Worksheets · AP Statistics

AP Statistics Unit 4 Practice Test: Inference for Means

Unit 4: Inference for Quantitative Data: Means

20 exam-style multiple-choice questions on inference for means, free to use in class. Good practice before the Unit 4 Progress Check in AP Classroom. Free response for this unit: Unit 4 FRQ set.

Sigma Prep · sigmaprep.io/worksheets/ap-statistics

Name

AP Statistics Unit 4: Inference for Means

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
  1. The label on a new exterior paint says that it dries in 4 hours on average. A painting contractor suspects that the mean drying time of all gallons of the new exterior paint is greater than 4 hours. The painting contractor selected a random sample of 20 gallons and recorded the drying time of each. The sample mean was 4.33 hours, and the sample standard deviation was 0.49 hours. The painting contractor tested H0:μ=4H_0: \mu = 4 against Ha:μ>4H_a: \mu > 4, where μ\mu is the mean drying time of all gallons of the new exterior paint. All conditions for inference were met, and the P-value of the test was 0.0036. Which of the following is an appropriate conclusion at the α=0.05\alpha = 0.05 level?
    1. (A)The P-value of 0.0036 is less than α=0.05\alpha = 0.05, so the null hypothesis is not rejected. There is not convincing statistical evidence that the mean drying time of all gallons of the new exterior paint is greater than 4 hours.
    2. (B)The P-value of 0.0036 is less than α=0.05\alpha = 0.05, so the null hypothesis is rejected. There is convincing statistical evidence that proves that the mean drying time of all gallons of the new exterior paint is greater than 4 hours.
    3. (C)The P-value of 0.0036 is less than α=0.05\alpha = 0.05, so the null hypothesis is rejected. There is convincing statistical evidence that the mean drying time of the 20 sampled gallons is greater than 4 hours.
    4. (D)The P-value of 0.0036 is less than α=0.05\alpha = 0.05, so the null hypothesis is rejected. There is convincing statistical evidence that the mean drying time of all gallons of the new exterior paint is greater than 4 hours.
  2. The reading coordinator of a large school district selected a random sample of 24 fourth graders to construct a one-sample tt interval for the mean oral reading rate of all fourth graders in the school district. Which of the following describes how the normal/large sample condition for the interval is checked?
    1. (A)A graph of the 24 sample values shows no strong skewness and no outliers.
    2. (B)The sample size, 24, is large enough for the central limit theorem.
    3. (C)The sample size, 24, is less than 10% of all fourth graders in the school district.
    4. (D)The data come from a random sample of fourth graders.
  3. To estimate the mean serving temperature of all cups of coffee served at a coffee chain's drive-through windows, the quality manager of the coffee chain selected a random sample of 40 cups and recorded the serving temperature of each. The sample mean was 164.07 degrees Fahrenheit, and the sample standard deviation was 5.54 degrees Fahrenheit. A 95% confidence interval for the mean serving temperature of all cups of coffee served at the coffee chain's drive-through windows is (162.30,165.84)(162.30, 165.84). Which of the following is a correct interpretation of the 95% confidence level?
    1. (A)If many random samples of 40 cups were selected and an interval were built the same way from each, about 95% of the intervals would contain 164.07 degrees Fahrenheit.
    2. (B)About 95% of all cups of coffee served at the coffee chain's drive-through windows have a serving temperature between 162.30 and 165.84 degrees Fahrenheit.
    3. (C)About 95% of all random samples of 40 cups will have a sample mean between 162.30 and 165.84 degrees Fahrenheit.
    4. (D)If many random samples of 40 cups were selected and an interval were built the same way from each, about 95% of the intervals would capture the mean serving temperature of all cups of coffee served at the coffee chain's drive-through windows.
  4. A forester wants to compare the heights of mature pine trees in two state forests. The forester will select independent random samples of 40 pines in the north forest and 40 pines in the south forest and record the height of each. The goal is to decide whether the mean height of all mature pines in the north forest is different from the mean height of all mature pines in the south forest. Which of the following is the most appropriate procedure?
    1. (A)A one-sample tt-test for a population mean
    2. (B)A two-sample tt-interval for a difference between two population means
    3. (C)A two-sample tt-test for a difference between two population means
    4. (D)A two-sample zz-test for a difference between two population proportions
  5. To estimate the mean weight of all sourdough loaves from a bakery, the inspector at the bakery selected a random sample of 17 loaves and recorded the weight of each, in grams. The data are 791, 785, 803, 807, 785, 783, 799, 795, 778, 783, 801, 785, 794, 804, 797, 811, 775. Assume the conditions for inference are met. Which of the following is a 95% confidence interval for the mean weight of all sourdough loaves from the bakery?
    1. (A)(770.2,815.2)(770.2, 815.2)
    2. (B)(787.2,798.2)(787.2, 798.2)
    3. (C)(790.1,795.3)(790.1, 795.3)
    4. (D)(791.4,794.0)(791.4, 794.0)
  6. Questions 6–7 refer to the following.

