Hypothesis I

SAMPLE CHAPTER. NOT FOR DISTRIBUTION.
CHAPTER 7
Hypothesis Testing
with One Sample 7.1
Introduction to Hypothesis
Testing
7.2
Hypothesis Testing for the
Mean (s Known)
7.3
Hypothesis Testing for the
Mean (s Unknown)
Activity
Case Study
7.4
Hypothesis Testing for
Proportions
Activity
7.5
Hypothesis Testing for
Variance and Standard
Deviation
The Entertainment Software Rating Board (ESRB) assigns ratings to video games to Uses and Abuses
indicate the appropriate ages for players. These ratings include EC (early childhood), Real Statistics—Real Decisions
E (everyone), E10+ (everyone 10+), T (teen), M (mature), and AO (adults only). Technology
346
Copyright Pearson. All Rights Reserved.

Where You’ve Been

In Chapter 6, you began your study of inferential statistics. You have learned how to use these results to state with 95%
There, you learned how to form a confidence interval to confidence that the population proportion of U.S. adults
estimate a population parameter, such as the proportion who agree that people who play violent video games are
of people in the United States who agree with a certain more likely to be violent themselves is between 37.9%
statement. For instance, in a nationwide poll conducted by and 42.1%.
Pew Research Center, 2001 U.S. adults were asked whether
they agreed or disagreed with the statement, “People who
play violent video games are more likely to be violent
themselves.” Out of those surveyed, 800 adults agreed with
the statement.
Where You’re Going

In this chapter, you will continue your study of inferential Is your sample statistic different enough from the claim
statistics. But now, instead of making an estimate about 1p = 0.352 to decide that the claim is false? The answer lies
a population parameter, you will learn how to test a claim in the sampling distribution of sample proportions taken
about a parameter. from a population in which p = 0.35. The figure below
For instance, suppose that you work for Pew Research shows that your sample statistic is more than 4 standard
Center and are asked to test a claim that the proportion of errors from the claimed value. If the claim is true, then the
U.S. adults who agree that people who play violent video probability of the sample statistic being 4 standard errors or
games are more likely to be violent themselves is p = 0.35. more from the claimed value is extremely small. Something
To test the claim, you take a random sample of n = 2001 is wrong! If your sample was truly random, then you can
U.S. adults and find that 800 of them think that people conclude that the actual proportion of the adult population
who play violent video games are more likely to be violent is not 0.35. In other words, you tested the original claim
themselves. Your sample statistic is pn ≈ 0.400. (hypothesis), and you decided to reject it.
Sample statistic
Claim
pˆ ≈ 0.400
p = 0.35
pˆ
0.29 0.3 0.31 0.32 0.33 0.34 0.35 0.36 0.37 0.38 0.39 0.4 0.41
z
−6 −5 −4 −3 −2 −1 0 1 2 3 4 5 6
z ≈ 4.69
Sampling Distribution
347

348 CHA PTER 7 Hypothesis Testing with One Sample
7.1 Introduction to Hypothesis Testing

Hypothesis Tests Stating a Hypothesis Types of Errors and Level of
What You Should Learn
Significance Statistical Tests and P-Values Making a Decision and
A
practical introduction to Interpreting the Decision Strategies for Hypothesis Testing
hypothesis tests
H
ow to state a null hypothesis
and an alternative hypothesis Hypothesis Tests
H
ow to identify type I and type Throughout the remainder of this text, you will study an important technique in
II errors and interpret the level inferential statistics called hypothesis testing. A hypothesis test is a process that
of significance uses sample statistics to test a claim about the value of a population parameter.
H
ow to know whether to use Researchers in fields such as medicine, psychology, and business rely on
a one-tailed or two-tailed hypothesis testing to make informed decisions about new medicines, treatments,
statistical test and find a P@value and marketing strategies.
H
ow to make and interpret a For instance, consider a manufacturer that advertises its new hybrid car has
decision based on the results of a mean gas mileage of 50 miles per gallon. If you suspect that the mean mileage
a statistical test is not 50 miles per gallon, how could you show that the advertisement is false?
H
ow to write a claim for a Obviously, you cannot test all the vehicles, but you can still make a
hypothesis test reasonable decision about the mean gas mileage by taking a random sample
from the population of vehicles and measuring the mileage of each. If the sample
mean differs enough from the advertisement’s mean, you can decide that the
advertisement is wrong.
For instance, to test that the mean gas mileage of all hybrid vehicles of this
type is m = 50 miles per gallon, you take a random sample of n = 30 vehicles
and measure the mileage of each. You obtain a sample mean of x = 47 miles per
gallon with a sample standard deviation of s = 5.5 miles per gallon. Does this
indicate that the manufacturer’s advertisement is false?
To decide, you do something unusual—you assume the advertisement is
Study Tip correct! That is, you assume that m = 50. Then, you examine the sampling
distribution of sample means (with n = 30) taken from a population in which
As you study this chapter,
m = 50 and s = 5.5. From the Central Limit Theorem, you know this sampling
do not get confused
regarding concepts of
distribution is normal with a mean of 50 and standard error of
certainty and importance. 5.5
≈ 1.
For instance, even if you 230
were very certain that the
mean gas mileage of a type of hybrid In the figure below, notice that the sample mean of x = 47 miles per gallon
vehicle is not 50 miles per gallon, the is highly unlikely—it is about 3 standard errors 1z ≈ -2.992 from the claimed
actual mean mileage might be very mean! Using the techniques you studied in Chapter 5, you can determine that
close to this value and the difference if the advertisement is true, then the probability of obtaining a sample mean
might not be important. of 47 or less is about 0.001. This is an unusual event! Your assumption that the
company’s advertisement is correct has led you to an improbable result. So,
either you had a very unusual sample, or the advertisement is probably false. The
logical conclusion is that the advertisement is probably false.
Sampling Distribution of x
Hypothesized mean
Sample mean μ = 50
x = 47
x
z ≈ − 2.99 46 47 48 49 50 51 52 53 54
z
−4 −3 −2 −1 0 1 2 3 4

S EC T IO N 7 .1 Introduction to Hypothesis Testing 349
Note to Instructor Stating a Hypothesis
Some texts state the null hypothesis
using the strict equality symbol. We A statement about a population parameter is called a statistical hypothesis. To
use the symbol that is complementary test a population parameter, you should carefully state a pair of hypotheses—
to the alternative hypothesis. one that represents the claim and the other, its complement. When one of
these hypotheses is false, the other must be true. Either hypothesis—the null
hypothesis or the alternative hypothesis—may represent the original claim.
DEF I N I T I O N
Study Tip
The term null hypothesis 1. A null hypothesis H0 is a statistical hypothesis that contains a statement of
was introduced by Ronald equality, such as … , =, or Ú .
Fisher (see page 35). If 2. The alternative hypothesis Ha is the complement of the null hypothesis.
the statement in the null It is a statement that must be true if H0 is false and it contains a statement
hypothesis is not true, of strict inequality, such as 7 , ≠, or 6 .
then the alternative The symbol H0 is read as “H sub-zero” or “H naught” and Ha is read as
hypothesis must be true. “H sub-a.”
To write the null and alternative hypotheses, translate the claim made
about the population parameter from a verbal statement to a mathematical
statement. Then, write its complement. For instance, if the claim value is k and
the population parameter is m, then some possible pairs of null and alternative
hypotheses are
Picturing e
H0: m … k
Ha: m 7 k
H:m Ú k
, e 0
Ha: m 6 k
H:m = k
, and e 0
Ha: m ≠ k
.
the World Regardless of which of the three pairs of hypotheses you use, you always
A study was done on the effect of a
wearable fitness device combined assume m = k and examine the sampling distribution on the basis of this
with a low-calorie diet on weight assumption. Within this sampling distribution, you will determine whether or not
loss. The study used a random a sample statistic is unusual.
sample of 237 adults. At the end of The table shows the relationship between possible verbal statements
the study, the adults had a mean about the parameter m and the corresponding null and alternative hypotheses.
weight loss of 3.5 kilograms. So, Similar statements can be made to test other population parameters, such as p,
it is claimed that the mean weight s, or s2.
loss is 3.5 kilograms for all adults
who use a wearable fitness device
combined with a low-calorie diet. Verbal Verbal
(Adapted from The Journal of the Statement H0 Mathematical Statement Ha
American Medical Association) The mean is . . . Statements The mean is . . .
Determine a null hypothesis and . . . greater than or equal to k. . . . less than k.

alternative hypothesis for this . . . at least k. H:m Ú k . . . below k.
. . . not less than k. e 0 . . . fewer than k.
claim. Ha: m 6 k
. . . not shorter than k. . . . shorter than k.
. . . less than or equal to k. . . . greater than k.

H0: m = 3.5, Ha: m ≠ 3.5
. . . at most k. H:m … k . . . above k.
. . . not more than k. e 0 . . . more than k.
Ha: m 7 k
. . . not longer than k. . . . longer than k.
. . . equal to k. . . . not equal to k.

. . . k. . . . different from k.
. . . exactly k. H0: m = k . . . not k.
e
. . . the same as k. Ha: m ≠ k . . . different from k.
. . . not changed from k. . . . changed from k.

Note to Instructor
EX AMP LE 1
Begin with a hypothesis statement
and ask students to state its logical
Stating the Null and Alternative Hypotheses
complement. Some students will
have difficulty with the fact that Write each claim as a mathematical statement. State the null and alternative
the complement of m ≠ k is m = k. hypotheses, and identify which represents the claim.
Discuss the role of a double negative
1. A school publicizes that the proportion of its students who are involved in
in English. The important point is that
if you conclude that H0 is false, then
at least one extracurricular activity is 61%.
you are also concluding that Ha is true. 2. A car dealership announces that the mean time for an oil change is less than
15 minutes.
3. A company advertises that the mean life of its furnaces is more than 18 years.
SO L UT ION
Ha H0 Ha 1. The claim “the proportion . . . is 61%” can be written as p = 0.61. Its
p
complement is p ≠ 0.61, as shown in the figure at the left. Because
0.57 0.59 0.61 0.63 0.65 p = 0.61 contains the statement of equality, it becomes the null hypothesis.
In this case, the null hypothesis represents the claim. You can write the null
and alternative hypotheses as shown.
H0: p = 0.61 (Claim)
Ha: p ≠ 0.61
Ha H0 2. The claim “the mean . . . is less than 15 minutes” can be written as m 6 15.
μ
Its complement is m Ú 15, as shown in the figure at the left. Because m Ú 15
11 12 13 14 15 16 17 18 19 contains the statement of equality, it becomes the null hypothesis. In this
case, the alternative hypothesis represents the claim. You can write the null
H0: m Ú 15 minutes
Ha: m 6 15 minutes (Claim)
H0 Ha 3. The claim “the mean . . . is more than 18 years” can be written as m 7 18.
μ
Its complement is m … 18, as shown in the figure at the left. Because m … 18
14 15 16 17 18 19 20 21 22 contains the statement of equality, it becomes the null hypothesis. In this
case, the alternative hypothesis represents the claim. You can write the null
H0: m … 18 years
Ha: m 7 18 years (Claim)
In the three figures at the left, notice that each point on the number line is in
either H0 or Ha, but no point is in both.
TRY IT YOU RS ELF 1

Write each claim as a mathematical statement. State the null and alternative
hypotheses, and identify which represents the claim.
1. A consumer analyst reports that the mean life of a certain type of automobile
battery is not 74 months.
2. An electronics manufacturer publishes that the variance of the life of its
home theater systems is less than or equal to 2.7.
3. A realtor publicizes that the proportion of homeowners who feel their
house is too small for their family is more than 24%.
Answer: Page A36
In Example 1, notice that the claim is represented by either the null

hypothesis or the alternative hypothesis.

Types of Errors and Level of Significance

No matter which hypothesis represents the claim, you always begin a hypothesis
test by assuming that the equality condition in the null hypothesis is true. So,
when you perform a hypothesis test, you make one of two decisions:
1. reject the null hypothesis

or
2. fail to reject the null hypothesis.
Because your decision is based on a sample rather than the entire population,
there is always the possibility you will make the wrong decision.
For instance, you claim that a coin is not fair. To test your claim, you toss the
coin 100 times and get 49 heads and 51 tails. You would probably agree that you
do not have enough evidence to support your claim. Even so, it is possible that
the coin is actually not fair and you had an unusual sample.
But then you toss the coin 100 times and get 21 heads and 79 tails. It would
be a rare occurrence to get only 21 heads out of 100 tosses with a fair coin. So,
you probably have enough evidence to support your claim that the coin is not
fair. However, you cannot be 100% sure. It is possible that the coin is fair and
you had an unusual sample.
Letting p represent the proportion of heads, the claim that “the coin is not
fair” can be written as the mathematical statement p ≠ 0.5. Its complement,
“the coin is fair,” is written as p = 0.5, as shown in the figure.
Ha H0 Ha
p
0.48 0.49 0.50 0.51 0.52
So, the null hypothesis is

H0: p = 0.5
and the alternative hypothesis is
Ha: p ≠ 0.5. (Claim)
Remember, the only way to be absolutely certain of whether H0 is true or
false is to test the entire population. Because your decision—to reject H0 or
to fail to reject H0—is based on a sample, you must accept the fact that your
decision might be incorrect. You might reject a null hypothesis when it is actually
true. Or, you might fail to reject a null hypothesis when it is actually false. These
types of errors are summarized in the next definition.
DEF I N I T I O N
A type I error occurs if the null hypothesis is rejected when it is true.
A type II error occurs if the null hypothesis is not rejected when it is false.
The table shows the four possible outcomes of a hypothesis test.
Truth of H0
Decision H0 is true. H0 is false.
Do not reject H0. Correct decision Type II error
Reject H0. Type I error Correct decision

Hypothesis testing is sometimes compared to the legal system used in the

United States. Under this system, these steps are used.
1. A carefully worded accusation is written.

2. The defendant is assumed innocent (H0) until proven guilty. The burden of
Truth about proof lies with the prosecution. If the evidence is not strong enough, then
defendant there is no conviction. A “not guilty” verdict does not prove that a defendant
is innocent.
Verdict Innocent Guilty
3. The evidence needs to be conclusive beyond a reasonable doubt. The system
Type II assumes that more harm is done by convicting the innocent (type I error) than
Not guilty Justice
error by not convicting the guilty (type II error).
Guilty Type I error Justice
The table at the left shows the four possible outcomes.
EX AMP LE 2
Identifying Type I and Type II Errors

The USDA limit for salmonella contamination for ground beef is 7.5%. A
meat inspector reports that the ground beef produced by a company exceeds
the USDA limit. You perform a hypothesis test to determine whether the meat
inspector’s claim is true. When will a type I or type II error occur? Which error
is more serious? (Source: U.S. Department of Agriculture)
SO L UT ION
Let p represent the proportion of the ground beef that is contaminated. The
meat inspector’s claim is “more than 7.5% is contaminated.” You can write the
null hypothesis as
H0: p … 0.075 The proportion is less than or equal to 0.075.
and the alternative hypothesis is

Ha: p 7 0.075. (Claim) The proportion is greater than 0.075.
You can visualize the null and alternative hypotheses using a number line, as
shown below.
Ground beef meets Ground beef exceeds
USDA limits USDA limits
H0 : p ≤ 0.075 Ha : p > 0.075
p
0.055 0.065 0.075 0.085 0.095
A type I error will occur when the actual proportion of contaminated ground
beef is less than or equal to 0.075, but you reject H0. A type II error will occur
when the actual proportion of contaminated ground beef is greater than 0.075,
but you do not reject H0. With a type I error, you might create a health scare
and hurt the sales of ground beef producers who were actually meeting the
USDA limits. With a type II error, you could be allowing ground beef that
exceeded the USDA contamination limit to be sold to consumers. A type II
error is more serious because it could result in sickness or even death.
TRY IT YOU RS ELF 2

A company specializing in parachute assembly states that its main parachute
failure rate is not more than 1%. You perform a hypothesis test to determine
whether the company’s claim is false. When will a type I or type II error occur?
Which error is more serious?
Answer: Page A36

You will reject the null hypothesis when the sample statistic from the
sampling distribution is unusual. You have already identified unusual events
to be those that occur with a probability of 0.05 or less. When statistical tests
are used, an unusual event is sometimes required to have a probability of 0.10
or less, 0.05 or less, or 0.01 or less. Because there is variation from sample to
sample, there is always a possibility that you will reject a null hypothesis when
it is actually true. In other words, although the null hypothesis is true, your
sample statistic is determined to be an unusual event in the sampling distribution.
You can decrease the probability of this happening by lowering the level of
significance.
DEF I N I T I O N
Study Tip
When you decrease a In a hypothesis test, the level of significance is your maximum allowable
(the maximum allowable probability of making a type I error. It is denoted by a, the lowercase Greek
probability of making a letter alpha.
type I error), you are likely The probability of a type II error is denoted by b, the lowercase Greek
to be increasing b. The letter beta.
value 1 - b is called the
power of the test. It represents
the probability of rejecting the null
By setting the level of significance at a small value, you are saying that
hypothesis when it is false. The you want the probability of rejecting a true null hypothesis to be small. Three
value of the power is difficult (and commonly used levels of significance are
sometimes impossible) to find in a = 0.10, a = 0.05, and a = 0.01.
most cases.
Statistical Tests and P -Values

After stating the null and alternative hypotheses and specifying the level of
Note to Instructor
significance, the next step in a hypothesis test is to obtain a random sample
You can use an example of “false
from the population and calculate the sample statistic ( such as x, pn , or s2 )
positive” and “false negative” results
corresponding to the parameter in the null hypothesis ( such as m, p, or s2 ) .
for a medical test (for example,
cancer) to discuss type I and type II
This sample statistic is called the test statistic. With the assumption that the
errors. You might also want to point null hypothesis is true, the test statistic is then converted to a standardized test
out that the computation of b is statistic, such as z, t, or x 2. The standardized test statistic is used in making the
beyond the scope of this text. decision about the null hypothesis.
In this chapter, you will learn about several one-sample statistical tests.
The table shows the relationships between population parameters and their
corresponding test statistics and standardized test statistics.
Population Test Standardized

parameter statistic test statistic
m x z (Section 7.2, s known),
t (Section 7.3, s unknown)
p p
n z (Section 7.4)
2 2
s s x 2 (Section 7.5)
One way to decide whether to reject the null hypothesis is to determine

whether the probability of obtaining the standardized test statistic (or one that is
more extreme) is less than the level of significance.
DEF I N I T I O N
If the null hypothesis is true, then a P@value (or probability value) of a
hypothesis test is the probability of obtaining a sample statistic with a value
as extreme or more extreme than the one determined from the sample data.

