ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE

SAMPLES
This activity sheet includes exercises to assess students’ understanding of important concepts
presented in the Population Mean Hypothesis Testing for Large Samples lesson.

Population Mean Hypothesis Testing

for Large Samples
The data for these exercises are in the Minitab file HypTestForMean_LargeSample_Activity.mtw.

Exercise 1
For the following multiple choice problems, choose the best answer.

(a) The test statistic and p-value corresponding to the hypothesis test H0: μ = 2 versus H1: μ > 2
are 𝑥̅ = 2.076 and p = 0.065, respectively. Which of the following is an appropriate interpretation
of this p-value?

A. The probability that the null hypothesis is true is 0.065.

B. The probability that the alternative hypothesis is true is 0.065.
C. The data is not normally distributed.
D. In repeated sampling, the probability of observing a test statistic at least as extreme as 𝑥̅ =
2.076 is 0.065.

(b) A pudding manufacturer packages its product into bags weighing 1 kilogram, on average.
The manufacturer’s statistician has discovered that the setting of the machine is causing the fill
weights to drift. The statistician needs to detect shifts in the mean weight as quickly as possible
and reset the machine when appropriate. In order to detect shifts in the mean weight, he
collects a random sample of 50 bags periodically, weighs them, and calculates the mean and
standard deviation. The data from this afternoon’s sample yields a sample mean of 1.03 kg and a
sample standard deviation of 0.08 kg. Determine the p-value for the hypothesis test H0: μ = 1
versus H1: μ  1.

WWW.MINITAB.COM/ACADEMIC
A. 0.008
B. 0.004
C. 0.011
D. 0.005
E. 0.704
F. 0.996
G. We cannot determine the p-value because the data does not come from a normal
distribution.

We can calculate the p-value in Minitab:

1 Open the 1-sample Z dialog box.
 Minitab: Stat > Basic Statistics > 1-Sample Z
 Minitab Express Mac: Statistics > 1-Sample Inference > Z
 Minitab Express PC: STATISTICS > One Sample > Z
2 From the drop-down list, select Summarized data.
3 In Sample size, enter 50.
4 In Sample mean, enter 1.03.
5 In Known standard deviation, enter 0.08.
6 Select Perform hypothesis test. In Hypothesized mean, enter 1.
7 Click OK.

(c) The pain reliever currently used at General Hospital brings relief to patients in a mean time of
3.5 minutes. To compare a new pain reliever with the current one, the new pain reliever is
administered to a random sample of n = 50 patients. The mean time to feel relief for this sample
of patients is 2.8 minutes with a standard deviation of 1.14 minutes.

What are the appropriate null and alternative hypotheses to determine if the mean time for
patients to feel relief from the new pain reliever is less than the time required
for the hospital’s current pain reliever?

A. H0 : μ = 2.8 versus H1: μ < 2.8

B. H0: 𝑥̅ = 2.8 versus H1: 𝑥̅ < 2.8
C. H0 : μ = 2.8 versus H1: μ > 2.8
D. H0 : μ = 3.5 versus H1: μ < 3.5
E. H0 : 𝑥̅ = 3.5 versus H1: 𝑥̅ < 3.5
F. H0 : μ = 3.5 versus H1: μ > 3.5

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 2

(d) We are testing H0:  = 2 versus H1:  > 2 and conclude that we can reject the null hypothesis
H0 at significance level = 0.05. Suppose we decide to change the alternative hypothesis from
H1: μ > 2 to H1:  ≠ 2. Using the same data, can we still reject H0 at  = 0.05?

A. Yes
B. No
C. There is not enough information to answer this question.

(e) We are conducting the following hypothesis test: H0: μ = 9.5 versus H1: μ > 9.5. The Minitab
output for this 1-sample Z-test is provided below.

One-Sample Z
Descriptive Statistics
N Mean SE Mean
50 9.728 0.122
μ: mean of Sample
Known standard deviation = 0.86

Test
Null hypothesis H₀: μ = 9.5
Alternative hypothesis H₁: μ > 9.5
The approximate p-value for this hypothesis test is:
A. 0.015
B. 0.031
C. 0.058
D. 0.267
E. 0.395
F. 0.971
G. We cannot determine the p-value because we don’t know if the data is from a normal
distribution.

(f) A certain brand of orange juice is advertised to contain 85% fruit juice per bottle. A random
sample of 32 bottles of this juice is selected in order to perform the hypothesis test:

H0: μ = 0.85 versus H1:_____,

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 3

where μ represents the average percentage of juice per bottle. The Minitab output for the test is:

One-Sample Z
Descriptive Statistics
N Mean SE Mean
32 0.8228 0.0335
μ: mean of Sample
Known standard deviation = 0.189505

Test
Z-Value P-Value
-0.81 0.417

What is the correct alternative hypothesis for this test?