    To estimate the mean daily energy output of all SunTile rooftop solar panels in a sunny region, an installer selected a random sample of 38 panels and recorded the daily energy output of each. The sample mean was 1.733 kilowatt-hours, and the sample standard deviation was 0.127 kilowatt-hours.
  7. Assume the conditions for inference are met. Which of the following is a 95% confidence interval for the mean daily energy output of all SunTile rooftop solar panels in the sunny region?
    1. (A)(1.476,1.990)(1.476, 1.990)
    2. (B)(1.677,1.789)(1.677, 1.789)
    3. (C)(1.691,1.775)(1.691, 1.775)
    4. (D)(1.712,1.754)(1.712, 1.754)
  8. A 90% confidence interval for the mean daily energy output of all SunTile rooftop solar panels in the sunny region is (1.698,1.768)(1.698, 1.768). The installer has heard a claim that the mean daily energy output of all SunTile rooftop solar panels in the sunny region is no longer 1.68 kilowatt-hours. Which of the following is the best conclusion about the claim?
    1. (A)Because every value in the interval is greater than 1.68, the interval gives convincing evidence that the mean daily energy output of all SunTile rooftop solar panels in the sunny region is no longer 1.68 kilowatt-hours.
    2. (B)Because the sample mean, 1.733, is greater than 1.68, the sample gives convincing evidence that the mean daily energy output of all SunTile rooftop solar panels in the sunny region is no longer 1.68 kilowatt-hours.
    3. (C)Because every value in the interval is greater than 1.68, the interval proves that the mean daily energy output of all SunTile rooftop solar panels in the sunny region is no longer 1.68 kilowatt-hours.
    4. (D)Because the interval does not contain 1.68, the interval does not give convincing evidence that the mean daily energy output of all SunTile rooftop solar panels in the sunny region is no longer 1.68 kilowatt-hours.
  9. To estimate the mean time to hike the summit trail of all adult hikers on the trail, a park ranger selected a random sample of 54 hikers and recorded the time to hike the summit trail of each. The sample mean was 87.1 minutes, and the sample standard deviation was 11.5 minutes. A 99% confidence interval for the mean time to hike the summit trail of all adult hikers on the trail was constructed. Suppose a random sample of 216 hikers had been used instead, with about the same mean and standard deviation. How would the width of the 99% interval compare?
    1. (A)About one-fourth as wide, because the sample is four times as large.
    2. (B)About twice as wide, because a larger sample has more variability.
    3. (C)About half as wide, because the width is proportional to 1n\frac{1}{\sqrt{n}} (with t∗t^* a little smaller too).
    4. (D)About the same width, because the confidence level is the same.
  10. The distribution of the scores of students who take a statewide 100-point placement test is skewed to the left, with mean 78 points and standard deviation 9 points. About 90,000 students take the test each year. A random sample of 6 students will be selected, and the sample mean xˉ\bar{x} will be computed.
    I. The standard deviation of the sampling distribution of xˉ\bar{x} is 9 points.
    II. The 6 values in the sample will have a distribution that is approximately normal.
    III. The mean of the sampling distribution of xˉ\bar{x} is 78 points.
    Which of the statements above are true?
    1. (A)III only
    2. (B)I and III only
    3. (C)II and III only
    4. (D)I, II, and III
  11. The distribution of the wash time of cars washed at a busy car wash is skewed to the right, with mean 10 minutes and standard deviation 3 minutes. The car wash serves about 120,000 cars a year. A random sample of 64 cars will be selected, and the sample mean xˉ\bar{x} will be computed. Which of the following best describes the sampling distribution of xˉ\bar{x}?
    1. (A)Approximately normal, with mean 10 minutes and standard deviation 3 minutes
    2. (B)Approximately normal, with mean 10 minutes and standard deviation 0.047 minutes
    3. (C)Skewed to the right, with mean 10 minutes and standard deviation 0.375 minutes