The P@value of a hypothesis test depends on the nature of the test. There
are three types of hypothesis tests—left-tailed, right-tailed, and two-tailed.
The type of test depends on the location of the region of the sampling
distribution that favors a rejection of H0. This region is indicated by the
alternative hypothesis.
DEFIN I T I O N
1. If the alternative hypothesis Ha contains the less-than inequality symbol
1 6 2, then the hypothesis test is a left-tailed test.
P is the area to
H0: μ ≥ k the left of the
Ha: μ < k standardized
test statistic.
−3 −2 −1 0 1 2 3
Standardized test statistic
Left-Tailed Test
2.
If the alternative hypothesis Ha contains the greater-than inequality
symbol 1 7 2, then the hypothesis test is a right-tailed test.
P is the area to
H0: μ ≤ k the right of the
Ha: μ > k standardized
test statistic.
−3 −2 −1 0 1 2 3
Right-Tailed Test
3. If the alternative hypothesis Ha contains the not-equal-to symbol 1 ≠ 2,

Study Tip then the hypothesis test is a two-tailed test. In a two-tailed test, each tail
The third type of test is has an area of 12P.
called a two-tailed test
because evidence that The area to the left The area to the right
H0: μ = k
would support the of the negative of the positive
Ha: μ ≠ k standardized
alternative hypothesis standardized
test statistic is 1 P. test statistic is 1 P.
could lie in either tail of 2 2
the sampling distribution.
−3 −2 −1 0 1 2 3
Standardized test statistic Standardized test statistic
Two-Tailed Test
The smaller the P@value of the test, the more evidence there is to reject the
null hypothesis. A very small P@value indicates an unusual event. Remember,
however, that even a very low P@value does not constitute proof that the null
hypothesis is false, only that it is probably false.

EX A M P L E 3
Identifying the Nature of a Hypothesis Test

For each claim, state H0 and Ha in words and in symbols. Then determine
whether the hypothesis test is a left-tailed test, right-tailed test, or two-tailed
test. Sketch a normal sampling distribution and shade the area for the P@value.
1. A school publicizes that the proportion of its students who are involved in
at least one extracurricular activity is 61%.
2. A car dealership announces that the mean time for an oil change is less than
15 minutes.
3. A company advertises that the mean life of its furnaces is more than 18 years.
SO LU TION
In Symbols In Words
1. H0: p = 0.61 The proportion of students who are involved in at least
one extracurricular activity is 61%.
1 1
Ha: p ≠ 0.61 The proportion of students who are involved in at least
2
P-value 2
P-value one extracurricular activity is not 61%.
area area
z Because Ha contains the ≠ symbol, the test is a two-tailed hypothesis test.
0 The figure at the left shows the normal sampling distribution with a shaded
Standardized test statistic area for the P@value.
In Symbols In Words
2. H0: m Ú 15 min The mean time for an oil change is greater than or
equal to 15 minutes.
P-value
Ha: m 6 15 min The mean time for an oil change is less than 15 minutes.
area
z Because Ha contains the 6 symbol, the test is a left-tailed hypothesis test.
In Symbols In Words
3. H0: m … 18 yr The mean life of the furnaces is less than or equal to
18 years.
P-value Ha: m 7 18 yr The mean life of the furnaces is more than 18 years.
area
z Because Ha contains the 7 symbol, the test is a right-tailed hypothesis test.
T RY I T YOURSELF 3
For each claim, state H0 and Ha in words and in symbols. Then determine
whether the hypothesis test is a left-tailed test, right-tailed test, or two-tailed
test. Sketch a normal sampling distribution and shade the area for the P@value.
2. An electronics manufacturer publishes that the variance of the life of its
home theater systems is less than or equal to 2.7.
3. A realtor publicizes that the proportion of homeowners who feel their
house is too small for their family is more than 24%.
Answer: Page A36

Making a Decision and Interpreting the Decision

To conclude a hypothesis test, you make a decision and interpret that decision.
For any hypothesis test, there are two possible outcomes: (1) reject the null
hypothesis or (2) fail to reject the null hypothesis. To decide to reject H0 or fail
to reject H0, you can use the following decision rule.
Study Tip Decision Rule Based on P-Value

In this chapter, you will learn
that there are two types of To use a P@value to make a decision in a hypothesis test, compare the P@value
decision rules for deciding with a.
whether to reject H0 or fail 1. If P … a, then reject H0.
to reject H0. The decision 2. If P 7 a, then fail to reject H0.
rule described on this page
is based on P-values. The second type
of decision rule is based on rejection Failing to reject the null hypothesis does not mean that you have accepted
regions. When the standardized test the null hypothesis as true. It simply means that there is not enough evidence
statistic falls in the rejection region, to reject the null hypothesis. To support a claim, state it so that it becomes the
the observed probability (P-value) of alternative hypothesis. To reject a claim, state it so that it becomes the null
a type I error is less than a. You will hypothesis. The table will help you interpret your decision.
learn more about rejection regions in
the next section. Claim
Decision Claim is H0. Claim is Ha.

Reject H0. There is enough evidence There is enough evidence to
to reject the claim. support the claim.
Fail to reject H0. There is not enough There is not enough evidence
evidence to reject the claim. to support the claim.
EX AMP LE 4
Interpreting a Decision
You perform a hypothesis test for each claim. How should you interpret your
decision if you reject H0? If you fail to reject H0?
1. H0 (Claim): A school publicizes that the proportion of its students who are
involved in at least one extracurricular activity is 61%.
2. Ha (Claim): A car dealership announces that the mean time for an oil
change is less than 15 minutes.
SO L UT ION
1. The claim is represented by H0. If you reject H0, then you should conclude
“there is enough evidence to reject the school’s claim that the proportion of
students who are involved in at least one extracurricular activity is 61%.”
If you fail to reject H0, then you should conclude “there is not enough
evidence to reject the school’s claim that the proportion of students who are
involved in at least one extracurricular activity is 61%.”
2. The claim is represented by Ha, so the null hypothesis is “the mean time for
an oil change is greater than or equal to 15 minutes.” If you reject H0, then
you should conclude “there is enough evidence to support the dealership’s
claim that the mean time for an oil change is less than 15 minutes.” If you
fail to reject H0, then you should conclude “there is not enough evidence to
support the dealership’s claim that the mean time for an oil change is less
than 15 minutes.”

TRY IT YOU RS ELF 4
You perform a hypothesis test for each claim. How should you interpret your
decision if you reject H0? If you fail to reject H0?
2. Ha (Claim): A realtor publicizes that the proportion of homeowners who
feel their house is too small for their family is more than 24%.
Answer: Page A36
The general steps for a hypothesis test using P@values are summarized below.
Note that when performing a hypothesis test, you should always state the null
and alternative hypotheses before collecting data. You should not collect the
data first and then create a hypothesis based on something unusual in the data.
Steps for Hypothesis Testing

1.
State the claim mathematically and verbally. Identify the null and
alternative hypotheses.
H0: ? Ha: ?
2. Specify the level of significance.
a = ?
3. Determine the standardized This sampling distribution

sampling distribution and sketch is based on the assumption
its graph. that H0 is true.
4. Calculate the test statistic and its

corresponding standardized test
statistic. Add it to your sketch.
0
5. Find the P@value.

6. Use this decision rule.
Is the P-value less than or

equal to the level of No Fail to reject H0.
significance?
Yes
Reject H0.
7. Write a statement to interpret the decision in the context of the original

claim.
In Step 4 above, the figure shows a right-tailed test. However, the same basic
steps also apply to left-tailed and two-tailed tests.

Strategies for Hypothesis Testing

In a courtroom, the strategy used by an attorney depends on whether the attorney
is representing the defense or the prosecution. In a similar way, the strategy that
you will use in hypothesis testing should depend on whether you are trying to
support or reject a claim. Remember that you cannot use a hypothesis test to
support your claim when your claim is the null hypothesis. So, as a researcher,
to perform a hypothesis test where the possible outcome will support a claim,
word the claim so it is the alternative hypothesis. To perform a hypothesis test
where the possible outcome will reject a claim, word it so the claim is the null
hypothesis.
EX AMP LE 5
Writing the Hypotheses

A medical research team is investigating the benefits of a new surgical
treatment. One of the claims is that the mean recovery time for patients after
the new treatment is less than 96 hours.
1. How would you write the null and alternative hypotheses when you are on
the research team and want to support the claim? How should you interpret
a decision that rejects the null hypothesis?
2. How would you write the null and alternative hypotheses when you are on
an opposing team and want to reject the claim? How should you interpret a
decision that rejects the null hypothesis?
SO L UT ION
1. To answer the question, first think about the context of the claim. Because
you want to support this claim, make the alternative hypothesis state that
the mean recovery time for patients is less than 96 hours. So, Ha: m 6 96
hours. Its complement, H0: m Ú 96 hours, would be the null hypothesis. If
you reject H0, then you will support the claim that the mean recovery time
is less than 96 hours.
H0: m Ú 96 and Ha: m 6 96 (Claim)
2. First think about the context of the claim. As an opposing researcher, you
do not want the recovery time to be less than 96 hours. Because you want
to reject this claim, make it the null hypothesis. So, H0: m … 96 hours. Its
complement, Ha: m 7 96 hours, would be the alternative hypothesis. If you
reject H0, then you will reject the claim that the mean recovery time is less
than or equal to 96 hours.
H0: m … 96 (Claim) and Ha: m 7 96
TRY IT YOU RS ELF 5

1. You represent a chemical company that is being sued for paint damage to
automobiles. You want to support the claim that the mean repair cost per
automobile is less than $650. How would you write the null and alternative
hypotheses? How should you interpret a decision that rejects the null
hypothesis?
2. You are on a research team that is investigating the mean temperature of
adult humans. The commonly accepted claim is that the mean temperature
is about 98.6°F. You want to show that this claim is false. How would you
write the null and alternative hypotheses? How should you interpret a
decision that rejects the null hypothesis?
Answer: Page A36

7.1 EXERCISES For Extra Help: MyLab Statistics
1. The two types of hypotheses

Building Basic Skills and Vocabulary
used in a hypothesis test are 1. What are the two types of hypotheses used in a hypothesis test? How are
the null hypothesis and the they related?
2. Describe the two types of errors possible in a hypothesis test decision.
The alternative hypothesis is
the complement of the null 3.
What are the two decisions that you can make from performing a
hypothesis. hypothesis test?
2. A type I error occurs if the null
hypothesis is rejected when it is
4. Does failing to reject the null hypothesis mean that the null hypothesis
true. is true? Explain.
A type II error occurs if the null True or False? In Exercises 5–10, determine whether the statement is true or
hypothesis is not rejected when false. If it is false, rewrite it as a true statement.
it is false.
3. You can reject the null 5. In a hypothesis test, you assume the alternative hypothesis is true.
hypothesis, or you can fail to 6. A statistical hypothesis is a statement about a sample.
reject the null hypothesis.
4. No; Failing to reject the null 7.
If you decide to reject the null hypothesis, then you can support the
hypothesis means that there is alternative hypothesis.
not enough evidence to reject it.
8. The level of significance is the maximum probability you allow for rejecting
5. False. In a hypothesis test, you a null hypothesis when it is actually true.
assume the null hypothesis is
true. 9. A large P@value in a test will favor rejection of the null hypothesis.
6. False. A statistical hypothesis is 10. To support a claim, state it so that it becomes the null hypothesis.
a statement about a population.
7. True 8. True Stating Hypotheses In Exercises 11–16, the statement represents a claim.
9. False. A small P-value in a test Write its complement and state which is H0 and which is Ha.
will favor rejection of the null 11. m … 645 12.
m 6 128
hypothesis.
10. False. To support a claim, s2 Ú 1.2
13. s ≠ 5 14.
state it so that it becomes the 15. p 6 0.45 16. p = 0.21
11. H0: m … 645 (claim); Ha: m 7 645 Graphical Analysis In Exercises 17–20, match the alternative hypothesis with
12. H0: m Ú 128; Ha: m 6 128 (claim) its graph. Then state the null hypothesis and sketch its graph.
13. H0: s = 5; Ha: s ≠ 5 (claim) 17. Ha: m 7 3 (a) μ
14. H0: s2 Ú 1.2 (claim); Ha: s2 6 1.2 1 2 3 4
15. H0: p Ú 0.45; Ha: p 6 0.45 (claim) 18. Ha: m 6 3 (b) μ

16. H0: p = 0.21 (claim); Ha: p ≠ 0.21 1 2 3 4
17. c; H0: m … 3
μ
19. Ha: m ≠ 3 (c) μ
1 2 3 4
1 2 3 4
18. d; H0: m Ú 3 20. Ha: m 7 2 (d) μ

μ 1 2 3 4
1 2 3 4
19. b; H0: m = 3 Identifying a Test In Exercises 21–24, determine whether the hypothesis test
μ is left-tailed, right-tailed, or two-tailed.
1 2 3 4
20. a; H0: m … 2 21. H0: m … 8.0 22. H0: s Ú 5.2

μ Ha: m 7 8.0 Ha: s 6 5.2
1 2 3 4
23. H0: s2 = 142 24. H0: p = 0.25
21. Right-tailed 22. Left-tailed Ha: s2 ≠ 142 Ha: p ≠ 0.25
23. Two-tailed 24. Two-tailed

25. m 7 8 Using and Interpreting Concepts

H0: m … 8; Ha: m 7 8 (claim)
26. s 6 3 Stating the Null and Alternative Hypotheses In Exercises 25–30, write
H0: s Ú 3; Ha: s 6 3 (claim) the claim as a mathematical statement. State the null and alternative hypotheses,
27. s … 320 and identify which represents the claim.
H0: s … 320 (claim); Ha: s 7 320
25. Tablets A tablet manufacturer claims that the mean life of the battery for
28. m Ú 20,000 a certain model of tablet is more than 8 hours.
H0: m Ú 20,000 (claim);
Ha: m 6 20,000 26. Shipping Errors As stated by a company’s shipping department, the
29. p = 0.73 number of shipping errors per million shipments has a standard deviation
H0: p = 0.73 (claim); that is less than 3.
Ha: p ≠ 0.73
27. Base Price of an ATV The standard deviation of the base price of an
30. p = 0.52 all-terrain vehicle is no more than $320.
H0: p = 0.52 (claim);
Ha: p ≠ 0.52 28. Attendance An amusement park claims that the mean daily attendance at
31. A type I error will occur when the park is at least 20,000 people.
the actual proportion of new
29. Paying for College According to a recent survey, 73% of college students
customers who return to
did not use student loans to pay for college. (Source: Sallie Mae)
buy their next textbook is
at least 0.60, but you reject 30. P
aying for College According to a recent survey, 52% of college students
H0: p Ú 0.60. used their own income or savings to pay for college. (Source: Sallie Mae)
A type II error will occur when
the actual proportion of new Identifying Type I and Type II Errors In Exercises 31–36, describe type I
customers who return to buy and type II errors for a hypothesis test of the indicated claim.
their next textbook is less
than 0.60, but you fail to reject 31. Repeat Customers A used textbook selling website claims that at least
H0: p Ú 0.60. 60% of its new customers will return to buy their next textbook.
32. A type I error will occur when 32. Flow Rate An urban planner claims that the noontime mean traffic flow
the actual noontime mean traffic rate on a busy downtown college campus street is 35 cars per minute.
flow rate is 35 cars per minute,
but you reject H0: m = 35. 33. Chess A local chess club claims that the length of time to play a game has
A type II error will occur when a standard deviation of more than 12 minutes.
the actual noontime mean 34. Video Game Systems A researcher claims that the percentage of adults in
traffic flow rate is not 35 cars the United States who own a video game system is not 26%.
per minute, but you fail to reject
H0: m = 35. 35. Security A campus security department publicizes that at most 25% of
33. A type I error will occur when applicants become campus security officers.
the actual standard deviation
36. Phone Repairs A cellphone repair shop advertises that the mean cost of
of the length of time to play
repairing a phone screen is less than $75.
a game is less than or equal
to 12 minutes, but you reject
Identifying the Nature of a Hypothesis Test In Exercises 37– 42, state
H0: s … 12.
H0 and Ha in words and in symbols. Then determine whether the hypothesis test
A type II error will occur when is left-tailed, right-tailed, or two-tailed. Explain your reasoning. Sketch a normal
the actual standard deviation
sampling distribution and shade the area for the P-value.
of the length of time to
play a game is greater than 37. Security Alarms A security expert claims that at least 14% of all homeowners
12 minutes, but you fail to reject have a home security alarm.
H0: s … 12.
38.
Clocks A manufacturer of grandfather clocks claims that the mean time its
34. See Selected Answers, page A99.
clocks lose is no more than 0.02 second per day.
35. See Odd Answers, page A68.
36. See Selected Answers, page A99. 39. Golf A golf analyst claims that the standard deviation of the 18-hole scores
for a golfer is less than 2.1 strokes.
38. See Selected Answers, page A100. 40. Lung Cancer A report claims that lung cancer accounts for 25% of all
39. See Odd Answers, page A68. cancer diagnoses. (Source: American Cancer Society)

41. See Odd Answers, page A68. 41. H
igh School Graduation Rate A high school claims that its mean
42. See Selected Answers, page A100. graduation rate is more than 97%.
43. See Odd Answers, page A68. 42. Survey A polling organization reports that the number of responses to a
44. See Selected Answers, page A100. survey mailed to 100,000 U.S. residents is not 100,000.
Interpreting a Decision In Exercises 43– 48, determine whether the claim
46. Null hypothesis
represents the null hypothesis or the alternative hypothesis. If a hypothesis test is
(a) There is enough evidence performed, how should you interpret a decision that
to reject the automotive
manufacturer’s claim that the (a) rejects the null hypothesis?
standard deviation for the
gas mileage of its vehicles is (b) fails to reject the null hypothesis?
3.9 miles per gallon. 43. Swans A scientist claims that the mean incubation period for swan eggs is
(b) There is not enough less than 40 days.
evidence to reject the
automotive manufacturer’s 44.
Affording Basic Necessities A report claims that more than 40% of
claim that the standard households in a New York county struggle to afford basic necessities.
deviation for the gas mileage (Source: Niagara Frontier Publications)
of its vehicles is 3.9 miles 45. Lawn Mowers A researcher claims that the standard deviation of the life
per gallon.
of a brand of lawn mower is at most 2.8 years.
47. Null hypothesis
(a) There is enough evidence to
46. Gas Mileage An automotive manufacturer claims that the standard
reject the report’s claim that deviation for the gas mileage of one of the vehicles it manufactures is
at least 65% of individuals 3.9 miles per gallon.
convicted of terrorism or 47. Terrorism Convictions A report claims that at least 65% of individuals
terrorism-related offenses in
convicted of terrorism or terrorism-related offenses in the United States are
the United States are foreign
born.
foreign born. (Source: Hannity.com)
(b) There is not enough 48. Minimum Wage A marketing organization claims that none of its
evidence to reject the employees are paid minimum wage.
report’s claim that at
least 65% of individuals 49. Writing Hypotheses: Medicine A medical research team is investigating
convicted of terrorism or the mean cost of a 30-day supply of a heart medication. A pharmaceutical
terrorism-related offenses in company thinks that the mean cost is less than $60. You want to support this
the United States are foreign
claim. How would you write the null and alternative hypotheses?
born.
48. Null hypothesis 50. Writing Hypotheses: Transportation Network Company A transportation
(a) There is enough evidence network company claims that the mean travel time between two destinations
to reject the organization’s is about 16 minutes. You work for one of the company’s competitors and
claim that none of its want to reject this claim. How would you write the null and alternative
employees are paid hypotheses?
minimum wage.
51. Writing Hypotheses: Backpack Manufacturer A backpack manufacturer
(b) There is not enough claims that the mean life of its competitor’s backpacks is less than 5 years.
evidence to reject the
You are asked to perform a hypothesis test to test this claim. How would you
organization’s claim that
none of its employees are
write the null and alternative hypotheses when
paid minimum wage. (a) you represent the manufacturer and want to support the claim?
49. H0: m Ú 60; Ha: m 6 60 (b) you represent the competitor and want to reject the claim?
50. H0: m = 16; Ha: m ≠ 16 52. Writing Hypotheses: Internet Provider An Internet provider is trying to
51. (a) H0: m Ú 5; Ha: m 6 5 gain advertising deals and claims that the mean time a customer spends
(b)
H0: m … 5; Ha: m 7 5 online per day is greater than 28 minutes. You are asked to test this claim.
52. (a) H0: m … 28; Ha: m 7 28 How would you write the null and alternative hypotheses when
(b)
H0: m Ú 28; Ha: m 6 28 (a) you represent the Internet provider and want to support the claim?
(b) you represent a competing advertiser and want to reject the claim?

