AP Statistics Unit 1 Practice Test: Data and Study Design
Unit 1: Exploring One-Variable Data and Collecting Data
20 exam-style multiple-choice questions on describing data and designing studies, free to use in class. Good practice before the Unit 1 Progress Check in AP Classroom. Free response for this unit: Unit 1 FRQ set.
Sigma Prep · sigmaprep.io/worksheets/ap-statistics
Name
AP Statistics Unit 1: Data and Study Design
Date
Directions: Work each problem in the space below it, then choose the best of the four answer choices. A graphing calculator with statistical capabilities may be used on every question, as on the exam, and the exam’s formula sheet and tables apply. Some questions come in a set that refers to one shared stimulus.
Multiple choice
Questions 1–20- A sleep researcher wants to know whether a breathing app helps people fall asleep faster. For the study, 60 adults with trouble sleeping have volunteered. Half will use the breathing app at bedtime for two weeks, and the other half will use a similar app that plays only white noise. The adults will first be separated into blocks by age group; within each block, half of the adults will be randomly assigned to the breathing app and the rest will get the white-noise app. Which of the following describes the design of this experiment?
- (A)A matched pairs design
- (B)A completely randomized design
- (C)A stratified random sample
- (D)A randomized block design
- A greenhouse manager wants to compare two types of grow lights. She has 50 young basil plants available. Half of the plants will grow under LED lights and the other half under fluorescent lights for six weeks. Which of the following procedures randomly assigns the 50 plants so that each treatment group has 25 plants?
- (A)Label the plants 1 to 50, use a random number generator to produce 25 labels (repeats allowed); those plants get LED lights and the rest get fluorescent lights.
- (B)Number the plants 1 to 50, write each number on one of 50 identical slips, mix them in a container, and draw 25 slips without replacement; those plants get LED lights and the other 25 get fluorescent lights.
- (C)Line up the plants in a row and give LED lights to every other plant, starting with the first.
- (D)For each plant, flip a coin: heads gets LED lights and tails gets fluorescent lights.
- A teacher wonders whether a larger font helps students read faster. For the study, 40 students were randomly selected from all students at the school. Each student will read the same passage printed in either 12-point or 16-point type. The 40 students will be randomly assigned to the two treatments, 20 to each. What are the experimental units in this experiment?
- (A)The 40 students
- (B)Reading time, in seconds
- (C)The 16-point type and the 12-point type
- (D)All students at the school
- A high school's student council collected data from every one of the 1,800 students at the school and found that 30% buy lunch in the cafeteria at least three times a week. Is statistical inference needed to estimate the proportion of all students at the school who buy lunch in the cafeteria at least three times a week?
- (A)No, because the number of students is very large, so any sample would be accurate.
- (B)No, because the data come from every member of the population, so 30% is the population value.
- (C)Yes, because every statistical study needs a confidence interval or a significance test.
- (D)Yes, because 30% is a sample statistic that estimates the population proportion.
- A swim coach recorded the number of laps each of 71 swimmers completed in a 20-minute practice set. Summary statistics for the data are shown in the table. Which of the following best describes the shape of the distribution, with a reason based on the statistics?
- (A)Skewed to the right, because the maximum is farther above than the minimum is below .
- (B)Roughly symmetric and mound-shaped, because the mean (30.13) and the median (32) are close.
- (C)Skewed to the left, because the mean (30.13) is less than the median (32).
- (D)Skewed to the right, because the mean (30.13) is less than the median (32).
Questions 6–7 refer to the following.
A school office recorded the number of pages its copier printed on each of 21 school days. The stemplot below shows the data.- What is the mean number of pages printed, in pages, rounded to two decimal places?
- (A)
- (B)
- (C)
- (D)
- What is the interquartile range (IQR) of the numbers of pages printed, in pages?
- (A)
- (B)
- (C)
- (D)
Questions 8–9 refer to the following.
An English teacher counted the length, in hundreds of words, of 19 essays written for each of two prompts, a narrative prompt and an argument prompt. The dotplots below show the data.- Based on the display, which of the following statements is true?
- (A)The range of the essay length values for argument essays is greater than that for narrative essays.
- (B)The median essay length for argument essays is greater than the median essay length for narrative essays.
- (C)For narrative essays, the mean essay length is greater than the median essay length.