    4. (D)Approximately normal, with mean 10 minutes and standard deviation 0.375 minutes
  12. A shopper selected a random sample of 10 items sold at both of two grocery stores and recorded each item's price, in dollars, at each store. About 9,000 items are sold at both stores. A 90% confidence interval for the mean difference (Store B minus Store A) is (−0.11,0.45)(-0.11, 0.45) dollars. Which of the following is a correct interpretation of the interval?
    1. (A)There is a 90% probability that the mean difference in price (Store B minus Store A) for all items sold at both stores is between −0.11-0.11 and 0.45 dollars.
    2. (B)We are 90% confident that the interval from −0.11-0.11 to 0.45 dollars captures the mean difference for the 10 items in the sample.
    3. (C)We are 90% confident that the interval from −0.11-0.11 to 0.45 dollars captures the mean difference in price (Store B minus Store A) for all items sold at both stores.
    4. (D)About 90% of the items have a difference (Store B minus Store A) between −0.11-0.11 and 0.45 dollars.
  13. An engineer tested an additive that might change the strength of concrete. A total of 65 test cylinders were randomly assigned to the additive (25) or the standard mix (40). The compressive strength, in megapascals, of the test cylinders made with the additive had mean 30.04 and standard deviation 1.83; the test cylinders made without it had mean 31.48 and standard deviation 1.53. The engineer will test H0:μ1−μ2=0H_0: \mu_1 - \mu_2 = 0 against Ha:μ1−μ2≠0H_a: \mu_1 - \mu_2 \neq 0, where μ1\mu_1 is the mean strength of concrete made with the additive and μ2\mu_2 is the mean strength of concrete made without the additive. Assume the conditions for inference are met. What is the value of the test statistic?
    1. (A)−4.87-4.87
    2. (B)−3.93-3.93
    3. (C)−3.42-3.42
    4. (D)−3.28-3.28
  14. The maker of the Volta electric scooter advertises a mean range of 25 miles on a full charge. A consumer magazine suspects that the mean range on a full charge of all electric scooters of the Volta model is less than 25 miles. The consumer magazine selected a random sample of 19 scooters and recorded the range on a full charge of each. The sample mean was 22.65 miles, and the sample standard deviation was 2.73 miles. The consumer magazine tested H0:μ=25H_0: \mu = 25 against Ha:μ<25H_a: \mu < 25, where μ\mu is the mean range on a full charge of all electric scooters of the Volta model. Assume the conditions for inference are met. What is the value of the test statistic?
    1. (A)−3.75-3.75
    2. (B)−1.37-1.37
    3. (C)−0.86-0.86
    4. (D)36.1636.16
  15. A nurse selected a random sample of 12 patients at a large clinic and took each patient's temperature, in degrees Fahrenheit, with an oral thermometer and with an ear thermometer. The nurse wants to know whether there is a difference. Which of the following is the most appropriate procedure?
    1. (A)A two-sample tt-test for a difference between two population means
    2. (B)A matched-pairs tt-test for a mean difference
    3. (C)A matched-pairs tt-interval for a mean difference
    4. (D)A two-sample zz-test for a difference between two population proportions
  16. The distribution of the weight of eggs from a large poultry farm is approximately normal, with mean 60 grams and standard deviation 4 grams. The poultry farm produces about 5,000,000 eggs a month. A random sample of 18 eggs will be selected. What is the standard deviation of the sampling distribution of the sample mean xˉ\bar{x}?
    1. (A)0.2220.222
    2. (B)0.9430.943
    3. (C)3.7713.771
    4. (D)4.0004.000
  17. A bookstore chain compared what customers spend at its downtown store and at its mall store. The downtown store has about 50,000 customers a year, and the mall store has about 70,000. Independent random samples of 29 downtown customers and 42 mall customers were selected. The amount spent per visit, in dollars, of the downtown customers had mean 31.83 and standard deviation 10.38; the mall customers had mean 28.97 and standard deviation 8.82. The chain's manager tested H0:μ1−μ2=0H_0: \mu_1 - \mu_2 = 0 against Ha:μ1−μ2>0H_a: \mu_1 - \mu_2 > 0, where μ1\mu_1 is the mean amount spent per visit by all downtown customers and μ2\mu_2 is the mean amount spent per visit by all mall customers. All conditions were met, and the P-value was 0.1154. Which of the following is an appropriate conclusion at the α=0.05\alpha = 0.05 level?