53. If you decrease a, then you are Extending Concepts

decreasing the probability that
you will reject H0. Therefore, you 53. Getting at the Concept Why can decreasing the probability of a type I error
are increasing the probability cause an increase in the probability of a type II error?
of failing to reject H0. This could
increase b, the probability of 54. Getting at the Concept Explain why a level of significance of a = 0 is
failing to reject H0 when H0 is not used.
false.
55. Writing A null hypothesis is rejected with a level of significance of 0.05.
54. If a = 0, then the null Is it also rejected at a level of significance of 0.10? Explain.
hypothesis cannot be rejected
and the hypothesis test is 56. Writing A null hypothesis is rejected with a level of significance of 0.10.
useless. Is it also rejected at a level of significance of 0.05? Explain.
55. Yes; If the P-value is less than
a = 0.05, then it is also less Graphical Analysis In Exercises 57– 60, you are given a null hypothesis and
than a = 0.10. three confidence intervals that represent three samplings. Determine whether each
confidence interval indicates that you should reject H0. Explain your reasoning.
56. Not necessarily; A P-value less
than a = 0.10 may or may not 57. H0: μ ≥ 70 (a) 67 < μ < 71
also be less than a = 0.05. μ x
57. (a) Fail to reject H0 because the 67 68 69 70 71 72 73 67 68 69 70 71 72 73
confidence interval includes
(b)
67 < μ < 69
values greater than 70.
x
(b) Reject H0 because the 67 68 69 70 71 72 73
confidence interval is located
entirely to the left of 70. (c)
69.5 < μ < 72.5
x
(c) Fail to reject H0 because the
67 68 69 70 71 72 73
values greater than 70.
58. H0: μ ≤ 54 (a) 53.5 < μ < 56.5
58. (a) Fail to reject H0 because the μ x
confidence interval includes 51 52 53 54 55 56 57 51 52 53 54 55 56 57
values less than 54.
(b)
51.5 < μ < 54.5
(b) Fail to reject H0 because the
confidence interval includes x
51 52 53 54 55 56 57
values less than 54.
(c) Reject H0 because the (c)
54.5 < μ < 55.5
confidence interval is located x
entirely to the right of 54. 51 52 53 54 55 56 57
59. (a) Reject H0 because the

confidence interval is located 59. H0: p ≤ 0.20 (a) 0.21 < p < 0.23
entirely to the right of 0.20. p pˆ
0.17 0.18 0.19 0.20 0.21 0.22 0.23 0.17 0.18 0.19 0.20 0.21 0.22 0.23
(b) Fail to reject H0 because the
confidence interval includes (b)
0.19 < p < 0.23
values less than 0.20. pˆ
(c) Fail to reject H0 because the 0.17 0.18 0.19 0.20 0.21 0.22 0.23
confidence interval includes (c)

0.175 < p < 0.205
values less than 0.20. pˆ
60. (a) Fail to reject H0 because the 0.17 0.18 0.19 0.20 0.21 0.22 0.23
values greater than 0.73. 60. H0: p ≥ 0.73 (a) 0.73 < p < 0.75
(b) Reject H0 because the p p̂
confidence interval is located 0.70 0.71 0.72 0.73 0.74 0.75 0.76 0.70 0.71 0.72 0.73 0.74 0.75 0.76
entirely to the left of 0.73. (b)

0.715 < p < 0.725
(c) Fail to reject H0 because the p̂
confidence interval includes 0.70 0.71 0.72 0.73 0.74 0.75 0.76
values greater than 0.73.
(c)
0.695 < p < 0.745
p̂
0.70 0.71 0.72 0.73 0.74 0.75 0.76

S EC T IO N 7 . 2 Hypothesis Testing for the Mean (s Known) 363
7.2 Hypothesis Testing for the Mean (s Known)

Using P@Values to Make Decisions Using P@Values for a z@Test Rejection
Regions and Critical Values Using Rejection Regions for a z@Test
H
ow to find and interpret
P-values
H
ow to use P-values for a Using P@ Values to Make Decisions
z-test for a mean m when s is In Chapter 5, you learned that when the sample size is at least 30, the sampling
known distribution for x (the sample mean) is normal. In Section 7.1, you learned
H
ow to find critical values that a way to reach a conclusion in a hypothesis test is to use a P@value for the
and rejection regions in the sample statistic, such as x. Recall that when you assume the null hypothesis is
standard normal distribution true, a P@value (or probability value) of a hypothesis test is the probability of
H
ow to use rejection regions for obtaining a sample statistic with a value as extreme or more extreme than the
a z-test for a mean m when s is one determined from the sample data. The decision rule for a hypothesis test
known based on a P@value is shown below.
Decision Rule Based on P-Value
Note to Instructor To use a P@value to make a decision in a hypothesis test, compare the P@value
If a P@value is less than 0.01, then the
with a.
null hypothesis will be rejected at the 1. If P … a, then reject H0.
common levels of a = 0.01, a = 0.05, 2. If P 7 a, then fail to reject H0.
and a = 0.10. If the P@value is greater
than 0.10, then you would fail to reject
H0 for these common levels. Make
sure students know that the same EX A M P L E 1
conclusion will be reached regardless
of whether they use the critical value Interpreting a P-Value
method or the P@value method.
The P@value for a hypothesis test is P = 0.0237. What is your decision when
the level of significance is (1) a = 0.05 and (2) a = 0.01?
SO LU TION
1. Because 0.0237 6 0.05, you reject the null hypothesis.
2. Because 0.0237 7 0.01, you fail to reject the null hypothesis.
TRY IT YOU RS ELF 1

The P@value for a hypothesis test is P = 0.0745. What is your decision when
the level of significance is (1) a = 0.05 and (2) a = 0.10? Answer: Page A37
The lower the P@value, the more evidence there is in favor of rejecting H0.
The P@value gives you the lowest level of significance for which the sample
statistic allows you to reject the null hypothesis. In Example 1, you would reject
H0 at any level of significance greater than or equal to 0.0237.
Finding the P-Value for a Hypothesis Test

After determining the hypothesis test’s standardized test statistic and the
standardized test statistic’s corresponding area, do one of the following to
find the P@value.
a. For a left-tailed test, P = (Area in left tail).
b. For a right-tailed test, P = (Area in right tail).
c. For a two-tailed test, P = 2(Area in tail of standardized test statistic).

EX AMP LE 2
Finding a P-Value for a Left-Tailed Test

Find the P@value for a left-tailed hypothesis test with a standardized test
statistic of z = -2.23. Decide whether to reject H0 when the level of
significance is a = 0.01.
SO L UT ION
The area to the left The figure at the left shows the standard normal curve with a shaded area to
of z = −2.23 is the left of z = -2.23. For a left-tailed test,
P = 0.0129.
P = 1Area in left tail2.
Using Table 4 in Appendix B, the area corresponding to z = -2.23 is 0.0129,
which is the area in the left tail. So, the P@value for a left-tailed hypothesis test
with a standardized test statistic of z = -2.23 is P = 0.0129. You can check
z
your answer using technology, as shown below.
−3 −2 −1 0 1 2 3
z = − 2.23 EXCEL
Left-Tailed Test A B
1 NORM.DIST(-2.23,0,1,TRUE)
2 0.012873721
Interpretation Because the P@value of 0.0129 is greater than 0.01, you fail to

reject H0.
TRY IT YOU RS ELF 2

Find the P@value for a left-tailed hypothesis test with a standardized test
statistic of z = -1.71. Decide whether to reject H0 when the level of
significance is a = 0.05.
Answer: Page A37
EX AMP LE 3
Finding a P-Value for a Two-Tailed Test

Find the P@value for a two-tailed hypothesis test with a standardized test
statistic of z = 2.14. Decide whether to reject H0 when the level of significance
is a = 0.05.
SO L UTION
The area to the right The figure at the left shows the standard normal curve with shaded areas to the
of z = 2.14 is 0.0162, so left of z = -2.14 and to the right of z = 2.14. For a two-tailed test,
P = 2(0.0162) = 0.0324.
P = 21Area in tail of standardized test statistic2.
Using Table 4, the area corresponding to z = 2.14 is 0.9838. The area in the
right tail is 1 - 0.9838 = 0.0162. So, the P@value for a two-tailed hypothesis
test with a standardized test statistic of z = 2.14 is
z P = 210.01622 = 0.0324.
−3 −2 −1 0 1 2 3
z = 2.14 Interpretation Because the P@value of 0.0324 is less than 0.05, you reject H0.
Two-Tailed Test T RY IT YOURSELF 3
Find the P@value for a two-tailed hypothesis test with a standardized test
statistic of z = 1.64. Decide whether to reject H0 when the level of significance
is a = 0.10.
Answer: Page A37

Using P@ Values for a z-Test

You will now learn how to perform a hypothesis test for a mean m assuming
the standard deviation s is known. When s is known, you can use a z@test for
the mean. To use the z@test, you need to find the standardized value for the test
statistic x. The standardized test statistic takes the form of
1Sample mean2 - 1Hypothesized mean2
z = .
Standard error
z-Test for a Mean M

The z@test for a mean M is a statistical test for a population mean. The test
statistic is the sample mean x. The standardized test statistic is
x - m
z = Standardized test statistic for m (s known)
s 1n
when these conditions are met.
1. The sample is random.
2. At least one of the following is true: The population is normally distributed
or n Ú 30.
Recall that s 1n is the standard error of the mean, sx.
GUI D E L I N E S
Note to Instructor
We use the same format for all Using P@Values for a z@Test for a Mean M (S Known)
hypothesis testing throughout the In Words In Symbols
text. Using the same format makes 1. Verify that s is known, the
it easier for students to understand
sample is random, and either the
the logic of the test. Emphasize
that the sampling distribution and,
population is normally distributed
consequently, the logic of the test or n Ú 30.
are based on the assumption that 2. State the claim mathematically State H0 and Ha.
the equality condition of the null and verbally. Identify the null
hypothesis is true. and alternative hypotheses.
3. Specify the level of significance. Identify a.
x - m
4. Find the standardized test statistic. z =
s 1n
5. Find the area that corresponds to z. Use Table 4 in
Appendix B.
6. Find the P@value.
a. For a left-tailed test, P = 1Area in left tail2.
b. For a right-tailed test, P = 1Area in right tail2.
c. For a two-tailed test, P = 21Area in tail of standardized test statistic2.
7. Make a decision to reject or fail If P … a, then reject H0.
to reject the null hypothesis. Otherwise, fail to reject H0.
8. Interpret the decision in the
context of the original claim.
With all hypothesis tests, it is helpful to sketch the sampling distribution.

Your sketch should include the standardized test statistic.

EX AMP LE 4
Hypothesis Testing Using a P-Value

In auto racing, a pit stop is where a racing vehicle stops for new tires, fuel,
repairs, and other mechanical adjustments. The efficiency of a pit crew that
makes these adjustments can affect the outcome of a race. A pit crew claims
that its mean pit stop time (for 4 new tires and fuel) is less than 13 seconds. A
random sample of 32 pit stop times has a sample mean of 12.9 seconds. Assume
the population standard deviation is 0.19 second. Is there enough evidence to
support the claim at a = 0.01? Use a P@value.
SO L UT ION
Because s is known 1s = 0.192, the sample is random, and n = 32 Ú 30, you
can use the z@test. The claim is “the mean pit stop time is less than 13 seconds.”
So, the null and alternative hypotheses are
H0: m Ú 13 seconds and Ha: m 6 13 seconds. (Claim)
The level of significance is a = 0.01. The standardized test statistic is
x - m
z = Because s is known and n Ú 30, use the z-test.
s 1n
12.9 - 13
= Assume m = 13.
0.19 232
≈ - 2.98. Round to two decimal places.
The area to the left Using Table 4 in Appendix B, the area corresponding to z = -2.98 is 0.0014.
of z = −2.98 is Because this test is a left-tailed test, the P@value is equal to the area to the left
P = 0.0014. of z = -2.98, as shown in the figure at the left. So, P = 0.0014. Because the
P@value is less than a = 0.01, you reject the null hypothesis. You can check your
answer using technology, as shown below. Note that the P@value differs slightly
from the one you found due to rounding.
−3 −2 −1 0 1 2 3
z
STATCRUNCH
z = − 2.98 One sample Z hypothesis test:
Left-Tailed Test μ : Mean of population
H0 : μ = 13
HA : μ 6 13
Standard deviation = 0.19
Hypothesis test results:

Mean n Sample Mean Std. Err. Z-Stat P-value
μ 32 12.9 0.033587572 - 2.9772917 0.0015
Interpretation There is enough evidence at the 1% level of significance to

support the claim that the mean pit stop time is less than 13 seconds.
T RY IT YOU RS ELF 4
Homeowners claim that the mean speed of automobiles traveling on their
street is greater than the speed limit of 35 miles per hour. A random sample
of 100 automobiles has a mean speed of 36 miles per hour. Assume the
population standard deviation is 4 miles per hour. Is there enough evidence to
support the claim at a = 0.05? Use a P@value.
Answer: Page A37

See Minitab steps

EX A M P L E 5 on page 414.
Hypothesis Testing Using a P-Value

According to a study of U.S. homes that use heating equipment, the mean
indoor temperature at night during winter is 68.3°F. You think this information
is incorrect. You randomly select 25 U.S. homes that use heating equipment
in the winter and find that the mean indoor temperature at night is 67.2°F.
From past studies, the population standard deviation is known to be 3.5°F and
the population is normally distributed. Is there enough evidence to support
your claim at a = 0.05? Use a P@value. (Adapted from U.S. Energy Information
Administration)
SO LU TION
Because s is known 1s = 3.5°F2, the sample is random, and the population is
normally distributed, you can use the z@test. The claim is “the mean is different
from 68.3°F.” So, the null and alternative hypotheses are
H0: m = 68.3°F and Ha: m ≠ 68.3°F. (Claim)
The level of significance is a = 0.05. The standardized test statistic is
x - m Because s is known and the population
z = is normally distributed, use the z@test.
s 1n
67.2 - 68.3
= Assume m = 68.3°F.
3.5 225
≈ -1.57. Round to two decimal places.
In Table 4, the area corresponding to z = -1.57 is 0.0582. Because the test is a

two-tailed test, the P@value is equal to twice the area to the left of z = -1.57,
as shown in the figure.
The area to the left of

z = − 1.57 is 0.0582, so
P = 2(0.0582) = 0.1164.
z
−3 −2 −1 0 1 2 3
z = − 1.57
Two-Tailed Test
So, the P@value is P = 2(0.0582) = 0.1164. Because the P@value is greater than
a = 0.05, you fail to reject the null hypothesis.
Interpretation There is not enough evidence at the 5% level of significance
to support the claim that the mean indoor temperature at night during winter
is different from 68.3°F for U.S. homes that use heating equipment.
TRY IT YOU RS ELF 5

According to a study of employed U.S. adults ages 18 and over, the mean
number of workdays missed due to illness or injury in the past 12 months
is 3.5 days. You randomly select 25 employed U.S. adults ages 18 and over
and find that the mean number of workdays missed is 4 days. Assume the
population standard deviation is 1.5 days and the population is normally
distributed. Is there enough evidence to doubt the study’s claim at a = 0.01?
Use a P@value. (Adapted from U.S. National Center for Health Statistics)
Answer: Page A37

EX AMP LE 6
Tech Tip Using Technology to Find a P-Value

Using a TI-84 Plus, you Use the TI-84 Plus displays to make a decision to reject or fail to reject the null
can either enter the hypothesis at a level of significance of a = 0.05.
original data into a list
to find a P@value or T I - 8 4 PLUS T I - 8 4 PLUS
enter the descriptive
statistics. Z-Test Z-Test
STAT Inpt:Data Stats µ≠6.2
µ0:6.2 z=- 2.013647416
Choose the TESTS menu.
s:.47 p=.0440464253
1: Z-Test...
x:6.07 x=6.07
Select the Data input option when n:53 n=53
you use the original data. Select the µ: ≠µ0 <µ0 >µ0
Stats input option when you use Calculate Draw
the descriptive statistics. In each
case, enter the appropriate values
including the corresponding type SO L UT ION
of hypothesis test indicated by the The P@value for this test is 0.0440464253. Because the P@value is less than
alternative hypothesis. Then select a = 0.05, you reject the null hypothesis.
Calculate.
TRY IT YOU RS ELF 6
Repeat Example 6 using a level of significance of a = 0.01.
Answer: Page A37
Rejection Regions and Critical Values

Another method to decide whether to reject the null hypothesis is to determine
whether the standardized test statistic falls within a range of values called the
rejection region of the sampling distribution.
DEFIN I T I O N
A rejection region (or critical region) of the sampling distribution is the range
α
z of values for which the null hypothesis is not probable. If a standardized test
z0 0 statistic falls in this region, then the null hypothesis is rejected. A critical
Left-Tailed Test value z0 separates the rejection region from the nonrejection region.
GUIDELI N E S
Finding Critical Values in the Standard Normal Distribution
1. Specify the level of significance a.
α
z0
z
2. Determine whether the test is left-tailed, right-tailed, or two-tailed.
0
3. Find the critical value(s) z0. When the hypothesis test is
Right-Tailed Test
a. left-tailed, find the z@score that corresponds to an area of a.
b. right-tailed, find the z@score that corresponds to an area of 1 - a.
c. two-tailed, find the z@scores that correspond to 12a and 1 - 12a.
1 1 4. Sketch the standard normal distribution. Draw a vertical line at each
α α
2 2 critical value and shade the rejection region(s). (See the figures at the left.)
z
− z0 0 z0
Note that a standardized test statistic that falls in a rejection region is
Two-Tailed Test considered an unusual event.

