3 versions of one AP Statistics free-response question, each with a 10-point rubric and a model answer for every point. Write your response on paper before you open the rubric.

These are StatsLearn originals written in the AP style, not released exam questions. Topics: 1.10 The Investigative Question Revisited and Data Collection, 1.11 Random Sampling, 1.12 Potential Problems with Sampling, 1.13 Experimental Design.

Version 1

A school district with 1800 students wants to study whether a new reminder program causes students to submit assignments on time. It will select 120 students and compare the program with the current reminder.

  1. (a) Write the investigative question and identify both variables.
  2. (b) Describe a design that supports both a population generalization and a causal conclusion. Explain the purpose of its main features.
  3. (c) Suppose only 82% of selected students answer a follow-up survey about why they submitted late. Name the concern and describe two safeguards or limits.
Show the rubric and model answers

Part (a): 2 points

  • States a causal investigative question about the program and on-time submission. Ask whether assigning the new reminder program causes a change in the proportion of assignments submitted on time among district students.
  • Identifies the explanatory and response variables. The explanatory variable is assigned reminder type. The response is whether an assignment is submitted on time.

Part (b): 5 points

  • Uses a simple random sample from the district roster. Label all 1800 students and use a random number generator to select 120 distinct students.
  • Randomly assigns sampled students to reminder groups. Use a chance device to assign each selected student to the new or current reminder group.
  • Keeps a comparison group receiving the current reminder. The current-reminder group is the control group and provides the baseline comparison.
  • Explains replication. Using 120 students gives many experimental units in each treatment group, so the comparison is replicated.
  • Explains the scope earned by random sampling and assignment. Random sampling supports generalization to district students, and random assignment supports a cause-and-effect conclusion.

Part (c): 3 points

  • Names nonresponse as a possible problem. If only 82% of selected students answer the follow-up survey, their reasons for submitting late may differ from the reasons among students who do not answer.
  • Uses an objective outcome to limit response bias. Use the electronic submission timestamp instead of asking students whether they submitted on time.
  • Does not claim random assignment makes the groups identical. Random assignment uses chance to distribute other variables. Any observed difference can still reflect the treatment or chance variation.

Version 2

A school district with 2280 students wants to study whether a new reminder program causes students to submit assignments on time. It will select 152 students and compare the program with the current reminder.

  1. (a) Write the investigative question and identify both variables.
  2. (b) Describe a design that supports both a population generalization and a causal conclusion. Explain the purpose of its main features.
  3. (c) Suppose only 78% of selected students answer a follow-up survey about why they submitted late. Name the concern and describe two safeguards or limits.
Show the rubric and model answers

Part (a): 2 points

  • States a causal investigative question about the program and on-time submission. Ask whether assigning the new reminder program causes a change in the proportion of assignments submitted on time among district students.
  • Identifies the explanatory and response variables. The explanatory variable is assigned reminder type. The response is whether an assignment is submitted on time.

Part (b): 5 points

  • Uses a simple random sample from the district roster. Label all 2280 students and use a random number generator to select 152 distinct students.
  • Randomly assigns sampled students to reminder groups. Use a chance device to assign each selected student to the new or current reminder group.
  • Keeps a comparison group receiving the current reminder. The current-reminder group is the control group and provides the baseline comparison.
  • Explains replication. Using 152 students gives many experimental units in each treatment group, so the comparison is replicated.
  • Explains the scope earned by random sampling and assignment. Random sampling supports generalization to district students, and random assignment supports a cause-and-effect conclusion.

Part (c): 3 points

  • Names nonresponse as a possible problem. If only 78% of selected students answer the follow-up survey, their reasons for submitting late may differ from the reasons among students who do not answer.
  • Uses an objective outcome to limit response bias. Use the electronic submission timestamp instead of asking students whether they submitted on time.
  • Does not claim random assignment makes the groups identical. Random assignment uses chance to distribute other variables. Any observed difference can still reflect the treatment or chance variation.

Version 3

A school district with 2760 students wants to study whether a new reminder program causes students to submit assignments on time. It will select 184 students and compare the program with the current reminder.

  1. (a) Write the investigative question and identify both variables.
  2. (b) Describe a design that supports both a population generalization and a causal conclusion. Explain the purpose of its main features.
  3. (c) Suppose only 74% of selected students answer a follow-up survey about why they submitted late. Name the concern and describe two safeguards or limits.
Show the rubric and model answers

Part (a): 2 points

  • States a causal investigative question about the program and on-time submission. Ask whether assigning the new reminder program causes a change in the proportion of assignments submitted on time among district students.
  • Identifies the explanatory and response variables. The explanatory variable is assigned reminder type. The response is whether an assignment is submitted on time.

Part (b): 5 points

  • Uses a simple random sample from the district roster. Label all 2760 students and use a random number generator to select 184 distinct students.
  • Randomly assigns sampled students to reminder groups. Use a chance device to assign each selected student to the new or current reminder group.
  • Keeps a comparison group receiving the current reminder. The current-reminder group is the control group and provides the baseline comparison.
  • Explains replication. Using 184 students gives many experimental units in each treatment group, so the comparison is replicated.
  • Explains the scope earned by random sampling and assignment. Random sampling supports generalization to district students, and random assignment supports a cause-and-effect conclusion.

Part (c): 3 points

  • Names nonresponse as a possible problem. If only 74% of selected students answer the follow-up survey, their reasons for submitting late may differ from the reasons among students who do not answer.
  • Uses an objective outcome to limit response bias. Use the electronic submission timestamp instead of asking students whether they submitted on time.
  • Does not claim random assignment makes the groups identical. Random assignment uses chance to distribute other variables. Any observed difference can still reflect the treatment or chance variation.

Keep going