- (D)The third quartile essay length for argument essays is greater than the third quartile essay length for narrative essays.
- I. For argument essays, the mean essay length is less than the median essay length.
II. The first quartile essay length for argument essays is less than the first quartile essay length for narrative essays.
III. The maximum essay length for narrative essays is greater than the maximum essay length for argument essays.
Which of the statements above are supported by the display?- (A)II only
- (B)III only
- (C)I and II only
- (D)I, II, and III
- An online store wants to know whether a personalized email subject line gets more customers to open its email. For the study, 800 customers were randomly selected from all customers of the store. Some will receive the email with a personalized subject line and the others with a standard subject line. The 800 customers will be randomly assigned to the two treatments, 400 to each. After the study, a greater proportion of the customers with the personalized subject line opened the email, and the difference was statistically significant. Which of the following is the most appropriate conclusion?
- (A)The results should be generalized only to customers like those in the study, because only the treatments, not the customers, were chosen at random, and it can be concluded that the personalized subject line caused the difference in whether the customer opens the email, because the treatments were randomly assigned.
- (B)The results should be generalized only to customers like those in the study, because the customers were not randomly selected, and it cannot be concluded that the personalized subject line caused the difference in whether the customer opens the email, because nothing was randomly assigned.
- (C)The results can be generalized to all customers of the store, because the customers were randomly selected from that population, and it cannot be concluded that the personalized subject line caused the difference in whether the customer opens the email, because nothing was randomly assigned.
- (D)The results can be generalized to all customers of the store, because the customers were randomly selected from that population, and it can be concluded that the personalized subject line caused the difference in whether the customer opens the email, because the treatments were randomly assigned.
- A museum recorded the ages, in years, of the 14 volunteers who guided tours last summer. The age values, in years, are 47, 47, 49, 47, 39, 48, 31, 47, 44, 46, 49, 39, 48, 49. Later, the smallest value, 31 years, was found to be an entry error; the correct value is 34 years. Consider these statements about the effect of correcting the error.
I. The standard deviation will decrease.
II. The interquartile range will stay the same.
III. The median will stay the same.
Which of the statements are true?- (A)I and II only
- (B)I and III only
- (C)II and III only
- (D)I, II, and III
- An orchard worker weighed 23 apples picked from one row of trees. Summary statistics for the data are shown in the table. Using the rule, what is the upper boundary (fence) for outliers, in grams?
- (A)
- (B)
- (C)
- (D)
- A housing nonprofit wants to estimate the proportion of renters in the city who spend more than 30% of their income on rent. The nonprofit separates the renters by neighborhood income level (lower-income areas, middle-income areas and higher-income areas) and randomly selects 133 renters from each neighborhood income level. Which of the following is the best reason to stratify by neighborhood income level?
- (A)The answers are likely to differ from one neighborhood income level to another, so stratifying by neighborhood income level gives an estimate with less variability than a simple random sample of the same size.
- (B)Stratifying removes all bias, so the sample proportion will equal the proportion for all renters in the city.
- (C)Stratifying needs fewer renters to be surveyed than a simple random sample does.
- (D)Stratifying lets the results be generalized to all renters in the state.
- A researcher selected a random sample of 250 teenagers from a large city. She asked each one how many minutes a night, on average, they spent on a phone after 9 in the evening during the past month, and she recorded each teen's average hours of sleep per night for that month from a fitness tracker. She called the teens who averaged more than 60 minutes a night late-night phone users. The researcher compared the teenagers who were late-night phone users with those who were not. The results showed that the late-night phone users slept fewer hours per night, on average, than the other teenagers. Which of the following best explains why the study does not show that the difference in average hours of sleep per night is caused by whether the teenagers were late-night phone users?
- (A)The teenagers were randomly selected instead of volunteering.
- (B)The sample of 250 teenagers is too small to show a difference in average hours of sleep per night.
- (C)The two groups may also differ in how much caffeine each teenager drinks in the evening, which could explain the difference in average hours of sleep per night.
- (D)The average hours of sleep per night was measured only once for each teenager.
- A fish farm wants to compare two feeds. It has 60 young trout available, each in its own tank. Each fish will get feed X or feed Y for eight weeks. The 60 trout will be randomly assigned to the two treatments, 30 to each. After the study, the fish fed feed X gained more weight on average, and the difference was statistically significant. Consider the following statements about the conclusions of this study.