A. H1: μ < 0.82
B. H1: μ < 0.85
C. H1: μ > 0.82
D. H1: μ > 0.85
E. H1: μ  0.82
F. H1: μ  0.85

(g) A quality control specialist takes several measurements to test H 0: μ = 2 versus H1: μ  2. She
computes a p-value of 0.01 for the hypothesis test. Which interpretation is correct?

A. The probability that μ = 2 is 0.01

B. The probability that μ  2 is 0.01.
C. The probability that the quality control specialist conducted the study properly is 0.99.
D. The probability of the quality control specialist observing those results (or more extreme) if μ
= 2 is 0.01.

(h) Which of the following statements is not true regarding hypothesis testing?

A. The alternative hypothesis is the assertion that is contradictory to the null hypothesis.
B. The null hypothesis is the claim that is assumed to be true, or the “status quo” hypothesis.

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 4

C. The sample evidence is used to determine whether or not to reject the alternative hypothesis.
D. The two possible conclusions from a hypothesis test are reject H 0 or fail to reject H0.
E. When drawing a conclusion after performing a hypothesis test, there is always a chance that
you made the wrong decision, even if that chance is very small.

(i) In performing the hypothesis test H0:  = 8 versus H1:   8, the resulting p-value is 0.016.
Thus, if we construct a 95% confidence interval for  using the exact same data,  = 8 will not be
included in the 95% confidence interval.

A. True
B. False
C. We do not have enough information to determine this.
(j) You perform the hypothesis test H0:  = 180 versus H1:  > 180 for the average number of
minutes per day that students at your school watch TV. Which of the following statements is
correct regarding the p-value?

A. Assuming the null hypothesis is true, an extremely small p-value indicates that the sample
mean calculated from the sample data is extremely different from null mean  = 180.
B. The p-value measures the probability that the alternative hypothesis is true.
C. The p-value measures the probability that the null hypothesis is true.
D. The larger the p-value, the stronger the evidence against the null hypothesis.
E. A large p-value indicates that the data supports the alternative hypothesis.

(k) Under normal environmental conditions, adult catfish in Dog Lake have an average length of
µ = 13.9 cm with a standard deviation σ = 2.1 cm. Students who frequently fish at Dog Lake claim
that the catfish are smaller than usual this year. Suppose your statistics class takes a random
sample of adult catfish from Dog Lake. Which of the following provides the strongest evidence
to support the claim that students are catching smaller than average length (13.9 cm) catfish this
year?

A. A random sample of size n = 36 with a sample mean of 𝑥̅ = 13.5 cm.

B. A random sample of size n = 36 with a sample mean of 𝑥̅ = 13.3 cm.
C. A random sample of size n = 121 with a sample mean of 𝑥̅ = 13.5 cm.
D. A random sample of size n = 121 with a sample mean of 𝑥̅ = 14.5 inches.
E. We do not have enough information to determine this.

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 5

(l) You just bought a new laptop with a supposed true population mean battery life of 3 hours.
You survey friends who have the same laptop to determine if, in fact, the true population mean is
less than 3 hours. For a random sample of n = 40 friends, you calculate a sample mean of 3.25
hours. To test the “less than” speculation, you should use the following hypothesis:

H0: μ = 3 versus H1: μ < 3

A. True
B. False
C. We do not have enough information to determine this.

(m) The Central Limit Theorem, the key to performing a hypothesis test for the population mean
μ with a Z test, states that:

A. We can always use a normal curve to approximate the distribution of the sample mean 𝑋.

B. If n is large (e.g. n > 30) and the original population distribution is normal, then the distribution
of the sample mean 𝑋 can be approximated by a normal curve.

C. We can always use a normal curve to approximate the distribution of a random variable X.

D. If n is large (e.g. n > 30) then the distribution of the sample mean 𝑋 can be approximated
closely by a normal curve even if the original distribution is not normal.

E. If n is large (e.g. n > 30), then the distribution of the random variable X can be approximated
closely by a normal curve even if the original distribution is not normal.

Exercise 2
Putting Puzzles Together

If students are helping to conduct this exercise in class, at least 30 puzzle times are needed to be
able to apply the concepts, namely a 1-sample Z hypothesis test for the population mean.
Instructions for creating the data set are below. If you do not have time or puzzles to collect
class data or do not have at least 30 students to perform this activity, then you can use the
‘Puzzle Times (secs)’ data found in HypTestForMean_LargeSample_Activity.mtw. For this data,
the population mean is μ0 = 90 with sample size n = 43.

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 6

Activity Instructions: To obtain data for this exercise, students will need easy jigsaw puzzles –
all identical – consisting of 25 to 40 pieces, such as the ones found at dollar stores. Alternatively,
you can find free online puzzle websites such as www.jigzone.com.