When you cannot find the exact area in Table 4, use the area that is closest.
For an area that is exactly midway between two areas in the table, use the z@score
midway between the corresponding z@scores.
EX A M P L E 7
Finding a Critical Value for a Left-Tailed Test

Find the critical value and rejection region for a left-tailed test with a = 0.01.
SO LUTI ON
The figure shows the standard normal
curve with a shaded area of 0.01 in the left
tail. In Table 4, the z@score that is closest
α = 0.01
to an area of 0.01 is -2.33. So, the critical
value is z
−3 −2 −1 0 1 2 3
z0 = -2.33. z0 = −2.33
The rejection region is to the left of this 1% Level of Significance
critical value. You can check your answer
using technology, as shown below.
EXCEL
A B
1 NORM.S.INV(0.01)
2 –2.32634787
TRY IT YOU RS ELF 7

Find the critical value and rejection region for a left-tailed test with a = 0.10.
Answer: Page A37
Because normal distributions are symmetric, in a two-tailed test the critical

values are opposites, as shown in the next example.
EX A M P L E 8
Finding Critical Values for a Two-Tailed Test

Study Tip
Find the critical values and rejection regions for a two-tailed test with a = 0.05.
The table lists the critical
values for commonly used SO LUTI ON
levels of significance. The figure shows the standard normal 1 − α = 0.95
curve with shaded areas of 12a = 0.025 in
Alpha Tail z 1 1
each tail. The area to the left of -z0 is α = 0.025 α = 0.025
2 2
1
0.10 Left - 1.28 2 a = 0.025, and the area to the left of z0
Right 1.28 is 1 - 12a = 0.975. In Table 4, the z@scores
Two { 1.645 z
that correspond to the areas 0.025 and −3 −2 −1 0 1 2 3
0.05 Left - 1.645 0.975 are -1.96 and 1.96, respectively. So, −z 0 = −1.96 z 0 = 1.96
Right 1.645 the critical values are
5% Level of Significance
Two { 1.96
-z0 = -1.96 and z0 = 1.96.
0.01 Left - 2.33
Right 2.33
The rejection regions are to the left of
Two { 2.575 -1.96 and to the right of 1.96.
Find the critical values and rejection regions for a two-tailed test with a = 0.08.
Answer: Page A37

Using Rejection Regions for a z-Test

To conclude a hypothesis test using rejection region(s), you make a decision and
interpret the decision according to the next rule.
Decision Rule Based on Rejection Region

To use a rejection region to conduct a hypothesis test, calculate the standardized
test statistic z. If the standardized test statistic
1. is in the rejection region, then reject H0.
2. is not in the rejection region, then fail to reject H0.
Fail to reject H0. Fail to reject H0.
z < z 0: Reject H0. z > z 0: Reject H0.
z z
z0 0 0 z0
Left-Tailed Test Right-Tailed Test
Fail to reject H0.
z < − z 0: Reject H0. z > z 0: Reject H0.
z
− z0 0 z0
Two-Tailed Test
Remember, failing to reject the null hypothesis does not mean that you have
accepted the null hypothesis as true. It simply means that there is not enough
evidence to reject the null hypothesis.
GUIDELI N E S
Using Rejection Regions for a z-Test for a Mean M (S Known)
In Words In Symbols
1. Verify that s is known, the
population is normally distributed
or n Ú 30.
2. State the claim mathematically State H0 and Ha.
and verbally. Identify the null
and alternative hypotheses.
4. Determine the critical value(s). Use Table 4 in Appendix B.
5. Determine the rejection region(s).
x - m
6. Find the standardized test statistic z =
and sketch the sampling distribution. s 1n
7. Make a decision to reject or fail to If z is in the rejection region,
reject the null hypothesis. then reject H0. Otherwise,
fail to reject H0.
8. Interpret the decision in the context
of the original claim.

See TI-84 Plus

EX A M P L E 9 steps on page 415.
Picturing Hypothesis Testing Using a Rejection Region
the World Employees at a construction and mining company claim that the mean
salary of the company’s mechanical engineers is less than that of one of its
Each year, the Environmental
competitors, which is $88,200. A random sample of 20 of the company’s
Protection Agency (EPA) publishes
reports of gas mileage for all mechanical engineers has a mean salary of $85,900. Assume the population
makes and models of passenger standard deviation is $9500 and the population is normally distributed. At
vehicles. In a recent year, the small a = 0.05, test the employees’ claim.
station wagon with an automatic
transmission that posted the best SO LU TION
mileage had a mean mileage of Because s is known 1s = $95002, the sample is random, and the population
52 miles per gallon (city) and is normally distributed, you can use the z@test. The claim is “the mean salary
49 miles per gallon (highway). is less than $88,200.” So, the null and alternative hypotheses can be written as
An auto manufacturer claims its
station wagons exceed 49 miles H0: m Ú $88,200 and Ha: m 6 $88,200. (Claim)
per gallon on the highway.
Because the test is a left-tailed test and the level of significance is a = 0.05,
To support its claim, it tests
36 vehicles on highway driving
the critical value is z0 = -1.645 and the rejection region is z 6 -1.645. The
and obtains a sample mean of standardized test statistic is
51.2 miles per gallon. Assume the x - m Because s is known and the population
population standard deviation is z =
s 1n is normally distributed, use the z@test.
4.8 miles per gallon. (Source: U.S.
Department of Energy) 85,900 - 88,200
= Assume m = $88,200.
9500 220
The figure shows the location of the rejection region and the standardized test
statistic z. Because z is not in the rejection region, you fail to reject the null
hypothesis.
1 − α = 0.95
α = 0.05
Is the evidence strong enough to
support the claim that the station
wagon’s highway miles per gallon z
exceeds the EPA estimate? Use a −2 −1 0 1 2
z-test with A = 0.01. z ≈ −1.08
z 0 = −1.645
There is enough evidence at the 1%
level of significance to conclude that Interpretation There is not enough evidence at the 5% level of significance
the mean mileage of the station wagon to support the employees’ claim that the mean salary is less than $88,200.
is greater than 49 miles per gallon on
the highway. Be sure you understand the decision made in this example. Even though
your sample has a mean of $85,900, you cannot (at a 5% level of significance)
support the claim that the mean of all the mechanical engineers’ salaries is less
than $88,200. The difference between your test statistic 1x = $85,9002 and the
hypothesized mean 1m = $88,2002 is probably due to sampling error.
TRY IT YOU RS ELF 9

The CEO of the company in Example 9 claims that the mean workday of the
company’s mechanical engineers is less than 8.5 hours. A random sample of
25 of the company’s mechanical engineers has a mean workday of 8.2 hours.
Assume the population standard deviation is 0.5 hour and the population is
normally distributed. At a = 0.01, test the CEO’s claim.
Answer: Page A37

EX AMP LE 1 0
Hypothesis Testing Using Rejection Regions

A researcher claims that the mean annual cost of raising a child (age 2 and
under) by married-couple families in the U.S. is $14,050. In a random sample
of married-couple families in the U.S., the mean annual cost of raising a child
(age 2 and under) is $13,795. The sample consists of 500 children. Assume the
population standard deviation is $2875. At a = 0.10, is there enough evidence
to reject the claim? (Adapted from U.S. Department of Agriculture Center for
Nutrition Policy and Promotion)
SO L UT ION
Because s is known 1s = $28752, the sample is random, and n = 500 Ú 30,
you can use the z@test. The claim is “the mean annual cost is $14,050.” So, the
null and alternative hypotheses are
H0: m = $14,050 (Claim) and Ha: m ≠ $14,050.
Because the test is a two-tailed test and the level of significance is a = 0.10,
the critical values are -z0 = -1.645 and z0 = 1.645. The rejection regions are
z 6 -1.645 and z 7 1.645. The standardized test statistic is
x - m
z = Because s is known and n Ú 30, use the z-test.
s 1n
13,795 - 14,050
= Assume m = $14,050.
2875 2500
The figure shows the location of the rejection regions and the standardized test
statistic z. Because z is in the rejection region, you reject the null hypothesis.
1 − α = 0.90
1 1
α = 0.05 α = 0.05
2 2
z
−3 −2 −1 0 1 2 3
z ≈ − 1.98 − z0 = − 1.645 z0 = 1.645
You can check your answer using technology, as shown below.
MINITAB
One-Sample Z
Test of μ = 14050 vs ≠ 14050
The assumed standard deviation = 2875
N Mean SE Mean 90% CI Z P
500 13795 129 (13584, 14006) - 1.98 0.047

reject the claim that the mean annual cost of raising a child (age 2 and under)
by married-couple families in the U.S. is $14,050.
TRY IT YOU RS ELF 1 0

In Example 10, at a = 0.01, is there enough evidence to reject the claim?
Answer: Page A37

1. The z-test using a P-value

compares the P-value with the 1. Explain the difference between the z@test for m using a P@value and the z@test
level of significance a. In the for m using rejection region(s).
z-test using rejection region(s),
the test statistic is compared 2. In hypothesis testing, does using the critical value method or the P@value
with critical values. method affect your conclusion? Explain.
2. No; Both involve comparing
Interpreting a P-Value In Exercises 3– 8, the P@value for a hypothesis test is
the test statistic’s probability
with the level of significance.
shown. Use the P@value to decide whether to reject H0 when the level of significance
The P-value method converts is (a) a = 0.01, (b) a = 0.05, and (c) a = 0.10.
the standardized test statistic 3. P = 0.0461 4. P = 0.0691
to a probability (P-value) and
compares this with the level of 5. P = 0.1271 6. P = 0.0107
significance, whereas the critical
value method converts the
7. P = 0.0838 8. P = 0.0062
level of significance to a z-score
Finding a P-Value In Exercises 9 –14, find the P@value for the hypothesis test
and compares this with the
standardized test statistic.
with the standardized test statistic z. Decide whether to reject H0 for the level of
significance a.
3. (a) Fail to reject H0.
(b) Reject H0. (c) Reject H0. 9. Left-tailed test 10. Left-tailed test
z = -1.32 z = -1.55
a = 0.10 a = 0.05
(b) Fail to reject H0.
(c) Reject H0. 11. Right-tailed test 12. Right-tailed test
z = 2.46 z = 1.23
a = 0.01 a = 0.10
(b) Fail to reject H0.
(c) Fail to reject H0. 13. Two-tailed test 14. Two-tailed test
z = -1.68 z = 1.95
a = 0.05 a = 0.08
(b) Reject H0. (c) Reject H0.
7. (a) Fail to reject H0. Graphical Analysis In Exercises 15 and 16, match each P@value with the
(b) Fail to reject H0. graph that displays its area without performing any calculations. Explain
(c) Reject H0. your reasoning.
8. (a) Reject H0. (b) Reject H0. 15. P = 0.0089 and P = 0.3050
(c) Reject H0. (a) (b)
9. P = 0.0934; Reject H0.
10. P = 0.0606; Fail to reject H0.
11. P = 0.0069; Reject H0.
12. P = 0.1093; Fail to reject H0. z z
−3 −2 −1 0 1 2 3 −3 −2 −1 0 1 2 3
13. P = 0.0930; Fail to reject H0. z = −2.37 z = −0.51
14. P = 0.0512; Reject H0.
15. (a) P = 0.0089 16. P = 0.0688 and P = 0.2802
(b)
P = 0.3050 (a) (b)
The larger P-value corresponds
to the larger area.
16. (a) P = 0.2802
(b)
P = 0.0688 z z
−3 −2 −1 0 1 2 3 −3 −2 −1 0 1 2 3
The larger P-value corresponds z = 1.08 z = 1.82
to the larger area.

17. Fail to reject H0. In Exercises 17 and 18, use the TI-84 Plus displays to make a decision to reject or
18. Reject H0. fail to reject the null hypothesis at the level of significance.
19. Critical value: z0 = - 1.88 17. a = 0.05
Rejection region: z 6 - 1.88

z
−3 −2 −1 0 1 2 3
z 0 = − 1.88
20. Critical value: z0 = - 1.34

Rejection region: z 6 - 1.34 18. a = 0.01

z
−3 −2 −1 0 1 2 3
z 0 = −1.34
21. Critical value: z0 = 1.645

Rejection region: z 7 1.645
Finding Critical Values and Rejection Regions In Exercises 19 –24,
find the critical value(s) and rejection region(s) for the type of z@test with level of
significance a. Include a graph with your answer.
z
−3 −2 −1 0 1 2 3
z 0 = 1.645 19. Left-tailed test, a = 0.03 20. Left-tailed test, a = 0.09
22. See Selected Answers, page A100. 21. Right-tailed test, a = 0.05 22. Right-tailed test, a = 0.08
23. See Odd Answers, page A69. 23. Two-tailed test, a = 0.02 24. Two-tailed test, a = 0.12
25. (a) Fail to reject H0 because Graphical Analysis In Exercises 25 and 26, state whether each standardized
z 6 1.285. test statistic z allows you to reject the null hypothesis. Explain your reasoning.
(b) Fail to reject H0 because 25. (a) z = -1.301 26. (a) z = 1.98
z 6 1.285.
(b) z = 1.203 (b) z = -1.89
(c) Fail to reject H0 because
z 6 1.285. (c) z = 1.280 (c) z = 1.65
(d) Reject H0 because z 7 1.285. (d) z = 1.286 (d) z = -1.99
26. (a) Reject H0 because z 7 1.96.
(b) Fail to reject H0 because
- 1.96 6 z 6 1.96.
- 1.96 6 z 6 1.96.
(d) Reject H0 because z 6 - 1.96. z z
−3 −2 −1 0 1 2 3 −3 −2 −1 0 1 2 3
27. Reject H0. There is enough
z 0 = 1.285 − z 0 = −1.96 z 0 = 1.96
evidence at the 5% level of
significance to reject the claim.
28. Fail to reject H0. There is not In Exercises 27–30, test the claim about the population mean m at the level of
enough evidence at the 7% level significance a. Assume the population is normally distributed.
of significance to support the
27. Claim: m = 40; a = 0.05; s = 1.97
claim.
Sample statistics: x = 39.2, n = 25
29. Fail to reject H0. There is not
enough evidence at the 3% level 28. Claim: m Ú 1475; a = 0.07; s = 29
of significance to support the Sample statistics: x = 1468, n = 26
claim.
29. Claim: m ≠ 5880; a = 0.03; s = 413
Sample statistics: x = 5771, n = 67
significance to reject the claim. 30. Claim: m … 22,500; a = 0.01; s = 1200
Sample statistics: x = 23,500, n = 45

31. (a) The claim is “the mean Using and Interpreting Concepts
total score for the school’s
applicants is more than 499.” Hypothesis Testing Using a P-Value In Exercises 31–36,
H0: m … 499

Ha: m 7 499 (claim) (a) identify the claim and state H0 and Ha.
(b) 2.83 (c) 0.0023 (b) find the standardized test statistic z.
(d) Reject H0. (c) find the corresponding P@value.
(e) There is enough evidence at
the 1% level of significance (d) decide whether to reject or fail to reject the null hypothesis.
to support the report’s claim (e) interpret the decision in the context of the original claim.
that the mean total score
for the school’s applicants is 31. MCAT Scores A random sample of 100 medical school applicants at a
more than 499. university has a mean total score of 502 on the MCAT. According to a
32. (a) The claim is “the average report, the mean total score for the school’s applicants is more than 499.
activating temperature is at Assume the population standard deviation is 10.6. At a = 0.01, is there
least 135°F.” enough evidence to support the report’s claim? (Source: Association of

H0: m Ú 135 (claim) American Medical Colleges)
Ha: m 6 135
32. Sprinkler Systems A manufacturer of sprinkler systems designed for fire
(b)
- 3.43 (c) 0.0003
protection claims that the average activating temperature is at least 135°F.
(d) Reject H0.
To test this claim, you randomly select a sample of 32 systems and find the
(e) There is enough evidence at mean activation temperature to be 133°F. Assume the population standard
the 10% level of significance deviation is 3.3°F. At a = 0.10, do you have enough evidence to reject the
to reject the manufacturer’s
manufacturer’s claim?
claim that the average
activating temperature is at 33. Boston Marathon A sports statistician claims that the mean winning
least 135°F. times for Boston Marathon women’s open division champions is at least
33. (a) The claim is “the mean 2.68 hours. The mean winning time of a sample of 30 randomly selected
winning times for Boston Boston Marathon women’s open division champions is 2.60 hours. Assume
Marathon women’s open the population standard deviation is 0.32 hour. At a = 0.05, can you reject
division champions is at the claim? (Source: Boston Athletic Association)
least 2.68 hours.”

H0: m Ú 2.68 (claim) 34. Acceleration Times A consumer group claims that the mean acceleration
Ha: m 6 2.68 time from 0 to 60 miles per hour for a sedan is 6.3 seconds. A random sample
of 33 sedans has a mean acceleration time from 0 to 60 miles per hour of
(b)
- 1.37 (c) 0.0853
7.2 seconds. Assume the population standard deviation is 2.5 seconds. At
(d) Fail to reject H0.
a = 0.05, can you reject the claim? (Source: Zero to 60 Times)
(e) There is not enough
evidence at the 5% level of 35. Roller Coasters The heights (in feet) of 36 randomly selected
significance to reject the top-rated roller coasters are listed. Assume the population standard
statistician’s claim that the deviation is 71.6 feet. At a = 0.05, is there enough evidence to reject
mean winning times for the claim that the mean height of top-rated roller coasters is 160 feet?
Boston Marathon women’s (Source: POP World Media, LLC)
open division champions is
at least 2.68 hours. 325 188 306 107 208 167 105 78 140
34. See Selected Answers, page A100. 232 230 170 170 205 305 135 200 200
100 223 135 195 80 90 120 210 82
161 245 88 70 116 121 146 149 124
36. Salaries An analyst claims that the mean annual salary for
intermediate level architects in Wichita, Kansas, is more than the
national mean, $52,000. The annual salaries (in dollars) for a random
sample of 21 intermediate level architects in Wichita are listed. Assume
the population is normally distributed and the population standard
deviation is $8000. At a = 0.09, is there enough evidence to support the
analyst’s claim? (Adapted from Salary.com)
47,066 58,955 59,774 56,016 52,487 41,258 43,806
44,291 44,063 44,365 40,120 49,853 50,233 43,827
56,085 48,967 57,983 60,295 57,776 46,500 47,658

37. (a) The claim is “the mean Hypothesis Testing Using Rejection Region(s) In Exercises 37– 42,
caffeine content per (a) identify the claim and state H0 and Ha, (b) find the critical value(s) and identify
12-ounce bottle of a the rejection region(s), (c) find the standardized test statistic z, (d) decide whether
population of caffeinated soft to reject or fail to reject the null hypothesis, and (e) interpret the decision in the
drinks is 37.7 milligrams.”