    1. (A)The P-value of 0.1154 is greater than α=0.05\alpha = 0.05, so the null hypothesis is not rejected. There is convincing statistical evidence that the mean amount spent per visit by all downtown customers is greater than the mean amount spent per visit by all mall customers.
    2. (B)The P-value of 0.1154 is greater than α=0.05\alpha = 0.05, so the null hypothesis is not rejected. There is convincing statistical evidence that the mean amount spent per visit by all downtown customers is equal to the mean amount spent per visit by all mall customers.
    3. (C)The P-value of 0.1154 is greater than α=0.05\alpha = 0.05, so the null hypothesis is not rejected. There is not convincing statistical evidence that the mean amount spent per visit by all downtown customers is greater than the mean amount spent per visit by all mall customers.
    4. (D)The P-value of 0.1154 is greater than α=0.05\alpha = 0.05, so the null hypothesis is rejected. There is convincing statistical evidence that the mean amount spent per visit by all downtown customers is greater than the mean amount spent per visit by all mall customers.
  18. A test statistic will be compared with the tt distribution with 6 degrees of freedom instead of the standard normal (zz) distribution.
    I. A value of tt more than 2 units from 0 is more likely with 6 degrees of freedom than a zz value that far from 0.
    II. Values of tt with 6 degrees of freedom are less spread out around 0 than values of zz.
    III. The density curve for tt with 6 degrees of freedom has the same shape on both sides of 0.
    Which of the statements above are true?
    1. (A)I only
    2. (B)III only
    3. (C)I and II only
    4. (D)I and III only
  19. The distribution of the length of bolts made by a machine is approximately normal, with mean 50 millimeters and standard deviation 0.8 millimeters. The machine makes about 2,000,000 bolts a month. A random sample of 25 bolts will be selected. What is the approximate probability that the mean length of the 25 bolts is greater than 50.22 millimeters?
    1. (A)0.08460.0846
    2. (B)0.39170.3917
    3. (C)0.41540.4154
    4. (D)0.91540.9154
  20. A harbor ferry's schedule lists a mean crossing time of 22 minutes. A riders' group suspects that the mean crossing time of all crossings of the harbor ferry is greater than 22 minutes. The riders' group selected a random sample of 22 crossings and recorded the crossing time of each. The sample mean was 22.16 minutes, and the sample standard deviation was 1.87 minutes. Let μ\mu be the mean crossing time of all crossings of the harbor ferry. Which of the following are appropriate hypotheses for the test?
    1. (A)H0:μ=22H_0: \mu = 22 and Ha:μ≠22H_a: \mu \neq 22
    2. (B)H0:μ=22H_0: \mu = 22 and Ha:μ>22H_a: \mu > 22
    3. (C)H0:μ>22H_0: \mu > 22 and Ha:μ=22H_a: \mu = 22
    4. (D)H0:μ=22.16H_0: \mu = 22.16 and Ha:μ>22.16H_a: \mu > 22.16
  21. A city compared the charging sessions at its two kinds of public electric-vehicle chargers. The fast chargers record about 80,000 sessions a year, and the standard chargers about 120,000. Independent random samples of 30 sessions at fast chargers and 32 sessions at standard chargers were selected. A two-sample tt interval for μ1−μ2\mu_1 - \mu_2 will be constructed, where μ1\mu_1 is the mean energy delivered in all sessions at the city's fast chargers and μ2\mu_2 is the mean energy delivered in all sessions at the city's standard chargers. Which of the following describes how the normal/large sample condition is met?
    1. (A)Each sample has at least 10 values above and at least 10 below its mean.
    2. (B)Both sample sizes, 30 and 32, are at least 30.
    3. (C)The combined sample size, 62, is at least 30.
    4. (D)Both samples were selected at random.