At the beginning of class, hand out the puzzles to the students. You can have groups of students
share one puzzle and take turns. Tell them to record (in seconds) the amount of time it takes to
complete the puzzle. Other group members should not watch each other to avoid biasing the
results. Times can be recorded using a cell phone. Alternatively, have students bring their
laptops to class and send them the link to a given online puzzle, which typically measures the
time for you.

As students finish the puzzle, ask them to go to the board to record their puzzle construction
times. Once everyone has recorded his or her data, the instructor can enter the data in Minitab.
The instructor can then email the worksheet data to students to ensure that everyone is working
with the same data set.

Activity “Story”: At a circuit board company, employees are required to assemble circuit
boards (puzzles) correctly and completely in a desired amount of time. If they are too slow or
inaccurate, then the entire assembly line is affected.

Based on former employee records, the company states that these circuit boards can be
assembled in 0 = 90 seconds. [Instructors may need to provide a different μ0 based on their
students’ puzzle times.]

You are the manager of these employees. You suspect that the true mean time is not accurate.
Specifically, you think the true mean time  to assemble these boards is more than 90 seconds,
and employees are being unfairly assessed. In order to test the hypothesis:

H0:  = μ0 seconds versus H1:  > μ0 seconds

you randomly select n workers to assemble these boards (puzzles). Their average time to
assemble the boards is 𝑥̅ seconds with standard deviation s seconds. [Instructors will need to
provide values for n, 𝑥̅ , and s based on the class’s data. The data provided in the Minitab
worksheet has n = 43, 𝑥̅ = 95.65 seconds, and s = 28.09 seconds.]

(a) Can we assume that the distribution of the mean time 𝑋 for n = 43 employees is normally
distributed? Why or why not? Be specific.

(b) Determine the standardized test statistic z and its p-value by hand.

(c) Determine the standardized test statistic z and its p-value in Minitab.

1 Open the 1-sample Z dialog box.

 Minitab: Stat > Basic Statistics > 1-Sample Z

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 7

  Minitab Express Mac: Statistics > 1-Sample Inference > Z
 Minitab Express PC: STATISTICS > One Sample > Z
2 In One or more samples, each in a column, enter Puzzle Times (secs).
3 In Known standard deviation, enter 28.09.
4 Select Perform hypothesis test. In Hypothesized mean, enter 90.
5 Select Options.
6 Choose the desired Alternative hypothesis.
 Minitab: Choose Mean > hypothesized mean
 Minitab Express Mac: Choose Mean > hypothesized value
 Minitab Express PC: Choose Mean > hypothesized value
7 Click OK in each dialog.

(d) Can we reject H0 at an  = 0.10 level of significance? Why or why not?

(e) Can we reject H0 at an  = 0.05 level of significance? Why or why not?

Exercise 3
Cutting Paper Strips

Reference: “The Blind Paper Cutter: Teaching about Variation, Bias, Stability, and Process Control,”
by Richard A. Stone (August 1998). The American Statistician, 52(3), pp. 244-247.

If you do not have the time or materials required to collect class data, then you can use the ‘Cut
Lengths (cm)’ data found in HypTestForMean_LargeSample_Activity.mtw. For this data, the
mean is μ0 = 14 cm (half the length of the 28 cm paper strips). There are only 25 lengths in the
dataset, but the data in that column is normally distributed.

Activity Instructions: To obtain data for this exercise, groups of 3-4 students will cut 30 strips of
paper of equal length. For example, you can use 8.5 x 11 inch scrap paper to create the strips. It
doesn’t matter how long the strips are as long as they are all the same length. The mean μ0 for
the questions below is equal to ½ of the length.

It is recommended that the instructor or students create the strips of paper prior to class. During
class, each group will need a ruler, as well as a pair of scissors to cut the paper. Each group will
need to select one person to be the cutter, and then do the following:

 Before cutting the strips, measure the length. Every strip should be the same length. Then
divide the length by 2 to calculate the value of μ0. For example, if the strips are 28cm, then
μ0 = 14 cm.

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 8

  Cutter: Cut ~30 strips of paper in half from the given pile of strips in front of you. Keep
your eyes closed for the entire experiment, although you can use your scissors to “feel”
along the length of the strip.
 Other group members: Presuming the cutter is right-handed, take each strip remaining
in the cutter’s left hand and measure the minimum length. Clean up the fallen strips to
keep them out of the cutter’s way as you go. The fallen strips will not be measured.

 Enter the minimum strip lengths into Minitab and email the data to your instructor.

Perform the following three hypothesis tests in Minitab, estimating  by calculating the standard
deviation of the data. What conclusions can you draw from the p-values reported for each
hypothesis test?