H0: m = 37.7 (claim)
Ha: m ≠ 37.7 37.
Caffeine Content A consumer research organization states that the mean
(b) - z0 = - 2.575, z0 = 2.575 caffeine content per 12-ounce bottle of a population of caffeinated soft
Rejection regions: drinks is 37.7 milligrams. You want to test this claim. During your tests,
z 6 -2.575, z 7 2.575 you find that a random sample of thirty-six 12-ounce bottles of caffeinated
(c)
- 0.72 (d) Fail to reject H0. soft drinks has a mean caffeine content of 36.4 milligrams. Assume the
population standard deviation is 10.8 milligrams. At a = 0.01, can you reject
evidence at the 1% level
the research organization’s claim? (Source: National Soft Drink Association)
of significance to reject 38. High School Graduation Rate An education researcher claims that the
the consumer research mean high school graduation rate per state in the United States is 80%. You
organization’s claim that want to test this claim. You find that a random sample of 30 states has a
the mean caffeine content
mean high school graduation rate of 82%. Assume the population standard
per 12-ounce bottle of a
population of caffeinated
deviation is 5.1%. At a = 0.05, do you have enough evidence to support the
soft drinks is 37.7 milligrams. researcher’s claim? (Source: U.S. Department of Education)
38. (a) The claim is “the mean high 39. Fast Food A fast food restaurant estimates that the mean sodium content
school graduation rate per in one of its breakfast sandwiches is no more than 920 milligrams. A
state in the United States is random sample of 44 breakfast sandwiches has a mean sodium content of
80%.” 925 milligrams. Assume the population standard deviation is 18 milligrams.

H0: m = 80 (claim) At a = 0.10, do you have enough evidence to reject the restaurant’s claim?
Ha: m ≠ 80
40. Light Bulbs A light bulb manufacturer guarantees that the mean life
(b) - z0 = - 1.96, - z0 = 1.96
Rejection regions: z 6 - 1.96,
of a certain type of light bulb is at least 750 hours. A random sample of
z 7 1.96 25 light bulbs has a mean life of 745 hours. Assume the population is
normally distributed and the population standard deviation is 60 hours. At
(c) 2.15 (d) Reject H0.
a = 0.02, do you have enough evidence to reject the manufacturer’s claim?
(e) There is enough evidence at
the 5% level of significance 41. Fluorescent Lamps A fluorescent lamp manufacturer guarantees that
to reject the education the mean life of a fluorescent lamp is at least 10,000 hours. You want to
researcher’s claim that the test this guarantee. To do so, you record the lives of a random sample
mean high school graduation of 32 fluorescent lamps. The results (in hours) are listed. Assume the
rate per state in the United population standard deviation is 1850 hours. At a = 0.11, do you have
States is 80%. enough evidence to reject the manufacturer’s claim?
8,800 9,155 13,001 10,250 10,002 11,413 8,234 10,402
10,016 8,015 6,110 11,005 11,555 9,254 6,991 12,006
41. See Odd Answers, page A69. 10,420 8,302 8,151 10,980 10,186 10,003 8,814 11,445
6,277 8,632 7,265 10,584 9,397 11,987 7,556 10,380
Carbon dioxide emissions

42.
Carbon Dioxide Emissions A scientist estimates that the mean
(in megatons) carbon dioxide emissions per country in a recent year are greater than
150 megatons. You want to test this estimate. To do so, you determine
340 76 46 44 75 1617 the carbon dioxide emissions for 42 randomly selected countries for that
34 43 23 0.5 0.3 6 year. The results (in megatons) are shown in the table at the left. Assume
0.3 0.7 11 0.1 0.2 7.6
0.6 0.6 26 9.9 2.3 8.2 the population standard deviation is 816 megatons. At a = 0.06, can
3.4 0.1 472 4.2 4.2 0 you support the scientist’s estimate? (Source: Global Carbon Project)
113 21 7.2 5 0.1 16
0.2 45 5.1 175 0 4.1
Extending Concepts
TABLE FOR EXERCISE 42
43. Writing When P 7 a, does the standardized test statistic lie inside or
42. See Selected Answers, page A100. outside of the rejection region(s)? Explain your reasoning.
43. See Odd Answers, page A69. 44.
Writing In a right-tailed test where P 6 a, does the standardized test
44. See Selected Answers, page A100. statistic lie to the left or the right of the critical value? Explain your reasoning.

S EC T IO N 7 . 3 Hypothesis Testing for the Mean (s Unknown) 377
7.3 Hypothesis Testing for the Mean (s Unknown)

Critical Values in a t@Distribution The t@Test for a Mean m Using
P-Values with t@Tests
H
ow to find critical values in a
t-distribution
H
ow to use the t-test to test a Critical Values in a t@ Distribution
mean m when s is not known In Section 7.2, you learned how to perform a hypothesis test for a population
H
ow to use technology to find mean when the population standard deviation is known. In many real-life
P-values and use them with a situations, the population standard deviation in not known. When either the
t-test to test a mean m when s population has a normal distribution or the sample size is at least 30, you can still
is not known test the population mean m. To do so, you can use the t@distribution with n - 1
degrees of freedom.
GUI D E L I N E S
Note to Instructor Finding Critical Values in a t@Distribution
A thoughtful student might ask what 1. Specify the level of significance a.
should be done if the sample size is
2. Identify the degrees of freedom, d.f. = n - 1.
small, the standard deviation is not
known, and you cannot assume that 3. Find the critical value(s) using Table 5 in Appendix B in the row with
the population is normally distributed. n - 1 degrees of freedom. When the hypothesis test is
Chapter 11 will cover this case (see a. left-tailed, use the “One Tail, a” column with a negative sign.
nonparametric tests). You can cover
these tests immediately after this b. right-tailed, use the “One Tail, a” column with a positive sign.
section if desirable. c. two-tailed, use the “Two Tails, a” column with a negative and a
positive sign.
See the figures below.
1 1
2
α 2
α
α α
t t t
t0 0 0 t0 − t0 0 t0
Left-Tailed Test Right-Tailed Test Two-Tailed Test
EX A M P L E 1

Find the critical value t0 for a left-tailed test with a = 0.05 and n = 21.
SO LUTI ON
The degrees of freedom are
α = 0.05
d.f. = n - 1 = 21 - 1 = 20.
t
−3 −2 −1 0 1 2 3 To find the critical value, use Table 5 in Appendix B with d.f. = 20 and
t0 = − 1.725 a = 0.05 in the “One Tail, a” column. Because the test is left-tailed, the critical
5% Level of Significance value is negative. So, t0 = -1.725, as shown in the figure at the left.
Find the critical value t0 for a left-tailed test with a = 0.01 and n = 14.
Answer: Page A37

EX AMP LE 2
Finding a Critical Value for a Right-Tailed Test

Find the critical value t0 for a right-tailed test with a = 0.01 and n = 17.
SO L UTI ON
d.f. = n - 1
= 17 - 1
= 16.
To find the critical value, use Table 5 with
d.f. = 16 and a = 0.01 in the “One Tail, a” α = 0.01
column. Because the test is right-tailed, the
critical value is positive. So, t
− 4 −3 −2 − 1 0 1 2 3 4
t0 = 2.583 t0 = 2.583
as shown in the figure. 1% Level of Significance
TRY IT YOU RS ELF 2

Find the critical value t0 for a right-tailed test with a = 0.10 and n = 9.
Answer: Page A37
Because t-distributions are symmetric, in a two-tailed test the critical values

are opposites, as shown in the next example.
EX AMP LE 3

Find the critical values -t0 and t0 for a two-tailed test with a = 0.10 and n = 26.
SO L UTI ON
d.f. = n - 1
= 26 - 1
= 25.
To find the critical values, use Table 5 with d.f. = 25 and a = 0.10 in the “Two
1 1
2
α = 0.05 2
α = 0.05 Tails, a” column. Because the test is two-tailed, one critical value is negative
and one is positive. So,
t
−4 −3 − 2 − 1 0 1 2 3 4 -t0 = -1.708 and t0 = 1.708
− t0 = − 1.708 t0 = 1.708
as shown in the figure at the left. You can check your answer using technology,
10% Level of Significance as shown below.
EXCEL
A B
1 T.INV.2T(0.1,25)
2 1.708140761
Find the critical values -t0 and t0 for a two-tailed test with a = 0.05 and n = 16.
Answer: Page A37

The t@ Test for a Mean M

Picturing To test a claim about a mean m when s is not known, you can use a t@sampling
distribution. The standardized test statistic takes the form of
the World t =
1Sample mean2 - 1Hypothesized mean2
.
Exposure to lead may cause Standard error
health problems ranging from
stomach distress to brain damage. Because s is not known, the standardized test statistic is calculated using the
The Environmental Protection sample standard deviation s, as shown in the next definition.
Agency established rules that
require water systems to monitor t-Test for a Mean M
drinking water at customer
taps. If lead concentrations The t@test for a mean M is a statistical test for a population mean. The test
exceed 0.015 milligram per liter statistic is the sample mean x. The standardized test statistic is
in more than 10% of customer
taps sampled, the system must x - m
t = Standardized test statistic for m (s unknown)
undertake a number of actions, s 1n
such as source water treatment,
public education, and lead when these conditions are met.
service line replacement. On the 1. The sample is random.
basis of a t-test, a water system
2. At least one of the following is true: The population is normally distributed
makes a decision on whether the
or n Ú 30.
mean level of lead in the water
exceeds the allowable amount of The degrees of freedom are d.f. = n - 1.
0.015 milligram per liter. Assume
the null hypothesis is m … 0.015.
(Source: Environmental Protection Agency) GUI D E L I N E S
H0 True H0 False Using the t@Test for a Mean M (S Unknown)
Fail to In Words In Symbols
reject H0.
1. Verify that s is not known, the
Reject H0. population is normally distributed
or n Ú 30.
Describe the possible type I and 2. State the claim mathematically State H0 and Ha.
type II errors of this situation. and verbally. Identify the null
A type I error will occur when the
actual amount of lead is less than or 4. Identify the degrees of freedom. d.f. = n - 1
equal to 0.015 milligram per liter, but 5. Determine the critical value(s). Use Table 5 in Appendix B.
you reject H0: m … 0.015. So, even
though the water is safe, the water
x - m
system will undertake actions that are 7. Find the standardized test statistic t =
not needed and possibly cause a public and sketch the sampling s 1n
panic. A type II error will occur when distribution.
the actual amount of lead is greater
than 0.015 milligram per liter, but you 8. Make a decision to reject or fail to If t is in the rejection region,
fail to reject H0: m … 0.015. So, the reject the null hypothesis. then reject H0. Otherwise,
water system will not undertake actions fail to reject H0.
to protect the public from water that 9. Interpret the decision in the context
has too much lead, which could cause of the original claim.
health problems.
In Step 8 of the guidelines, the decision rule uses rejection regions. You can
also test a claim using P-values, as shown on page 382. Also, when the number
of degrees of freedom you need is not in Table 5, use the closest number in the
table that is less than the value you need (or use technology). For instance, for
d.f. = 57, use 50 degrees of freedom.

See Minitab steps

EX AMP LE 4 on page 414.
Hypothesis Testing Using a Rejection Region

A used car dealer says that the mean price of used cars sold in the last
12 months is at least $21,000. You suspect this claim is incorrect and find
that a random sample of 14 used cars sold in the last 12 months has a mean
price of $19,189 and a standard deviation of $2950. Is there enough evidence
to reject the dealer’s claim at a = 0.05? Assume the population is normally
distributed. (Adapted from Edmunds.com)
SO L UT ION
Because s is unknown, the sample is random, and the population is normally
distributed, you can use the t@test. The claim is “the mean price is at least
$21,000.” So, the null and alternative hypotheses are
H0: m Ú $21,000 (Claim)
and
Ha: m 6 $21,000.
The test is a left-tailed test, the level of significance is a = 0.05, and the
degrees of freedom are
d.f. = 14 - 1 = 13.
So, using Table 5, the critical value is t0 = -1.771. The rejection region is
t 6 -1.771. The standardized test statistic is
x - m Because s is unknown and the population
t =
s 1n is normally distributed, use the t@test.
19,189 - 21,000
= Assume m = 21,000.
2950 214
≈ -2.297. Round to three decimal places.
To explore this topic further, The figure shows the location of the
7.3 see Activity 7.3 on page 386. rejection region and the standardized test
statistic t. Because t is in the rejection
region, you reject the null hypothesis.
α = 0.05
Interpretation There is enough evidence
at the 5% level of significance to reject t
the claim that the mean price of used −3 −2 −1 0 1 2 3
cars sold in the last 12 months is at least t ≈ − 2.297 t0 = −1.771

$21,000. 5% Level of Significance
TRY IT YOU RS ELF 4

An industry analyst says that the mean age of a used car sold in the last
12 months is less than 4.1 years. A random sample of 25 used cars sold in
the last 12 months has a mean age of 3.7 years and a standard deviation of
1.3 years. Is there enough evidence to support the analyst’s claim at a = 0.10?
Assume the population is normally distributed. (Adapted from Edmunds.com)
Answer: Page A37
Remember that when you make a decision, the possibility of a type I or a

type II error exists. For instance, in Example 4, a type I error is possible when
you reject H0, because m Ú $21,000 may be true.

See TI-84 Plus

Hypothesis Testing Using Rejection Regions

An industrial company claims that the mean pH level of the water in a nearby
river is 6.8. You randomly select 39 water samples and measure the pH of each.
The sample mean and standard deviation are 6.7 and 0.35, respectively. Is there
enough evidence to reject the company’s claim at a = 0.05?
SO LU TION
Because s is unknown, the sample is random, and n = 39 Ú 30, you can use
the t@test. The claim is “the mean pH level is 6.8.” So, the null and alternative
hypotheses are
H0: m = 6.8 (Claim) and Ha: m ≠ 6.8.
The test is a two-tailed test, the level of significance is a = 0.05, and the
degrees of freedom are d.f. = 39 - 1 = 38. So, using Table 5, the critical
values are -t0 = -2.024 and t0 = 2.024. The rejection regions are t 6 -2.024
and t 7 2.024. The standardized test statistic is
x - m
t = Because s is unknown and n Ú 30, use the t@test.
s 1n
6.7 - 6.8
= Assume m = 6.8.
0.35 239
≈ -1.784. Round to three decimal places.
The figure shows the location

of the rejection regions and
the standardized test statistic
t. Because t is not in the
rejection region, you fail to
1 1
reject the null hypothesis. 2
α = 0.025 2
α = 0.025
You can confirm this
t
decision using technology, as −4 −3 −1 0 1 2 3 4
shown below. Note that the
−t0 = −2.024 t ≈ −1.784 t0 = 2.024
standardized statistic t differs
from the one found using 5% Level of Significance
Table 5 due to rounding.
MINITAB
One-Sample T
Test of μ = 6.8 vs ≠ 6.8
N Mean StDev SE Mean 95% CI T P

3 9 6.7000 0.3500 0.0560 (6.5865, 6.8135) - 1.78 0.082

to reject the claim that the mean pH level is 6.8.
The company in Example 5 claims that the mean conductivity of the river is
1890 milligrams per liter. The conductivity of a water sample is a measure of
the total dissolved solids in the sample. You randomly select 39 water samples
and measure the conductivity of each. The sample mean and standard deviation
are 2350 milligrams per liter and 900 milligrams per liter, respectively. Is there
enough evidence to reject the company’s claim at a = 0.01?
Answer: Page A37

Using P@ Values With t@ Tests

You can also use P@values for a t@test for a mean m. For instance, consider finding
Tech Tip a P@value given t = 1.98, 15 degrees of freedom, and a right-tailed test. Using
Using a TI-84 Plus, you Table 5 in Appendix B, you can determine that P falls between
can either enter the a = 0.025 and a = 0.05
original data into a list
to find a P-value or but you cannot determine an exact value for P. In such cases, you can use
enter the descriptive technology to perform a hypothesis test and find exact P@values.
statistics.
STAT EX AMP LE 6
Choose the TESTS menu.
2: T-Test... Using P-Values with a t-Test
Select the Data input option when A department of motor vehicles office claims that the mean wait time is less
you use the original data. Select the than 14 minutes. A random sample of 10 people has a mean wait time of
Stats input option when you use 13 minutes with a standard deviation of 3.5 minutes. At a = 0.10, test the
the descriptive statistics. In each office’s claim. Assume the population is normally distributed.
case, enter the appropriate values,
including the corresponding type SO L UT ION
of hypothesis test indicated by the Because s is unknown, the sample is random, and the population is normally
alternative hypothesis. Then select distributed, you can use the t@test. The claim is “the mean wait time is less than
Calculate. 14 minutes.” So, the null and alternative hypotheses are
H0: m Ú 14 minutes
and
Ha: m 6 14 minutes. (Claim)
The TI-84 Plus display at the far left shows how to set up the hypothesis test.
The two displays on the right show the possible results, depending on whether
you select Calculate or Draw.
T I - 8 4 PLUS T I - 8 4 PLUS T I - 8 4 PLUS
T-Test T-Test
Inpt:Data Stats µ<14
µ0:14 t= - .9035079029
x:13 p=.1948994027
Sx:3.5
n:10 x=13
t=-.9035 p=.1949
µ:≠µ0 <µ0 >µ0 Sx=3.5
Calculate Draw n=10
From the displays, you can see that

P ≈ 0.1949.
Because the P@value is greater than a = 0.10, you fail to reject the null
hypothesis.
to support the office’s claim that the mean wait time is less than 14 minutes.
TRY IT YOU RS ELF 6

Another department of motor vehicles office claims that the mean wait time
is at most 18 minutes. A random sample of 12 people has a mean wait time
of 15 minutes with a standard deviation of 2.2 minutes. At a = 0.05, test the
office’s claim. Assume the population is normally distributed.
Answer: Page A37