    End of the multiple-choice questions

Answer key

12345678910
DADCBCACAD
4.54.24.34.94.24.24.34.34.14.1
11121314151617181920
CDABBCDABB
4.34.104.54.44.14.104.24.14.44.7

The second row is the correct letter; the third is the course topic each question tests.

Worked solutions

1. Answer (D) Topic 4.5

  1. Compare the P-value with the significance level: 0.0036 is less than α=0.05\alpha = 0.05, so reject H0H_0.
  2. The conclusion is stated about the population mean, in the direction of HaH_a, as evidence and not proof.
  3. The answer is: The P-value of 0.0036 is less than α=0.05\alpha = 0.05, so the null hypothesis is rejected. There is convincing statistical evidence that the mean drying time of all gallons of the new exterior paint is greater than 4 hours.

2. Answer (A) Topic 4.2

  1. The normal/large sample condition makes the sampling distribution of xˉ\bar{x} approximately normal: a normal population, or n≥30n \ge 30, or (for a small sample) data with no strong skewness or outliers.
  2. n=24n = 24 is less than 30, so the sample data must be checked with a graph.
  3. The answer is: A graph of the 24 sample values shows no strong skewness and no outliers.

3. Answer (D) Topic 4.3

  1. The confidence level is a property of the method: the long-run share of intervals, over repeated random samples, that capture the parameter.
  2. It is not a probability about this one interval, about sample means, or about individual cups.
  3. The answer is: If many random samples of 40 cups were selected and an interval were built the same way from each, about 95% of the intervals would capture the mean serving temperature of all cups of coffee served at the coffee chain's drive-through windows.

4. Answer (C) Topic 4.9

  1. The response is quantitative and there are two independent samples with no pairing, so the parameter is the difference of two means, μ1−μ2\mu_1 - \mu_2.
  2. The question is whether the mean height of all mature pines in the north forest is different from the mean height of all mature pines in the south forest, which a significance test answers.
  3. The answer is: A two-sample tt-test for a difference between two population means.

5. Answer (B) Topic 4.2

  1. From the data, xˉ=792.71\bar{x} = 792.71 and s=10.62s = 10.62 grams (the sample SD divides by n−1n - 1).
  2. With df=16df = 16, t∗=2.120t^* = 2.120 for 95% confidence, and SE=sn=10.6217=2.58SE = \frac{s}{\sqrt{n}} = \frac{10.62}{\sqrt{17}} = 2.58.
  3. The margin of error is 2.120(2.58)=5.52.120(2.58) = 5.5.
  4. So the interval is 792.71±5.5792.71 \pm 5.5: (787.2,798.2)(787.2, 798.2).