I. The study shows that feed X caused the difference in weight gained in eight weeks.
II. The results can be generalized to all young trout raised on fish farms.
III. Because the treatments were randomly assigned, other variables should be roughly balanced between the treatment groups.
Which of the statements are correct?- (A)I only
- (B)I and II only
- (C)I and III only
- (D)I, II, and III
- A paint company wants to compare two formulas of outdoor paint. It has 40 wooden boards available. Each board will be painted with formula A or formula B and left outside for a year. The 40 boards will be randomly assigned to the two treatments, 20 to each, and an inspector who rates the peeling will record each board's percent of the surface that has peeled after a year. What is the main purpose of the group that gets formula B?
- (A)It doubles the number of boards measured, which is what replication means.
- (B)It lets the results be generalized to all wooden boards used outdoors.
- (C)It makes the experiment more ethical, because fewer boards receive formula A.
- (D)It gives a comparison group, so the results with formula A can be judged against the results with formula B.
- A hardware store listed the prices, in dollars, of 23 power tools. The mean was 71.1 dollars, the median was 69.1 dollars, the third quartile was 80.1 dollars, the standard deviation was 19.0 dollars, and the interquartile range was 23.3 dollars. The store then added an 8% sales tax to every price and then a 2-dollar recycling fee. What is the standard deviation of the new price values, in dollars?
- (A)
- (B)
- (C)
- (D)
- A county library system wants to learn, for card holders of the library system, whether they borrowed an e-book in the past year. The library system randomly chooses one of the first 160 card holders on the list of library card holders and then selects every 160th name after it on the list. Which of the following best describes the sampling method?
- (A)A stratified random sample of the card holders
- (B)A systematic random sample of the card holders
- (C)A voluntary response sample of the card holders
- (D)A cluster sample of the card holders
- A science museum wants to estimate the proportion of visitors to the museum this year who rated their visit 8 or higher. The museum invites visitors to post a rating on the museum's social media page. Which type of bias is most likely in this plan?
- (A)Voluntary response bias
- (B)Response bias
- (C)Nonresponse bias
- (D)Undercoverage
- A teacher recorded the scores, out of 50 points, of the 66 students in a class on a vocabulary quiz. The histogram below shows the data. How is the distribution of the quiz score values in the histogram shaped?
- (A)Bimodal
- (B)Approximately uniform
- (C)Roughly symmetric and mound-shaped
- (D)Skewed to the left
End of the multiple-choice questions
Answer key
| 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 |
|---|---|---|---|---|---|---|---|---|---|
| D | B | A | B | C | B | C | A | A | D |
| 1.13 | 1.13 | 1.10 | 1.10 | 1.8 | 1.7 | 1.7 | 1.9 | 1.9 | 1.10 |
| 11 | 12 | 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 |
|---|---|---|---|---|---|---|---|---|---|
| D | B | A | C | C | D | C | B | A | D |
| 1.7 | 1.7 | 1.11 | 1.10 | 1.10 | 1.13 | 1.7 | 1.11 | 1.12 | 1.6 |
The second row is the correct letter; the third is the course topic each question tests.
Worked solutions
1. Answer (D) Topic 1.13
- This is a randomized block design: the units are put into blocks by age group first, and the random assignment is done separately within each block.
- The answer is: A randomized block design.
2. Answer (B) Topic 1.13
- A valid random assignment uses a chance process to choose which 25 plants get LED lights, and gives the remaining 25 fluorescent lights, so the groups are equal in size.
- The answer is: Number the plants 1 to 50, write each number on one of 50 identical slips, mix them in a container, and draw 25 slips without replacement; those plants get LED lights and the other 25 get fluorescent lights.
3. Answer (A) Topic 1.10
- The experimental units are what the treatments are applied to: the 40 students.
- The answer is: The 40 students.
4. Answer (B) Topic 1.10
- This is a census: every member of the population was measured, so the proportion is known exactly and there is no sampling variability to account for.
- The answer is: No, because the data come from every member of the population, so 30% is the population value.
5. Answer (C) Topic 1.8
- From the table: mean 30.13, median 32; , , minimum 8, maximum 35.