(a) H0: μ = μ0 versus H1: μ  μ0

(b) H0: μ = μ0 versus H1: μ < μ0

(c) H0: μ = μ0 versus H1: μ > μ0

Exercise 4
A drug manufacturer claims a given type of medicine contains 2.5 milligrams of a certain active
ingredient per capsule. An independent laboratory takes a random sample of 20 of these capsules
and measures the amount of the active ingredient in each.

The laboratory has been hired to determine if the true mean amount of the active ingredient is
actually less than 2.5.

(a) Using the proper statistical notation, write down the null and alternative hypotheses.

H0:_______________ versus H1: _______________

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 9

(b) What does the parameter of interest  represent in words? Select the best answer.

A. The true mean amount of the ingredient in all capsules of this type.

B. The true mean amount of the ingredient in the 20 capsules of the laboratory’s sample.

C. The difference between the true mean amount of the ingredient in the population of all
capsules and the sample mean amount of the ingredient in the 20 capsules in our sample.

D. The true proportion of all capsules of this type that contain less than 2.5 milligrams of the
ingredient.

E. The amount of the ingredient in a randomly selected capsule of this type.

(c) Using Minitab, determine the mean and standard deviation of the sample data provided. The
data is in the Minitab column “Active Ingredient.”

(d) Assume that the amount of the ingredient in capsules is normally distributed. Also, assume
that the laboratory is told that the population standard deviation is  = 0.8 mg. By hand, calculate
the z statistic and p-value for the hypothesis test in part (a) based on the sample data provided.

(e) Verify the z statistic and p-value using Minitab. From the 1-Sample Z dialog box, click Options
to select the appropriate alternative hypothesis.

Exercise 5
A waiter (with a statistics background) who works at the “World of Sushi” restaurant is asked to
estimate the true mean time to clean and set tables on a busy Saturday night. This knowledge will
help the restaurant owners determine how much time they should schedule between reservations.

Suppose the waiter randomly samples times for n = 40 tables on busy Saturday nights and obtains
a sample mean of 𝑥̅ = 4.2 minutes with a sample standard deviation of s = 0.8 minutes. The sample
data is used to construct the following 95% confidence interval for the true mean clean-up
time µ:
[3.952, 4.448]

Based on the 95% confidence interval, can the null hypothesis for the following hypothesis test
be rejected at an  = 0.05 level of significance? Explain why or why not.

H0: μ = 3.5 minutes versus H1: μ  3.5 minutes

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 10

Exercise 6
A random sample of n = 50 drill bits is used to put holes into a steel doorframe. The lifetime of a
drill bit is measured as the number of holes drilled before the bit fails. The average lifetime of a
drill bit is 12.68 holes with a standard deviation of 6.83 holes. Calculate the z statistic and p-value
for the following hypothesis tests by hand or in Minitab.

(a) H0: μ = 12 holes versus H1: μ > 12 holes

(b) H0: μ = 12 holes versus H1: μ  12 holes

(c) H0: μ = 12 holes versus H1: μ < 12 holes

Exercise 7
According to a Google search, the average height of male soccer players in
the U.S. is normally distributed with mean 1.79 m with a standard deviation
of 0.04 m.

(a) For a randomly selected soccer team of 11 players, what is the probability that the average
height of the players is less than 1.77 m? Calculate the probability by hand or in Minitab.

(b) In view of the small sample size, must you make any additional assumptions to justify the
answer to part (a)? Please provide a short explanation.

(c) Set up the hypothesis test to test the true average height of male U.S. soccer players.

H0:_______________ versus H1: _______________

(d) Determine the z statistic and p-value for the hypothesis test in part (c).

Exercise 8
According to a study, the U.S. mean family income is $63,091 with a standard deviation of
$21,000.

(a) If a consulting agency surveys 49 families at random, what is the probability that it finds a
mean family income that is more than $71,500? Calculate the probability by hand or in Minitab.

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 11

(b) For the hypothesis test H0: μ = 63,091 versus H1: μ  63,091, determine the z statistic and p-
value.

(c) Suppose the median income in the U.S. was $55,000. Why do many websites use the median
as their indicator of income level instead of the mean?

Exercise 9
Your neighbor grows and sells cucumbers in the summer. She packages them in plastic storage
bags and claims that the true mean weight of one of these bags is 1 pound. To test her claim,
you take a random sample of 64 of
these cucumber- filled bags, weigh
them, and record their weights in the
Minitab column “Bag Weights (lbs).”

With 90% confidence, is her

claim “the mean weight of these
bags is 1 pound” true? Use either a
hypothesis test or confidence interval
to provide supporting evidence
for or against this claim. The
descriptive statistics for the data are
provided below.

ACTIVITY SHEET: POPULATION MEAN HYPOTHESIS TESTING FOR LARGE SAMPLES 12