6. Answer (C) Topic 4.2

  1. With df=37df = 37, t∗=2.026t^* = 2.026 for 95% confidence, and SE=sn=0.12738=0.0206SE = \frac{s}{\sqrt{n}} = \frac{0.127}{\sqrt{38}} = 0.0206.
  2. The margin of error is 2.026(0.0206)=0.0422.026(0.0206) = 0.042.
  3. So the interval is 1.733±0.0421.733 \pm 0.042: (1.691,1.775)(1.691, 1.775).

7. Answer (A) Topic 4.3

  1. A value inside a confidence interval is plausible; values outside it are not.
  2. Every value in the interval is greater than 1.68.
  3. The answer is: Because every value in the interval is greater than 1.68, the interval gives convincing evidence that the mean daily energy output of all SunTile rooftop solar panels in the sunny region is no longer 1.68 kilowatt-hours.

8. Answer (C) Topic 4.3

  1. The margin of error t∗snt^*\frac{s}{\sqrt{n}} changes with 1n\frac{1}{\sqrt{n}} when ss and the level stay about the same.
  2. Going from 54 to 216 multiplies n\sqrt{n} by 2.
  3. The answer is: About half as wide, because the width is proportional to 1n\frac{1}{\sqrt{n}} (with t∗t^* a little smaller too).

9. Answer (A) Topic 4.1

  1. Statement I is false: the value 99 is the SD of one value; the SD of xˉ\bar{x} is 96=3.674\frac{9}{\sqrt{6}} = 3.674.
  2. Statement II is false: the values in a sample look like the population, which is skewed to the left; it is xˉ\bar{x} that the central limit theorem is about.
  3. Statement III is true: the sample mean is an unbiased estimator: its mean is μ=78\mu = 78.
  4. So only statement III is true. The answer is III only.

10. Answer (D) Topic 4.1

  1. The mean of xˉ\bar{x} is μ=10\mu = 10 and its standard deviation is 364=0.375\frac{3}{\sqrt{64}} = 0.375.
  2. The population is skewed to the right, but n=64n = 64 is large, so by the central limit theorem xˉ\bar{x} is approximately normal.
  3. The answer is: Approximately normal, with mean 10 minutes and standard deviation 0.375 minutes.

11. Answer (C) Topic 4.3

  1. The interval estimates μd\mu_d, the mean of the differences (Store B minus Store A) for the population, not the sampled items.
  2. An interpretation names the level, the interval and the parameter in context.
  3. The answer is: We are 90% confident that the interval from −0.11-0.11 to 0.45 dollars captures the mean difference in price (Store B minus Store A) for all items sold at both stores.

12. Answer (D) Topic 4.10

  1. The standard error does not pool: SE=1.83225+1.53240=0.439SE = \sqrt{\frac{1.83^2}{25} + \frac{1.53^2}{40}} = 0.439.
  2. t=30.04−31.480.439=−3.28t = \frac{30.04 - 31.48}{0.439} = -3.28, with df=44.34df = 44.34 from technology.
  3. So the test statistic is −3.28-3.28.

13. Answer (A) Topic 4.5

  1. The standard error is sn=2.7319=0.626\frac{s}{\sqrt{n}} = \frac{2.73}{\sqrt{19}} = 0.626.
  2. t=22.65−250.626=−3.75t = \frac{22.65 - 25}{0.626} = -3.75, with df=19−1=18df = 19 - 1 = 18.
  3. So the test statistic is −3.75-3.75.

14. Answer (B) Topic 4.4

  1. Each patient is measured twice (oral and ear), so the two sets of measurements are paired, not independent.
  2. The analysis uses the 12 differences (ear minus oral) and tests whether their mean is different from 0.
  3. The answer is: A matched-pairs tt-test for a mean difference.

15. Answer (B) Topic 4.1

  1. The sampling distribution of xˉ\bar{x} has standard deviation σn\frac{\sigma}{\sqrt{n}} (the 18 eggs are far fewer than 10% of all eggs from the poultry farm).
  2. Compute 418=0.943\frac{4}{\sqrt{18}} = 0.943 grams.
  3. So the standard deviation of xˉ\bar{x} is 0.943 grams.