- The mean (30.13) is less than the median (32), and the lower quarter of the data is spread over a longer interval, so the distribution is skewed to the left.
- The answer is: Skewed to the left, because the mean (30.13) is less than the median (32).
6. Answer (B) Topic 1.7
- The mean is the sum of all 21 values divided by 21: the sum is 3805.
- .
- So the mean number of pages printed is about pages.
7. Answer (C) Topic 1.7
- There are 21 values. Split the ordered data at the median (left out of both halves, since is odd): is the median of the lower half and the median of the upper half.
- From the stemplot, and , so .
- So the interquartile range is pages.
8. Answer (A) Topic 1.9
- Read each distribution from the dotplots. Narrative essays: minimum 9, first quartile 10, median 12, third quartile 13, maximum 14, mean 11.63. Argument essays: minimum 7, first quartile 7, median 9, third quartile 11, maximum 16, mean 9.53.
- The range for argument essays is 9 and the range for narrative essays is 5.
- Each of the other three statements is false: (B) the median for argument essays is 9 and the median for narrative essays is 12 (it is the maximum that is greater for argument essays); (C) the mean for narrative essays is 11.63 and the median is 12; (D) the third quartile for argument essays is 11 and the third quartile for narrative essays is 13 (it is the maximum that is greater for argument essays).
- The answer is: The range of the essay length values for argument essays is greater than that for narrative essays.
9. Answer (A) Topic 1.9
- Read each distribution from the dotplots. Narrative essays: minimum 9, first quartile 10, median 12, third quartile 13, maximum 14, mean 11.63. Argument essays: minimum 7, first quartile 7, median 9, third quartile 11, maximum 16, mean 9.53.
- Statement I is false: the mean for argument essays is 9.53 and the median is 9.
- Statement II is true: the first quartile for argument essays is 7 and the first quartile for narrative essays is 10.
- Statement III is false: the maximum for narrative essays is 14 and the maximum for argument essays is 16 (it is the third quartile that is greater for narrative essays).
- So only statement II is true. The answer is II only.
10. Answer (D) Topic 1.10
- The customers were randomly selected from customers of the store, so the results generalize to that population; the treatments were randomly assigned, so a cause-and-effect conclusion is possible.
- The answer is: The results can be generalized to all customers of the store, because the customers were randomly selected from that population, and it can be concluded that the personalized subject line caused the difference in whether the customer opens the email, because the treatments were randomly assigned.
11. Answer (D) Topic 1.7
- Changing 31 to 34 moves an extreme value closer to the rest of the data, but it stays the smallest value, so the order of the other values does not change.
- Statement I is true: the standard deviation goes from 5.20 to 4.61.
- Statement II is true: the interquartile range depends only on the middle of the ordered data, which does not change.
- Statement III is true: the median depends only on the middle of the ordered data, which does not change.
- So the true statements are I, II, and III. The answer is I, II, and III.
12. Answer (B) Topic 1.7
- , so .
- The upper fence is : values above it are outliers.
- So the upper fence is grams.
13. Answer (A) Topic 1.11
- Stratifying pays off when the response differs between the strata and is similar within each; then each stratum is represented and the estimate varies less from sample to sample.
- The answer is: The answers are likely to differ from one neighborhood income level to another, so stratifying by neighborhood income level gives an estimate with less variability than a simple random sample of the same size.
14. Answer (C) Topic 1.10
- In an observational study the groups form on their own, so a variable such as how much caffeine the teenager drinks in the evening, related to both whether the teenager was a late-night phone user and the average hours of sleep per night, is confounded with the explanatory variable.
- The answer is: The two groups may also differ in how much caffeine each teenager drinks in the evening, which could explain the difference in average hours of sleep per night.
15. Answer (C) Topic 1.10
- Statement I is true: the treatments were randomly assigned, so the significant difference can be attributed to them.
- Statement II is false: the trout were not randomly selected from young trout raised on fish farms.
- Statement III is true: random assignment tends to even out other variables between the treatment groups.
- So the true statements are I and III. The answer is I and III only.
16. Answer (D) Topic 1.13
- If every board got formula A, there would be nothing to compare the results with; the group given formula B shows the percent of the surface that has peeled after a year under the same conditions with the other treatment, so the two treatments can be compared.