2. See Selected Answers, page A100. 1. Explain how to find critical values for a t@distribution.
3. Critical value: t0 = - 1.328 2. Explain how to use a t@test to test a hypothesized mean m when s is unknown.
Rejection region: t 6 -1.328 What assumptions are necessary?
4. Critical value: t0 = - 2.441
Rejection region: t 6 -2.441
In Exercises 3– 8, find the critical value(s) and rejection region(s) for the type of
t-test with level of significance a and sample size n.
5. Critical value: t0 = 1.717
Rejection region: t 7 1.717 3. Left-tailed test, a = 0.10, n = 20 4. Left-tailed test, a = 0.01, n = 35
6. Critical value: t0 = 2.457 5. Right-tailed test, a = 0.05, n = 23 6. Right-tailed test, a = 0.01, n = 31
Rejection region: t 7 2.457
7. Two-tailed test, a = 0.05, n = 27 8. Two-tailed test, a = 0.10, n = 38
7. Critical values: - t0 = - 2.056,
t0 = 2.056 Graphical Analysis In Exercises 9–12, state whether each standardized test
Rejection regions: t 6 -2.056,
statistic t allows you to reject the null hypothesis. Explain.
t 7 2.056
8. Critical values: - t0 = - 1.687, 9. (a) t = 2.091 10. (a) t = 1.4
t0 = 1.687 (b) t = 0 (b) t = 1.42
t 7 1.687
(c) t = -2.096 (c) t = -1.402
9. (a) Fail to reject H0 because
t 7 -2.086.
t 7 -2.086.
(c) Reject H0 because
t 6 -2.086. t t
−4 −3 −1 0 1 2 3 4 −4 − 3 − 2 − 1 0 1 2 3 4
10. (a) Fail to reject H0 because t0 = −2.086 t0 = 1.402
t 6 1.402.
(b) Reject H0 because t 7 1.402. 11. (a) t = -1.755 12. (a) t = -1.1
(c) Fail to reject H0 because (b) t = -1.585 (b) t = 1.01
t 6 1.402. (c) t = 1.745 (c) t = 1.7
11. (a) Reject H0 because

t 6 -1.725.
- 1.725 6 t 6 1.725.
(c) Reject H0 because t 7 1.725.
12. (a) Reject H0 because t t
t 6 -1.071. − 4 − 3 −2 − 1 0 1 2 3 4 −4 − 3 −2 − 1 0 1 2 3 4
−t0 = −1.725 t0 = 1.725 − t0 = −1.071 t0 = 1.071
- 1.071 6 t 6 1.071.
In Exercises 13–18, test the claim about the population mean m at the level of
(c) Reject H0 because t 7 1.071.
significance a. Assume the population is normally distributed.
enough evidence at the 1% 13. Claim: m = 15; a = 0.01. Sample statistics: x = 13.9, s = 3.23, n = 36
level of significance to reject the
claim.
14. Claim: m 7 25; a = 0.05. Sample statistics: x = 26.2, s = 2.32, n = 17
14. See Selected Answers, page A100. 15. Claim: m Ú 8000; a = 0.01. Sample statistics: x = 7700, s = 450, n = 25
15. See Odd Answers, page A69. 16. Claim: m … 1600; a = 0.02. Sample statistics: x = 1550, s = 165, n = 46
17. Claim: m 6 4915; a = 0.02. Sample statistics: x = 5017, s = 5613, n = 51
18. See Selected Answers, page A100. 18. Claim: m ≠ 52,200; a = 0.05. Sample statistics: x = 53,220, s = 2700, n = 34

19. (a) The claim is “the mean Using and Interpreting Concepts
price of a three-year-old
sport utility vehicle (in good Hypothesis Testing Using Rejection Regions In Exercises 19–26,
condition) is $20,000.” (a) identify the claim and state H0 and Ha, (b) find the critical value(s) and identify the
H0: m = 20,000 (claim)
rejection region(s), (c) find the standardized test statistic t, (d) decide whether to reject
Ha: m ≠ 20,000 or fail to reject the null hypothesis, and (e) interpret the decision in the context of the
(b) - t0 = -2.080, t0 = 2.080 original claim. Assume the population is normally distributed.
Rejection regions:
t 6 -2.080, t 7 2.080 19.
Used Car Cost A used car dealer says that the mean price of a three-year-old
sport utility vehicle (in good condition) is $20,000. You suspect this claim is
(c) 1.51 (d) Fail to reject H0.
incorrect and find that a random sample of 22 similar vehicles has a mean
price of $20,640 and a standard deviation of $1990. Is there enough evidence
to reject the claim at a = 0.05?
significance to reject the
claim that the mean price of 20. D
MV Wait Times A state Department of Transportation claims that
a three-year-old sport utility the mean wait time for various services at its different locations is at most
vehicle (in good condition) is 6 minutes. A random sample of 34 services at different locations has a mean
$20,000.
wait time of 10.3 minutes and a standard deviation of 8.0 minutes. Is there
20. (a) The claim is “the mean wait enough evidence to reject the claim at a = 0.01?
time for various services at
different locations is at most 21. Credit Card Debt A credit reporting agency claims that the mean credit
6 minutes.” card debt by state is greater than $5500 per person. You want to test this
H0: m … 6 (claim); Ha: m 7 6 claim. You find that a random sample of 30 states has a mean credit card
(b) t0 = 2.445 debt of $5594 per person and a standard deviation of $597 per person. At
Rejection region: t 7 2.445 a = 0.05, can you support the claim? (Adapted from TransUnion)
(c) 3.13 (d) Reject H0. 22. Battery Life A company claims that the mean battery life of their MP3
(e) There is enough evidence at player is at least 30 hours. You suspect this claim is incorrect and find that a
the 1% level of significance random sample of 18 MP3 players has a mean battery life of 28.5 hours and a
to reject the state Department standard deviation of 1.7 hours. Is there enough evidence to reject the claim
of Transportation’s claim at a = 0.01?
that the mean wait time
for various services at 23.
Carbon Monoxide Levels As part of your work for an environmental
different locations is at most awareness group, you want to test a claim that the mean amount of carbon
6 minutes. monoxide in the air in U.S. cities is less than 2.34 parts per million. You find
21. See Odd Answers, page A70. that the mean amount of carbon monoxide in the air for a random sample
22. See Selected Answers, page A101. of 64 U.S. cities is 2.37 parts per million and the standard deviation is 2.11
parts per million. At a = 0.10, can you support the claim? (Adapted from U.S.
Environmental Protection Agency)
25. See Odd Answers, page A70. 24. Lead Levels As part of your work for an environmental awareness group,
you want to test a claim that the mean amount of lead in the air in U.S. cities
26. See Selected Answers, page A101..
is less than 0.036 microgram per cubic meter. You find that the mean amount
of lead in the air for a random sample of 56 U.S. cities is 0.039 microgram per
Annual salaries cubic meter and the standard deviation is 0.069 microgram per cubic meter.
At a = 0.01, can you support the claim? (Adapted from U.S. Environmental
100,651 82,505 102,450 91,091 Protection Agency)
96,309 74,193 76,184 82,088
93,551 77,012 104,020 85,063 25.
Annual Salary An employment information service claims the mean
112,717 80,970 103,982 110,316 annual salary for senior level product engineers is $98,000. The annual
salaries (in dollars) for a random sample of 16 senior level product engineers
TABLE FOR EXERCISE 25 are shown in the table at the left. At a = 0.05, test the claim that the mean
salary is $98,000. (Adapted from Salary.com)
Annual salaries
26. Annual Salary An employment information service claims the mean annual
89,245 86,013 83,151 69,771 salary for home care physical therapists is more than $80,000. The annual
87,834 67,964 76,523 90,268 salaries (in dollars) for a random sample of 12 home care physical therapists
90,440 93,538 76,999 68,257 are shown in the table at the left. At a = 0.10, is there enough evidence to
support the claim that the mean salary is more than $80,000? (Adapted from
TABLE FOR EXERCISE 26 Salary.com)

27. (a) The claim is “the mean Using a P-Value with a t-Test In Exercises 27–30, (a) identify the claim
minimum time it takes and state H0 and Ha, (b) use technology to find the P-value, (c) decide whether
for a sedan to travel a to reject or fail to reject the null hypothesis, and (d) interpret the decision in the
quarter mile is greater than context of the original claim. Assume the population is normally distributed.
14.7 seconds.”

H0: m … 14.7 27. Quarter Mile Times A consumer group claims that the mean minimum
Ha: m 7 14.7 (claim) time it takes for a sedan to travel a quarter mile is greater than 14.7 seconds.
(b) 0.0664 (c) Reject H0. A random sample of 22 sedans has a mean minimum time to travel a quarter
mile of 15.4 seconds and a standard deviation of 2.10 seconds. At a = 0.10,
(d) There is enough evidence at
the 10% level of significance
do you have enough evidence to support the consumer group’s claim?
to support the consumer (Adapted from Zero to 60 Times)
group’s claim that the 28. Dive Duration An oceanographer claims that the mean dive duration of
mean minimum time it a North Atlantic right whale is 11.5 minutes. A random sample of 34 dive
takes for a sedan to travel a
durations has a mean of 12.2 minutes and a standard deviation of 2.2 minutes.
quarter mile is greater than
14.7 seconds.
Is there enough evidence to reject the claim at a = 0.10? (Source: Marine
Ecology Progress Series)
29. Class Size You receive a brochure from a large university. The brochure
Class sizes
indicates that the mean class size for full-time faculty is fewer than
35 28 29 33 32 40 32 students. You want to test this claim. You randomly select 18 classes
26 25 29 28 30 36 taught by full-time faculty and determine the class size of each. The
33 29 27 30 28 25 results are shown in the table at the left. At a = 0.05, can you support the
university’s claim?
30. F
aculty Classroom Hours The dean of a university estimates that the
mean number of classroom hours per week for full-time faculty is 11.0. As a
Classroom hours member of the student council, you want to test this claim. A random sample
11.8 8.6 12.6 7.9 of the number of classroom hours for eight full-time faculty for one week is
6.4 10.4 13.6 9.1 shown in the table at the left. At a = 0.01, can you reject the dean’s claim?

Extending Concepts
28. (a) The claim is “the mean dive
Deciding on a Distribution In Exercises 31 and 32, decide whether you
duration of a North Atlantic
should use the standard normal sampling distribution or a t-sampling distribution
right whale is 11.5 minutes.”
to perform the hypothesis test. Justify your decision. Then use the distribution to

H0: m = 11.5 (claim)
test the claim. Write a short paragraph about the results of the test and what you
Ha: m ≠ 11.5
can conclude about the claim.
(b) 0.0725 (c) Reject H0.
(d) There is enough evidence at 31. Gas Mileage A car company claims that the mean gas mileage for its
the 10% level of significance luxury sedan is at least 23 miles per gallon. You believe the claim is
to reject the oceanographer’s incorrect and find that a random sample of 5 cars has a mean gas mileage
claim that the mean dive of 22 miles per gallon and a standard deviation of 4 miles per gallon.
duration of a North Atlantic At a = 0.05, test the company’s claim. Assume the population is
right whale is 11.5 minutes. normally distributed.
32. Tuition and Fees An education publication claims that the mean in-state
30. See Selected Answers, page A101. tuition and fees at public four-year institutions by state is more than
31. See Odd Answers, page A70. $9000 per year. A random sample of 30 states has a mean in-state tuition
32. See Selected Answers, page A101. and fees at public four-year institutions of $9231 per year. Assume the
33. See Odd Answers, page A70. population standard deviation is $2380. At a = 0.01, test the publication’s
claim. (Adapted from The College Board)
33. Writing You are testing a claim and incorrectly use the standard normal
sampling distribution instead of the t@sampling distribution. Does this make
it more or less likely to reject the null hypothesis? Is this result the same
no matter whether the test is left-tailed, right-tailed, or two-tailed? Explain
your reasoning.

7.3 Hypothesis Tests for a Mean

ACTIVITY
The hypothesis tests for a mean applet allows you to visually investigate hypothesis
tests for a mean. You can specify the sample size n, the shape of the distribution
APPLET
(Normal or Right skewed), the true population mean (Mean), the true population
You can find the interactive standard deviation (Std. Dev.), the null value for the mean (Null mean), and the
applet for this activity alternative for the test (Alternative). When you click SIMULATE, 100 separate
within MyLab Statistics or at samples of size n will be selected from a population with these population
www.pearsonhighered.com/ parameters. For each of the 100 samples, a hypothesis test based on the T statistic
mathstatsresources.
is performed, and the results from each test are displayed in the plots at the right.
The test statistic for each test is shown in the top plot and the P@value is shown
in the bottom plot. The green and blue lines represent the cutoffs for rejecting
the null hypothesis with the 0.05 and 0.01 level tests, respectively. Additional
simulations can be carried out by clicking SIMULATE multiple times. The
cumulative number of times that each test rejects the null hypothesis is also
shown. Press CLEAR to clear existing results and start a new simulation.
EX PLOR E n: 50
Distribution: Normal
Step 1 Specify a value for n. Mean: 50
Step 2 Specify a distribution. Std. Dev.: 10
Step 3 Specify a value for the mean. Null mean: 50
Step 4
Specify a value for the Alternative: <
standard deviation. Simulate

Step 5 Specify a value for the
null mean. Cumulative results:
Step 6 Specify an alternative 0.05 level 0.01 level
hypothesis. Reject null
Step 7 Click SIMULATE to Fail to reject null
generate the hypothesis tests. Prop. rejected
Clear
DRAW C O N C L U S I O N S
1. Set n = 15, Mean = 40, Std. Dev. = 5, and the distribution to “Normal.”
Test the claim that the mean is equal to 40. What are the null and alternative
APPLET
hypotheses? Run the simulation so that at least 1000 hypothesis tests are run.
Compare the proportion of null hypothesis rejections for the 0.05 level and the
0.01 level. Is this what you would expect? Explain.
2. Suppose a null hypothesis is rejected at the 0.01 level. Will it be rejected at the
0.05 level? Explain. Suppose a null hypothesis is rejected at the 0.05 level. Will
it be rejected at the 0.01 level? Explain.
3. Set n = 25, Mean = 25, Std. Dev. = 3, and the distribution to “Normal.”
Test the claim that the mean is at least 27. What are the null and alternative
hypotheses? Run the simulation so that at least 1000 hypothesis tests are run.
Compare the proportion of null hypothesis rejections for the 0.05 level and the
0.01 level. Is this what you would expect? Explain.
386
386 CHAPTE R 7 Hypothesis Testing with One Sample

CASE Human Body Temperature: What’s Normal?

STUDY
In an article in the Journal of Statistics Education Men’s Temperatures
(vol. 4, no. 2), Allen Shoemaker describes a study that (in degrees Fahrenheit)
was reported in the Journal of the American Medical
Association (JAMA).* It is generally accepted that 96 3
the mean body temperature of an adult human is 96 79
98.6°F. In his article, Shoemaker uses the data from 97 0111234444
the JAMA article to test this hypothesis. Here is a 97 556667888899
summary of his test. 98 000000112222334444
Claim: The body temperature of adults is 98.6°F. 98 55666666778889
H0: m = 98.6°F (Claim) Ha: m ≠ 98.6°F 99 0001234
99 5
Sample Size: n = 130
100
Population: Adult human temperatures (Fahrenheit)
100 Key: 96 0 3 = 96.3
Distribution: Approximately normal
Test Statistics: x ≈ 98.25, s ≈ 0.73 Women’s Temperatures
* Data for the JAMA article were collected from
(in degrees Fahrenheit)
healthy men and women, ages 18 to 40, at the 96 4
University of Maryland Center for Vaccine 96 78
Development, Baltimore. 97 224
97 677888999
98 00000122222233344444
98 5666677777788888889
99 00112234
99 9
100 0
100 8 Key: 96 0 4 = 96.4
EXER CI SES
1. Complete the hypothesis test for all adults (men 2. If you lower the level of significance to
and women) by performing the following steps. a = 0.01, does your decision change? Explain
Use a level of significance of a = 0.05. your reasoning.
(a) Sketch the sampling distribution. 3. Test the hypothesis that the mean temperature
(b) Determine the critical values and add them of men is 98.6°F. What can you conclude at a
to your sketch. level of significance of a = 0.01?
(c) Determine the rejection regions and shade 4. Test the hypothesis that the mean temperature
them in your sketch. of women is 98.6°F. What can you conclude at a
(d) Find the standardized test statistic. Plot and level of significance of a = 0.01?
label it in your sketch. 5. Use the sample of 130 temperatures to form
(e) Make a decision to reject or fail to reject the a 99% confidence interval for the mean body
null hypothesis. temperature of adult humans.
(f) Interpret the decision in the context of the 6. The conventional “normal” body temperature
original claim. was established by Carl Wunderlich over
100 years ago. What were possible sources of
error in Wunderlich’s sampling procedure?
387
Case Study 387

7.4 Hypothesis Testing for Proportions

Hypothesis Test for Proportions
H
ow to use the z@test to test a
population proportion p Hypothesis Test for Proportions
In Sections 7.2 and 7.3, you learned how to perform a hypothesis test for a
population mean m. In this section, you will learn how to test a population
proportion p.
Hypothesis tests for proportions can be used when politicians want to know
the proportion of their constituents who favor a certain bill or when quality
assurance engineers test the proportion of parts that are defective.
If np Ú 5 and nq Ú 5 for a binomial distribution, then the sampling
distribution for p
n is approximately normal with a mean of m pn = p and a standard
error of
spn = 2pq n.
z-Test for a Proportion p

The z@test for a proportion p is a statistical test for a population proportion.
The z@test can be used when a binomial distribution is given such that np Ú 5
and nq Ú 5. The test statistic is the sample proportion pn and the standardized
test statistic is
pn - m pn pn - p
z = = . Standardized test statistic for p
spn 2pq n
GUIDELI N E S
Using a z@Test for a Proportion p
In Words In Symbols
1. Verify that the sampling distribution np Ú 5, nq Ú 5
of pn can be approximated by a
normal distribution.
Study Tip
A hypothesis test for a
proportion p can also be 4. Determine the critical value(s). Use Table 4 in Appendix B.
performed using P@values. 5. Determine the rejection region(s).
Use the guidelines on pn - p
6. Find the standardized test statistic z = .
page 365 for using P@values 2pq n
and sketch the sampling distribution.
for a z@test for a mean m,
but in Step 4 find the standardized 7. Make a decision to reject or fail to If z is in the rejection region,
test statistic by using the formula reject the null hypothesis. then reject H0. Otherwise,
fail to reject H0.
pn - p
z = . 8. Interpret the decision in the context
2pqn of the original claim.
The other steps in the test are the
same. In Step 7 of the guidelines, the decision rule uses rejection regions. You can
also test a claim using P-values, as shown in the Study Tip at the left.