16. Answer (C) Topic 4.10

  1. Since 0.1154 is greater than α=0.05\alpha = 0.05, do not reject H0H_0.
  2. The conclusion is about the population means, in the direction of HaH_a, as evidence and not proof.
  3. The answer is: The P-value of 0.1154 is greater than α=0.05\alpha = 0.05, so the null hypothesis is not rejected. There is not convincing statistical evidence that the mean amount spent per visit by all downtown customers is greater than the mean amount spent per visit by all mall customers.

17. Answer (D) Topic 4.2

  1. Statement I is true: estimating σ\sigma with ss adds variability, so the tails are heavier: P(∣t∣>2)=2(0.0462)P(|t| > 2) = 2(0.0462) against P(∣z∣>2)=2(0.0228)P(|z| > 2) = 2(0.0228), both tails counted.
  2. Statement II is false: a tt distribution is more spread out than the standard normal, with heavier tails.
  3. Statement III is true: every tt distribution is symmetric about 0, like the standard normal.
  4. So the true statements are I and III. The answer is I and III only.

18. Answer (A) Topic 4.1

  1. The population is normal, so xˉ\bar{x} is normal with mean 50 and standard deviation 0.825=0.1600\frac{0.8}{\sqrt{25}} = 0.1600.
  2. P(xˉ>50.22)=normalcdf(50.22,∞,50,0.1600)=0.0846P(\bar{x} > 50.22) = \text{normalcdf}(50.22, \infty, 50, 0.1600) = 0.0846, with z=1.375z = 1.375; the zz table at z=1.38z = 1.38 gives 0.0838, which leads to the same choice.
  3. So the probability is 0.0846.

19. Answer (B) Topic 4.4

  1. The hypotheses are about the population mean μ\mu, and the null hypothesis gives the benchmark: H0:μ=22H_0: \mu = 22.
  2. A riders' group suspects the mean is greater than 22, so the alternative is μ>22\mu > 22.
  3. The answer is: H0:μ=22H_0: \mu = 22 and Ha:μ>22H_a: \mu > 22.

20. Answer (B) Topic 4.7

  1. The normal/large sample condition needs each sampling distribution of a sample mean to be approximately normal: both populations normal, or both n≥30n \ge 30, or (for small samples) data with no strong skewness or outliers.
  2. Both 30 and 32 are at least 30, so the central limit theorem applies to each sample.
  3. The answer is: Both sample sizes, 30 and 32, are at least 30.

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 4?

Unit 4 is a little under a fifth of the AP Statistics multiple choice: 76 of the 406 official multiple-choice questions on today's course (18.7%), and 4 of the 24 sample questions in the 2026 course description, the only ones in the 2027 format.

  • One mean is most of the unit. The sampling distribution of x̄, intervals and tests for one mean, paired data included (topics 4.1 to 4.5), hold 62 of the 76 Unit 4 questions; two means (topics 4.6 to 4.10) hold 14. Topic 4.3, interpreting intervals and their width, is the single biggest topic, with 17.
  • The sampling distribution of x̄ is asked in both sections. 7 official multiple-choice questions on 6 of the 13 sources ask for the mean, standard deviation or shape of the sampling distribution of x̄, and 4 free-response questions from 2012 to 2026 had a part on it.
  • Paired or two-sample is a choice you have to make. Choosing between a one-sample and a matched-pairs procedure has 6 official multiple-choice questions and choosing a two-sample procedure 3. Of the 5 official free-response questions on means from 2012 to 2026 that fit Question 3, 2 were matched-pairs t tests and 2 two-sample t tests.
  • 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 one set of two questions.
  • New topics have no official question yet. The 2026 course added the sampling distribution of x̄₁ − x̄₂. No official question has asked about it, so it is left off this sheet.

The most-tested kind here is the sampling distribution of x̄ (its shape, mean and SD), with 7 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 4 question type?