- The answer is: It gives a comparison group, so the results with formula A can be judged against the results with formula B.
17. Answer (C) Topic 1.7
- Adding a constant to every value shifts the center and every position (mean, median, quartiles) by that constant but leaves the spread (SD, IQR, range) unchanged; multiplying every value by a positive constant multiplies the center, the positions and the spread by it.
- So the new standard deviation is dollars.
- The answer is dollars.
18. Answer (B) Topic 1.11
- This is a systematic random sample of the card holders: a random start is followed by every th unit on the list.
- The answer is: A systematic random sample of the card holders.
19. Answer (A) Topic 1.12
- This plan has voluntary response bias: people choose themselves by replying, and those with strong feelings are the most likely to reply; here, only the visitors who choose to reply are in the sample.
- The answer is: Voluntary response bias.
20. Answer (D) Topic 1.6
- Look at the bar heights from left to right: 1, 2, 1, 9, 9, 12, 32.
- The distribution is skewed to the left: most values are on the right with a long tail of smaller values to the left; in the raw data (not shown), the mean (40.24) is below the median (41).
- The answer is: Skewed to the left.
Free AP Statistics worksheets at sigmaprep.io/worksheets/ap-statisticsOriginal questions written by Sigma Prep. AP is a registered trademark of the College Board, which is not affiliated with this sheet.
What does the AP Statistics exam ask on Unit 1?
Unit 1 is the biggest unit of the AP Statistics multiple choice: 132 of the 406 official multiple-choice questions on today's course (32.5%), and 7 of the 24 sample questions in the 2026 course description, the only ones in the 2027 format.
- Describing and comparing distributions is the larger half. Topics 1.6 to 1.9 (shape, summary statistics, boxplots, comparing groups) hold 73 of the 132 Unit 1 questions; collecting data (topics 1.10 to 1.13) holds 56. Topic 1.7, summary statistics, is the single biggest topic, with 35.
- Scope of inference is the study-design question to know. 11 official multiple-choice questions on 9 of the 13 sources ask what a study's design lets you conclude, and 7 free-response questions from 2012 to 2026 had a part on it.
- Reading summary statistics comes up everywhere. Computing or reading a median, quartiles, a mean or a standard deviation has 11 official multiple-choice questions, 8 of them on the six 2012–2019 practice exams.
- Questions come in sets on the 2027 exam. 6 of the 24 sample questions in the 2026 course description are in 2 sets that share one stimulus. This sheet has two sets of two questions.
- New topics have no official question yet. The 2026 course added bar charts and pie charts for one categorical variable, frequency and relative frequency tables for one categorical variable, and prospective and retrospective observational studies. No official question has asked about them, so they are left off this sheet.
The most-tested kind here is computing or reading summary statistics, with 11 official questions; every question on this sheet is original, and every answer was checked by an independent computer check.
Counted from the official AP Statistics questions: multiple choice from 13 College Board sources, 1997–2026, and free response 2012–2026. No official question is reproduced here.
How often does the AP Statistics exam ask each Unit 1 question type?
Multiple-choice counts are of the 406 official questions on today’s course whose main topic is that kind, from 13 College Board sources: the 1997, 2002 and 2007 released exams, the 2008, 2012–2015, 2018 and 2019 practice exams, and the sample questions in the 2005, 2020 and 2026 course descriptions. Free-response counts are of the 84 operational questions, 2012–2026 (no 2020 exam was released), with a part on that kind. Not on this sheet (asked less often): read, construct or match a boxplot; describe how to select a random sample; interpret and compare standard deviation; z-scores and relative position; classify a variable (categorical vs quantitative; discrete vs continuous); identify population and sample; percentiles and cumulative relative frequency; choose or critique a graphical display (what it shows or hides); write or evaluate a valid investigative question; construct or read a histogram, stemplot or dotplot; identify observational units, variables, parameters and statistics; components and purpose of a statistical study. New to the 2026 course, with no official question yet: bar charts and pie charts for one categorical variable; frequency and relative frequency table for one categorical variable; prospective vs retrospective observational study.
Questions about this worksheet
AP is a registered trademark of the College Board, which was not involved in making this worksheet and does not endorse it. All questions are original to Sigma Prep. Frozen 2026-11-19.