S EC T IO N 7 . 4 Hypothesis Testing for Proportions 389
See TI-84 Plus

7.4
To explore this topic further, Hypothesis Test for a Proportion
see Activity 7.4 on page 393.
A researcher claims that less than 45% of U.S. adults use passwords that are
less secure because complicated ones are too hard to remember. In a random
sample of 100 adults, 41% say they use passwords that are less secure because
complicated ones are too hard to remember. At a = 0.01, is there enough
evidence to support the researcher’s claim? (Adapted from Pew Research Center)
SO LU TION
The products np = 10010.452 = 45 and nq = 10010.552 = 55 are both
greater than 5. So, you can use a z@test. The claim is “less than 45% of U.S.
adults use passwords that are less secure because complicated ones are too
hard to remember.” So, the null and alternative hypotheses are
H0: p Ú 0.45 and Ha: p 6 0.45. (Claim)
Because the test is a left-tailed test and the level of significance is a = 0.01,
the critical value is z0 = -2.33 and the rejection region is z 6 -2.33. The
standardized test statistic is
pn - p
z = Because np Ú 5 and n Ú 5, you can use the z-test.
2pq n
0.41 - 0.45
= Assume p = 0.45.
210.45210.552 100
The figure shows the location of the

rejection region and the standardized test
Study Tip statistic z. Because z is not in the rejection
region, you fail to reject the null hypothesis.
Remember that when
you fail to reject H0, a Interpretation There is not enough
type II error is possible. evidence at the 1% level of significance z
− 4 −3 −2 − 1 0 1 2 3 4
For instance, in Example 1 to support the claim that less than 45%
the null hypothesis, of U.S. adults use passwords that are less z 0 = −2.33 z ≈ −0.80
p Ú 0.45, may be false. secure because complicated ones are too 1% Level of Significance
hard to remember.
TRY IT YOU RS ELF 1
A researcher claims that more than 90% of U.S. adults have access to a
smartphone. In a random sample of 150 adults, 87% say they have access to a
smartphone. At a = 0.01, is there enough evidence to support the researcher’s
claim? (Adapted from Nielsen Mobile Insights)
Answer: Page A37
To use a P-value to perform the hypothesis

test in Example 1, you can use technology, as T I - 8 4 PLUS
shown at the right, or you can use Table 4. Using
Table 4, the area corresponding to z = -0.80 is
0.2119. Because this is a left-tailed test, the P-value
is equal to the area to the left of z = -0.80. So,
P = 0.2119. (This value differs from the one
found using technology due to rounding.) Because
the P-value is greater than a = 0.01, you fail to
reject the null hypothesis. Note that this is the
same result obtained in Example 1.

Recall from Section 6.3 that when the sample proportion is not given, you
Picturing
can find it using the formula
x
pn = Sample proportion
the World n
where x is the number of successes in the sample and n is the sample size.
According to a survey, at least
35% of smartphone owners say
the first thing they access on their See Minitab steps
EX AMP LE 2 on page 414.
phones each day is texts or instant
messages. To test this claim, you Hypothesis Test for a Proportion
randomly select 300 smartphone
owners. In the sample, you find A researcher claims that 51% of U.S. adults believe, incorrectly, that
that 93 of them say the first thing antibiotics are effective against viruses. In a random sample of 2202 adults,
they access on their phones 1161 say antibiotics are effective against viruses. At a = 0.10, is there enough
each day is texts or instant evidence to support the researcher’s claim? (Source: HealthDay/Harris Poll)
messages. (Adapted from Deloitte’s
2016 Global Mobile Consumer Survey: SO L UT ION
U.S. edition) The products np = 220210.512 ≈ 1123 and nq = 220210.492 ≈ 1079 are
both greater than 5. So, you can use a z@test. The claim is “51% of U.S. adults
At A = 0.05, is there enough believe, incorrectly, that antibiotics are effective against viruses.” So, the null
evidence to reject the claim? and alternative hypotheses are
H0: p = 0.51 (Claim) and Ha: p ≠ 0.51.
No, there is not enough evidence at the
5% level of significance to reject the Because the test is a two-tailed test and the level of significance is a = 0.10,
claim that at least 35% of smartphone the critical values are -z0 = -1.645 and z0 = 1.645. The rejection regions are
owners say the first thing they access z 6 -1.645 and z 7 1.645. Because the number of successes is x = 1161 and
on their phones each day is texts or n = 2202, the sample proportion is
instant messages.
x 1161
pn = = ≈ 0.527.
n 2202
The standardized test statistic is
pn - p Because np Ú 5 and nq Ú 5,
z =
2pq n you can use the z-test.
0.527 - 0.51
= Assume p = 0.51.
210.51210.492 2202
≈ 1.60. Round to two decimal places.
The figure shows the location of the

rejection regions and the standardized test
statistic z. Because z is not in the rejection − z 0 = −1.645
region, you fail to reject the null hypothesis. z 0 = 1.645
Interpretation There is not enough
z
evidence at the 10% level of significance −4 −3 −2 −1 0 1 2 3 4
to reject the claim that 51% of U.S. adults z ≈ 1.60
believe, incorrectly, that antibiotics are
effective against viruses.
A researcher claims that 67% of U.S. adults believe that doctors prescribing
antibiotics for viral infections for which antibiotics are not effective is
a significant cause of drug-resistant superbugs. (Superbugs are bacterial
infections that are resistant to many or all antibiotics.) In a random sample
of 1768 adults, 1150 say they believe that doctors prescribing antibiotics for
viral infections for which antibiotics are not effective is a significant cause of
drug-resistant superbugs. At a = 0.10, is there enough evidence to support the
researcher’s claim? (Source: HealthDay/Harris Poll) Answer: Page A37

1. If np Ú 5 and nq Ú 5, then the

normal distribution can be used. 1. Explain how to determine whether a normal distribution can be used to
2. Verify that np Ú 5 and nq Ú 5. approximate a binomial distribution.
State H0 and Ha. Specify
2. Explain how to test a population proportion p.
the level of significance a.
Determine the critical value(s) In Exercises 3 – 6, determine whether a normal sampling distribution can be used.
and rejection region(s). Find the
If it can be used, test the claim.
standardized test statistic. Make
a decision and interpret it in the 3. Claim: p 6 0.12; a = 0.01. Sample statistics: pn = 0.10, n = 40
4. Claim: p Ú 0.48; a = 0.08. Sample statistics: pn = 0.40, n = 90
3. Cannot use normal distribution.
4. Can use normal distribution. 5. Claim: p ≠ 0.15; a = 0.05. Sample statistics: pn = 0.12, n = 500
Reject H0. There is enough 6. Claim: p 7 0.70; a = 0.04. Sample statistics: pn = 0.64, n = 225
5. Can use normal distribution. Using and Interpreting Concepts
Fail to reject H0. There is not
enough evidence at the 5% level Hypothesis Testing Using Rejection Regions In Exercises 7 –12,
of significance to support the (a) identify the claim and state H0 and Ha, (b) find the critical value(s) and identify
claim. the rejection region(s), (c) find the standardized test statistic z, (d) decide whether
6. Can use normal distribution. to reject or fail to reject the null hypothesis, and (e) interpret the decision in the
Fail to reject H0. There is not context of the original claim.
enough evidence at the 4% level 7. Vaccination Requirement A medical researcher says that less than 80% of
of significance to support the U.S. adults think that healthy children should be required to be vaccinated.
claim.
In a random sample of 200 U.S. adults, 82% think that healthy children
7. (a) The claim is “less than 80% should be required to be vaccinated. At a = 0.05, is there enough evidence
of U.S. adults think that to support the researcher’s claim? (Adapted from Pew Research Center)
healthy children should be
required to be vaccinated.” 8. Internal Revenue Service Audits A research center claims that at least

H0: p Ú 0.80 27% of U.S. adults think that the IRS will audit their taxes. In a random
Ha: p 6 0.80 (claim) sample of 1000 U.S. adults in a recent year, 23% say they are concerned that
(b) z0 = -1.645 the IRS will audit their taxes. At a = 0.01, is there enough evidence to reject
Rejection region: z 6 - 1.645 the center’s claim? (Source: Rasmussen Reports)
(c) 0.707 (d) Fail to reject H0. 9. Student Employment An eduction researcher claims that at most 3% of
(e) There is not enough working college students are employed as teachers or teaching assistants.
evidence at the 5% level of In a random sample of 200 working college students, 4% are employed as
significance to support the teachers or teaching assistants. At a = 0.01, is there enough evidence to
medical researcher’s claim reject the researcher’s claim? (Adapted from Sallie Mae)
that less than 80% of U.S.
adults think that healthy 10. Working Students An education researcher claims that 57% of college
children should be required students work year-round. In a random sample of 300 college students, 171
to be vaccinated. say they work year-round. At a = 0.10, is there enough evidence to support
8. See Selected Answers, page A101. the researcher’s claim? (Adapted from Sallie Mae)
9. See Odd Answers, page A70. 11. Zika Virus A researcher claims that 85% percent of Americans think they
10. See Selected Answers, page A101. are unlikely to contract the Zika virus. In a random sample of 250 Americans,
11. See Odd Answers, page A70. 225 think they are unlikely to contract the Zika virus. At a = 0.05, is there
12. See Selected Answers, page A101. enough evidence to reject the researcher’s claim? (Adapted from Gallup)
12. Changing Jobs A research center claims that more than 29% of U.S.
employees have changed jobs in the past three years. In a random sample
of 180 U.S. employees, 63 have changed jobs in the past three years. At
a = 0.10, is there enough evidence to support the center’s claim? (Adapted
from Gallup)

13. (a) The claim is “27% of U.S. Hypothesis Testing Using a P-Value In Exercises 13–16, (a) identify
adults would travel into the claim and state H0 and Ha, (b) use technology to find the P-value, (c) decide
space on a commercial flight whether to reject or fail to reject the null hypothesis, and (d) interpret the decision
if they could afford it.” in the context of the original claim.

H0: p = 0.27 (claim)
Ha: p ≠ 0.27 13. Space Travel A research center claims that 27% of U.S. adults would
(b) 0.03 (c) Reject H0.
travel into space on a commercial flight if they could afford it. In a random
sample of 1000 U.S. adults, 30% say that they would travel into space on
(d) There is enough evidence at
a commercial flight if they could afford it. At a = 0.05, is there enough
to reject the research
evidence to reject the research center’s claim? (Source: Rasmussen Reports)
center’s claim that 27% of 14. Purchasing Food Online A research center claims that at most 18% of
U.S. adults would travel into U.S. adults’ online food purchases are for snacks. In a random sample of
space on a commercial flight 1995 U.S. adults, 20% say their online food purchases are for snacks. At
if they could afford it.
a = 0.10, is there enough evidence to support the center’s claim? (Source:
14. See Selected Answers, page A101. The Harris Poll)
15. Pet Ownership A humane society claims that less than 67% of U.S.
16. See Selected Answers, page A101. households own a pet. In a random sample of 600 U.S. households, 390
17. Fail to reject H0. There is not say they own a pet. At a = 0.10, is there enough evidence to support the
enough evidence at the 5% society’s claim? (Adapted from The Humane Society of the United States)
level of significance to reject
the claim that at least 63% of 16. Stray dogs A humane society claims that 5% of U.S. households have
adults make an effort to live taken in a stray dog. In a random sample of 200 U.S. households, 12 say they
in ways that help protect the have taken in a stray dog. At a = 0.05, is there enough evidence to reject the
environment some of the time. society’s claim? (Adapted from The Humane Society of the United States)
Protecting the Protecting the Environment In Exercises 17 and 18, use the figure at the
left, which suggests what adults think about protecting the environment. (Source:
Environment Pew Research Center)
How often adults say
they make an effort to 17. Are People Concerned About Protecting the Environment? You interview
live in ways that help
protect the environment: a random sample of 100 adults. The results of the survey show that 59% of the
Not too often adults said they live in ways that help protect the environment some of the
All of the time time. At a = 0.05, can you reject the claim that at least 63% of adults make
13%
20%
an effort to live in ways that help protect the environment some of the time?
Not at all
4% 18. What Are People’s Attitudes About Protecting the Environment? Use
your conclusion from Exercise 17 to write a paragraph on people’s attitudes
Some of the time
about protecting the environment.
63%
Extending Concepts
Alternative Formula In Exercises 19 and 20, use the information below.
FIGURE FOR EXERCISES 17 AND 18 When you know the number of successes x, the sample size n, and the population
proportion p, it can be easier to use the formula
18. Answers will vary.
x - np
19. See Odd Answers, page A71. z =
1npq
to find the standardized test statistic when using a z-test for a population
proportion p.
19. Rework Exercise 7 using the alternative formula and verify that the results
are the same.
20. The alternative formula is derived from the formula
pn - p ( xn ) - p
z = = .
2pq n 2pq n
Use this formula to derive the alternative formula. Justify each step.

7.4 Hypothesis Tests for a Proportion

ACTIVITY
The hypothesis tests for a proportion applet allows you to visually investigate
hypothesis tests for a population proportion. You can specify the sample size n, the
APPLET
population proportion (True p), the null value for the proportion (Null p), and the
You can find the interactive alternative for the test (Alternative). When you click SIMULATE, 100 separate
applet for this activity samples of size n will be selected from a population with a proportion of successes
within MyLab Statistics or at equal to True p. For each of the 100 samples, a hypothesis test based on the
www.pearsonhighered.com/ Z statistic is performed, and the results from each test are displayed in plots at the
mathstatsresources.
right. The standardized test statistic for each test is shown in the top plot and the
P@value is shown in the bottom plot. The green and blue lines represent the cutoffs
for rejecting the null hypothesis with the 0.05 and 0.01 level tests, respectively.
Additional simulations can be carried out by clicking SIMULATE multiple times.
The cumulative number of times that each test rejects the null hypothesis is also
shown. Press CLEAR to clear existing results and start a new simulation.
n: 50
True p: 0.5
Null p: 0.5
Alternative: <
Simulate
Cumulative results:
0.05 level 0.01 level

Reject null
Fail to reject null
Prop. rejected
Clear
EX PLOR E
Step 1 Specify a value for n.
Step 2 Specify a value for True p.
Step 3 Specify a value for Null p.
Step 4 Specify an alternative hypothesis.
Step 5 Click SIMULATE to generate the hypothesis tests.
DRAW C O N C LU S I O N S
1. Set n = 25 and True p = 0.35. Test the claim that the proportion is equal
to 35%. What are the null and alternative hypotheses? Run the simulation
APPLET
so that at least 1000 tests are run. Compare the proportion of null hypothesis
rejections for the 0.05 and 0.01 levels. Is this what you would expect? Explain.
2. Set n = 50 and True p = 0.6. Test the claim that the proportion is at least
40%. What are the null and alternative hypotheses? Run the simulation so
that at least 1000 tests are run. Compare the proportion of null hypothesis
rejections for the 0.05 and 0.01 levels. Perform a hypothesis test for each level.
Use the results of the hypothesis tests to explain the results of the simulation.
393

7.5 Hypothesis Testing for Variance and Standard Deviation

Critical Values for a Chi-Square Test The Chi-Square Test
H
ow to find critical values for a
chi-square test Critical Values for a Chi-Square Test
H
ow to use the chi-square In real life, it is important to produce consistent, predictable results. For instance,
test to test a variance s2 or a consider a company that manufactures golf balls. The manufacturer must produce
standard deviation s
millions of golf balls, each having the same size and the same weight. There is
a very low tolerance for variation. For a normally distributed population, you
can test the variance and standard deviation of the process using the chi-square
distribution with n - 1 degrees of freedom. Before learning how to do the test,
you must know how to find the critical values, as shown in the guidelines.
GUIDELI N E S
Finding Critical Values for a Chi-Square Test
1−α 1. Specify the level of significance a.
α 2. Identify the degrees of freedom, d.f. = n - 1.
χ2 3. The critical values for the chi-square distribution are found in Table 6
Critical in Appendix B. To find the critical value(s) for a
value χ 20
a. right-tailed test, use the value that corresponds to d.f. and a.
Right-Tailed Test b. left-tailed test, use the value that corresponds to d.f. and 1 - a.
c. two-tailed test, use the values that correspond to d.f. and 12a, and
d.f. and 1 - 12a.
See the figures at the left.
α 1−α
EX AMP LE 1
2
χ
Critical Finding a Critical Value for a Right-Tailed Test
value χ 2 0 Find the critical value x20 for a right-tailed test when n = 26 and a = 0.10.
Left-Tailed Test
SO L UT ION
The degrees of freedom are d.f. = n - 1 = 26 - 1 = 25. The figure below
shows a chi-square distribution with 25 degrees of freedom and a shaded area
of a = 0.10 in the right tail. Using Table 6 in Appendix B with d.f. = 25 and
1
α 1−α a = 0.10, the critical value is x20 = 34.382.
2
1
2
α
χ2
Critical Critical α = 0.10
value χ 2 L
value χ 2
R
χ2
Two-Tailed Test 5 10 15 20 25 30 35 40 45
χ 2 = 34.382
0
Note to Instructor
TRY IT YOU RS ELF 1
This section can be omitted or
covered later (with Chapter 10) Find the critical value x20 for a right-tailed test when n = 18 and a = 0.01.
without loss of continuity. Answer: Page A37

S EC T IO N 7 . 5 Hypothesis Testing for Variance and Standard Deviation 395
EX A M P L E 2

Find the critical value x20 for a left-tailed test when n = 11 and a = 0.01.
SO LU TION
d.f. = n - 1 = 11 - 1 = 10.
The figure at the left shows a chi-square distribution with 10 degrees of
freedom and a shaded area of a = 0.01 in the left tail. The area to the right of
the critical value is
1 - a = 1 - 0.01 = 0.99.
Using Table 6 with d.f. = 10 and the area 0.99, the critical value is x20 = 2.558.
α = 0.01 You can check your answer using technology, as shown below.
χ2
5 10 15 20
χ 2 = 2.558
MINITAB
0
Inverse Cumulative Distribution Function
Chi-Square with 10 DF
P ( X … x) x
0.01 2.55821
TRY IT YOU RS ELF 2

Find the critical value x20 for a left-tailed test when n = 30 and a = 0.05.
Answer: Page A37
Note that because chi-square distributions are not symmetric (like normal
or t-distributions), in a two-tailed test the two critical values are not opposites.
Each critical value must be calculated separately, as shown in the next example.
EX A M P L E 3

Find the critical values xL2 and xR2 for a two-tailed test when n = 9 and a = 0.05.
SO LU TION
d.f. = n - 1 = 9 - 1 = 8.
The figure shows a chi-square distribution
with 8 degrees of freedom and a shaded area
of 12a = 0.025 in each tail. The area to the
EXCEL right of xR2 is 12a = 0.025, and the area to the
1 1
α = 0.025 α = 0.025
A B right of xL2 is 1 - 12a = 0.975. Using Table 6 2 2
1 CHISQ.INV(0.025,8) with d.f. = 8 and the areas 0.025 and 0.975, χ2

2 2.179730747 the critical values are xR2 = 17.535 and 5 10 15 20
3 CHISQ.INV.RT(0.025,8) xL2 = 2.180. You can check you answer χ 2 = 2.180 χ 2 = 17.535
L R
4 17.53454614 using technology, as shown at the left.
TRY IT YOU RS ELF 3

Find the critical values xL2 and xR2 for a two-tailed test when n = 51 and
a = 0.01. Answer: Page A37

The Chi-Square Test

To test a variance s2 or a standard deviation s of a population that is normally
distributed, you can use the chi-square test. The chi-square test for a variance or
standard deviation is not as robust as the tests for the population mean m or the
population proportion p. So, it is essential in performing a chi-square test for a
variance or standard deviation that the population be normally distributed. The
results can be misleading when the population is not normal.
Chi-Square Test for a Variance S 2 or Standard Deviation S

The chi-square test for a variance S 2 or standard deviation S is a statistical
test for a population variance or standard deviation. The chi-square test can
only be used when the population is normal. The test statistic is s2 and the
standardized test statistic
1n - 12s2
x2 = Standardized test statistic for s2 or s
s2
follows a chi-square distribution with degrees of freedom
d.f. = n - 1.
Note to Instructor In Step 8 of the guidelines below, the decision rule uses rejection regions.
Review the properties of chi-square You can also test a claim using P-values (see Exercises 31-34).
distributions. Tell students that this
family of distributions will be used GUIDELI N E S
in later chapters, but the degrees
of freedom for those tests are not Using the Chi-Square Test for a Variance S 2 or a Standard Deviation S
necessarily n - 1.
In Words In Symbols
1. Verify that the sample is random
and the population is normally
distributed.
4. Identify the degrees of freedom. d.f. = n - 1
5. Determine the critical value(s). Use Table 6 in Appendix B.
1n - 12s2
7. Find the standardized test statistic x2 =
and sketch the sampling s2
distribution.
8. Make a decision to reject or fail to If x2 is in the rejection region,
reject the null hypothesis. then reject H0. Otherwise, fail
to reject H0.
9. Interpret the decision in the context
of the original claim.
For Step 5 of the guidelines, in addition to using Table 6 in Appendix B, you

can use technology to find the critical value(s). Also, some technology tools allow
you to perform a hypothesis test for a variance (or a standard deviation) using
only the descriptive statistics.