Official AP Statistics questions by question type, Unit 4 (Inference for Quantitative Data: Means), and how many are on this worksheet
Question typeOn this worksheetOfficial multiple choice, 1997–2026Sources it was on (of 13)On the 2012–2019 practice examsFree-response questions, 2012–2026
Sampling distribution of x̄: shape, mean, SDTopic 4.137654
Probability about a sample meanTopic 4.114411
Construct a one-sample t-intervalTopic 4.223311
Conditions for inference about a meanTopic 4.211112
t-distributions and why t is usedTopic 4.214300
Interpret the confidence level (mean)Topic 4.315530
CI width vs sample size and confidence level (mean)Topic 4.314410
Interpret a confidence interval for a meanTopic 4.314420
Use a confidence interval for a mean to evaluate a claimTopic 4.314411
Identify a one-sample or paired t procedureTopic 4.416551
Hypotheses for a one-sample or paired t-testTopic 4.416633
Conclusion of a one-sample or paired t-testTopic 4.516632
Carry out a one-sample or paired t-testTopic 4.514432
Conditions for two-sample t proceduresTopic 4.711111
Identify a two-sample t procedureTopic 4.913321
Conclusion of a two-sample t-testTopic 4.1012212
Carry out a two-sample t-testTopic 4.1014312

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): hypotheses for a two-sample t-test; use a CI for μ₁ − μ₂ to evaluate a claim; sample size for a margin of error (mean); construct a two-sample t-interval; interpret a confidence interval for μ₁ − μ₂. New to the 2026 course, with no official question yet: sampling distribution of x̄₁ − x̄₂.

Questions about this worksheet

Unit 4, Inference for Quantitative Data: Means, has 10 topics in the College Board's 2026 course and exam description: the sampling distribution of a sample mean; constructing a confidence interval for a population mean or a mean difference (paired data), with the conditions and the t distribution; using the interval to judge a claim; setting up and carrying out a one-sample or matched-pairs t-test; and the same for the difference of two population means (the sampling distribution of the difference, the two-sample t-interval and t-test). The course description weights the unit at 10–20% of the multiple-choice section.

Yes, on every question. The AP Statistics exam allows a graphing calculator with statistical capabilities throughout both sections (on the digital exam, the Desmos calculator in Bluebook is also available), and it supplies a formula sheet and tables. Most Unit 4 questions read a value from a calculator interval or test (TInterval, T-Test, 2-SampTInt, 2-SampTTest, invT) or compute a standard error and a t statistic. For two samples, the degrees of freedom come from technology. Each worked solution shows the formula and the numbers, so the work can be checked by hand or with the formula sheet.

We tagged 406 official multiple-choice questions on today's course, from 13 College Board sources (released exams, practice exams and course-description samples, 1997–2026), and the official free-response questions from 2012 to 2026, then sorted the Unit 4 questions into 23 kinds and gave the kinds the exam asks most the most questions (3 on “Sampling distribution of x̄: shape, mean, SD”, 2 on “Construct a one-sample t-interval”). With more kinds than questions, the kinds the exam asks least are left out of this sheet, as is the one topic new to the 2026 course that no official question has asked about yet. 1 sets of questions share one stimulus, as on the 2027 exam.

As a timed unit practice exam: 20 original multiple-choice questions with four choices, in the 2027 format. Allow about 2 minutes per question, as the exam does, check the answer key, read the worked solution of every question you missed, then redo those kinds of question. For the free-response part, use the Unit 4 FRQ set, which has a scoring guide for every point.

No. Every question here is original, written by Sigma Prep in the style of the exam. We studied which kinds of questions the official exams ask and how often; no official question is copied or reworded. Each answer, and every number in the displays, was checked by an independent computer check before the sheet was published.

Yes. Every question has a worked solution that reaches the correct answer step by step. The answer key and the solutions are shown with the sheet, and the PDF prints them after the questions. There is also a PDF without them to hand out. For free-response practice, the Unit 4 FRQ set has a scoring guide with a model answer for every point.

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.