EX A M P L E 4
Using a Hypothesis Test for the Population Variance

A dairy processing company claims that the variance of the amount of fat in the
whole milk processed by the company is no more than 0.25. You suspect this
is wrong and find that a random sample of 41 milk containers has a variance
of 0.27. At a = 0.05, is there enough evidence to reject the company’s claim?
Assume the population is normally distributed.
SO LU TION
Because the sample is random and the population is normally distributed, you
can use the chi-square test. The claim is “the variance is no more than 0.25.”
So, the null and alternative hypotheses are
H0: s2 … 0.25 (Claim) and Ha: s2 7 0.25.
The test is a right-tailed test, the level of significance is a = 0.05, and the
degrees of freedom are d.f. = 41 - 1 = 40. So, using Table 6, the critical
value is
x20 = 55.758.
The rejection region is x2 7 55.758. The standardized test statistic is
1n - 12s2
x2 = Use the chi-square test.
s2
141 - 1210.272
= Assume s2 = 0.25.
0.25
= 43.2.
The figure at the left shows the location of the rejection region and the
standardized test statistic x2. Because x2 is not in the rejection region, you fail
to reject the null hypothesis. You can check your answer using technology, as
shown below. Note that the test statistic, 43.2, is the same as what you found
above.
α = 0.05
STATCRUNCH
χ2
10 20 30 40 50 60 70 One sample variance hypothesis test:
χ 2 = 43.2 χ 2 = 55.758 s2 : Variance of population
0
H0 : s2 = 0.25
HA : s2 7 0.25
Hypothesis test results:

Variance Sample Var. DF Chi-square Stat P-value
s2 0.27 40 43.2 0.3362

to reject the company’s claim that the variance of the amount of fat in the
whole milk is no more than 0.25.
T RY I T YOURSELF 4
A bottling company claims that the variance of the amount of sports drink in
a 12-ounce bottle is no more than 0.40. A random sample of 31 bottles has a
variance of 0.75. At a = 0.01, is there enough evidence to reject the company’s
claim? Assume the population is normally distributed.
Answer: Page A37

EX AMP LE 5
Using a Hypothesis Test for the Standard Deviation

A company claims that the standard deviation of the lengths of time it takes
an incoming telephone call to be transferred to the correct office is less than
1.4 minutes. A random sample of 25 incoming telephone calls has a standard
deviation of 1.1 minutes. At a = 0.10, is there enough evidence to support the
company’s claim? Assume the population is normally distributed.
SO L UT ION
Because the sample is random and the population is normally distributed, you
can use the chi-square test. The claim is “the standard deviation is less than
1.4 minutes.” So, the null and alternative hypotheses are
H0: s Ú 1.4 minutes and Ha: s 6 1.4 minutes. (Claim)
The test is a left-tailed test, the level of significance is a = 0.10, and the
degrees of freedom are
d.f. = 25 - 1 = 24.
So, using Table 6, the critical value is
x20 = 15.659.
The rejection region is x2 6 15.659. The standardized test statistic is
Study Tip 1n - 12s2
Although you are testing s2
a standard deviation
125 - 1211.12 2
in Example 5, the standardized = Assume s = 1.4.
test statistic x2 requires variance. 11.42 2
Remember to square the standard ≈ 14.816. Round to three decimal places.
deviation to calculate the variance.
The figure below shows the location of the rejection region and the standardized
test statistic x2. Because x2 is in the rejection region, you reject the null
hypothesis.
α = 0.10
χ2
5 10 20 25 30 35 40
χ 2 ≈ 14.816 χ 2 = 15.659
0

support the claim that the standard deviation of the lengths of time it takes an
incoming telephone call to be transferred to the correct office is less than 1.4
minutes.
A police chief claims that the standard deviation of the lengths of response times
is less than 3.7 minutes. A random sample of 9 response times has a standard
deviation of 3.0 minutes. At a = 0.05, is there enough evidence to support the
police chief’s claim? Assume the population is normally distributed.
Answer: Page A37

EX A M P L E 6
Picturing Using a Hypothesis Test for the Population Variance
the World A sporting goods manufacturer claims that the variance of the strengths
of a certain fishing line is 15.9. A random sample of 15 fishing line spools
A community center claims that
the chlorine level in its pool has
has a variance of 21.8. At a = 0.05, is there enough evidence to reject the
a standard deviation of 0.46 parts manufacturer’s claim? Assume the population is normally distributed.
per million (ppm). A sampling of
SO LU TION
the pool’s chlorine levels at 25
random times during a month Because the sample is random and the population is normally distributed, you
yields a standard deviation of can use the chi-square test. The claim is “the variance is 15.9.” So, the null and
0.61 ppm. (Adapted from American alternative hypotheses are
Pool Supply)
H0: s2 = 15.9 (Claim) and Ha: s2 ≠ 15.9.
f
The test is a two-tailed test, the level of significance is a = 0.05, and the
4 degrees of freedom are
Frequency
3 d.f. = 15 - 1
2 = 14.
1 Using Table 6, the critical values are xL2 = 5.629 and xR2 = 26.119. The rejection
x
regions are
1.0 1.4 1.8 2.2 2.6 3.0
x2 6 5.629 and x2 7 26.119.
Chlorine level (ppm)
The standardized test statistic is
At 0.05, is there enough evidence
to reject the claim? 1n - 12s2
s2
Yes, there is enough evidence at the 115 - 12121.82
= Assume s2 = 15.9.
5% level of significance to reject the 115.92
claim that the chlorine level in the pool ≈ 19.195. Round to three decimal places.
has a standard deviation of 0.46 parts
per million. The figure below shows the location of the rejection regions and the
standardized test statistic x2. Because x2 is not in the rejection regions, you fail
to reject the null hypothesis.
1
1
α = 0.025 α = 0.025
2 2
χ2
5 10 15 20 25 30
χ 2 = 5.629 χ 2 ≈ 19.195 χ 2 = 26.119
L R

to reject the claim that the variance of the strengths of the fishing line is 15.9.
TRY IT YOU RS ELF 6

A company that offers dieting products and weight loss services claims that
the variance of the weight losses of their users is 25.5. A random sample of
13 users has a variance of 10.8. At a = 0.10, is there enough evidence to reject
the company’s claim? Assume the population is normally distributed.
Answer: Page A37


2. See Selected Answers, page A101. 1. Explain how to find critical values in a chi-square distribution.
3. See Odd Answers, page A71. 2. Can a critical value for the chi-square test be negative? Explain.
4. See Selected Answers, page A101. 3. How do the requirements for a chi-square test for a variance or standard
5. Critical value: x20 = 38.885 deviation differ from a z@test or a t@test for a mean?
Rejection region: x2 7 38.885
6. Critical value: x20 = 14.684
4. Explain how to test a population variance or a population standard deviation.
Rejection region: x2 7 14.684
7. Critical value: x20 = 0.872 In Exercises 5–12, find the critical value(s) and rejection region(s) for the type of
Rejection region: x2 6 0.872 chi-square test with sample size n and level of significance a.
8. Critical value: x20 = 13.091 5. Right-tailed test, 6. Right-tailed test,
Rejection region: x2 6 13.091 n = 27, a = 0.05 n = 10, a = 0.10
9. Critical values: x2L = 60.391,
x2R = 101.879 7. Left-tailed test, 8. Left-tailed test,
Rejection regions: x2 6 60.391, n = 7, a = 0.01 n = 24, a = 0.05
x2 7 101.879 9. Two-tailed test, 10. Two-tailed test,
10. Critical values: x2L = 35.534, n = 81, a = 0.10 n = 61, a = 0.01
x2R = 91.952
Rejection regions: x2 6 35.534, 11. Right-tailed test, 12. Two-tailed test,
x2 7 91.952 n = 30, a = 0.01 n = 31, a = 0.05
Rejection region: x2 7 49.588 Graphical Analysis In Exercises 13 and 14, state whether each standardized
12. Critical values: x2L = 16.791, test statistic x2 allows you to reject the null hypothesis. Explain.
x2R = 46.979
Rejection regions: x2 6 16.791,
13. (a) x2 = 2.091 14. (a) x2 = 22.302
x2 7 46.979 (b) x2 = 0 (b) x2 = 23.309
13. (a) Fail to reject H0 because (c) x2 = 1.086 (c) x2 = 8.457
x2 6 6.251. (d) x2 = 6.3471 (d) x2 = 8.577

x2 6 6.251.
x2 6 6.251.
(d) Reject H0 because x2 7 6.251.
14. (a) Fail to reject H0 because
8.547 6 x2 6 22.307. χ2
χ2
(b) Reject H0 because 2 4 6 8 10 5 10 15 20 25 30
x2 7 22.307. χ 2 = 6.251 χ 2 = 8.547 χ 2 = 22.307
0 L R
(c) Reject H0 because x2 6 8.547.
In Exercises 15–22, test the claim about the population variance s2 or standard
(d) Fail to reject H0 because deviation s at the level of significance a. Assume the population is normally distributed.
8.547 6 x2 6 22.307.
15. See Odd Answers, page A71. 15. Claim: s2 = 0.52; a = 0.05. Sample statistics: s2 = 0.508, n = 18
16. See Selected Answers, page A101. 16. Claim: s2 Ú 8.5; a = 0.05. Sample statistics: s2 = 7.45, n = 23
17. See Odd Answers, page A71. 17. Claim: s2 … 17.6; a = 0.01. Sample statistics: s2 = 28.33, n = 41
18. Claim: s2 7 19; a = 0.1. Sample statistics: s2 = 28, n = 17
20. See Selected Answers, page A101. 19. Claim: s2 ≠ 32.8; a = 0.1. Sample statistics: s2 = 40.9, n = 101
21. See Odd Answers, page A71. 20. Claim: s2 = 63; a = 0.01. Sample statistics: s2 = 58, n = 29
21. Claim: s 6 40; a = 0.01. Sample statistics: s = 40.8, n = 12
significance to reject the claim. 22. Claim: s = 24.9; a = 0.10. Sample statistics: s = 29.1, n = 51

23. See Odd Answers, page A71. Using and Interpreting Concepts
Hypothesis Testing Using Rejection Regions In Exercises 23–30,
(a) identify the claim and state H0 and Ha, (b) find the critical value(s) and identify
26. See Selected Answers, page A102. the rejection region(s), (c) find the standardized test statistic x2, (d) decide whether
27. See Odd Answers, page A71. to reject or fail to reject the null hypothesis, and (e) interpret the decision in the
28. See Selected Answers, page A102. context of the original claim. Assume the population is normally distributed.
29. See Odd Answers, page A71. 23. Tires A tire manufacturer claims that the variance of the diameters in a tire
30. See Selected Answers, page A102. model is 8.6. A random sample of 10 tires has a variance of 4.3. At a = 0.01,
31. P-value = 0.4524 is there enough evidence to reject the claim?
Fail to reject H0.
24. Gas Mileage An auto manufacturer claims that the variance of the gas
32. P-value = 0.4014
mileages in a model of hybrid vehicle is 0.16. A random sample of 30 vehicles
Fail to reject H0.
has a variance of 0.26. At a = 0.05, is there enough evidence to reject the
33. P-value = 0.0033 claim? (Adapted from Green Hybrid)
Reject H0.
34. P-value = 0.0060 25.
Mathematics Assessment Tests A school administrator claims that the
Reject H0. standard deviation for grade 12 students on a mathematics assessment test
is less than 35 points. A random sample of 28 grade 12 test scores has a
standard deviation of 34 points. At a = 0.10, is there enough evidence to
support the claim? (Adapted from National Center for Educational Statistics)
26.
Vocabulary Assessment Tests A school administrator claims that the
standard deviation for grade 12 students on a vocabulary assessment test
is greater than 45 points. A random sample of 25 grade 12 test scores has
a standard deviation of 46 points. At a = 0.01, is there enough evidence to
support the claim? (Adapted from National Center for Educational Statistics)
Annual salaries
27. Waiting Times A hospital claims that the standard deviation of the waiting
times for patients in its emergency department is no more than 0.5 minute.
47,262 67,363 81,246 A random sample of 25 waiting times has a standard deviation of 0.7 minute.
65,876 59,649 78,268 At a = 0.10, is there enough evidence to reject the claim?
88,549 52,130 73,955
91,288 54,476 86,787 28. Hotel Room Rates A travel analyst claims that the standard deviation of
66,923 48,337 70,172 the room rates for two adults at three-star hotels in Denver is at least $68.
A random sample of 18 three-star hotels has a standard deviation of $40. At
TABLE FOR EXERCISE 29 a = 0.01, is there enough evidence to reject the claim? (Adapted from Expedia)
29. Salaries The annual salaries (in dollars) of 15 randomly chosen senior level
Annual salaries graphic design specialists are shown in the table at the left. At a = 0.05, is
there enough evidence to support the claim that the standard deviation of
59,922 99,493 98,221 the annual salaries is different from $10,300? (Adapted from Salary.com)
90,143 65,106 78,975
74,644 107,817 85,492 30. Salaries The annual salaries (in dollars) of 12 randomly chosen nursing
87,179 90,505 71,090 supervisors are shown in the table at the left. At a = 0.10, is there enough
evidence to reject the claim that the standard deviation of the annual salaries
TABLE FOR EXERCISE 30 is $16,500? (Adapted from Salary.com)
Extending Concepts
P-Values You can calculate the P-value for a chi-square test using technology.
T I - 8 4 PLUS
After calculating the standardized test statistic, use the cumulative distribution
function (CDF) to calculate the area under the curve. From Example 4 on page 397,
x2 = 43.2. Using a TI-84 Plus (choose 8 from the DISTR menu), enter 0 for
the lower bound, 43.2 for the upper bound, and 40 for the degrees of freedom,
as shown at the left. Because it is a right-tailed test, the P-value is approximately
1 - 0.6638 = 0.3362. Because P 7 a = 0.05, fail to reject H0. In Exercises 31 –34,
use the P-value method to perform the hypothesis test for the indicated exercise.
31. Exercise 25 32. Exercise 26 33. Exercise 27 34. Exercise 28

7 A Summary of Hypothesis Testing

With hypothesis testing, perhaps more than any other area of statistics, it can be
difficult to see the forest for all the trees. To help you see the forest—the overall
picture—a summary of what you studied in this chapter is provided.
Writing the Hypotheses
■ You are given a claim about a population parameter m, p, s2, or s.
■ Rewrite the claim and its complement using … , Ú , = and 7 , 6 , ≠.

H0 Ha
■ Identify the claim. Is it H0 or Ha?
Specifying a Level of Significance
■ Specify a, the maximum acceptable probability of rejecting a valid H0
(a type I error).
Specifying the Sample Size
Study Tip ■ Specify your sample size n.
Large sample sizes
Choosing the Test ▲ Normally distributed population ● Any population
will usually increase
the cost and effort of testing a ■ Mean: H0 describes a hypothesized population mean m.
hypothesis, but they also tend to ▲ Use a z@test when s is known and the population is normal.
make your decision more reliable.
● Use a z@test for any population when s is known and n Ú 30.
▲ Use a t@test when s is not known and the population is normal.
● Use a t@test for any population when s is not known and n Ú 30.
■ Proportion: H0 describes a hypothesized population proportion p.
Use a z@test for any population when np Ú 5 and nq Ú 5.
●
■ Variance or Standard Deviation: H0 describes a hypothesized population

variance s2 or standard deviation s.
▲ Use a chi-square test when the population is normal.
Sketching the Sampling Distribution

■ Use Ha to decide whether the test is left-tailed, right-tailed, or two-tailed.
Finding the Standardized Test Statistic

■ Take a random sample of size n from the population.
n , or s2.
■ Compute the test statistic x, p
■ Find the standardized test statistic z, t, or x2.

Making a Decision
Option 1. Decision based on rejection region
■ Use a to find the critical value(s) z0, t 0, or x2 and rejection region(s).
0
Decision
■ Rule:
Reject H0 when the standardized test statistic is in the rejection region.
Fail to reject H0 when the standardized test statistic is not in the rejection region.
Option 2. Decision based on P@value
■ Use the standardized test statistic or technology to find the P@value.
■ Decision Rule:
Reject H0 when P … a.
Fail to reject H0 when P 7 a.

A Summary of Hypothesis Testing 403
z@Test for a Hypothesized Mean M (S Known) (Section 7.2)

Test statistic: x Standardized test statistic: z
Critical value: z0 (Use Table 4.) Sample mean Hypothesized
Sampling distribution of x - m mean
sample means is a normal z =
s 1n
distribution.
Population Sample size
standard deviation

1 1
α 2
α 2
α α
z z z
z0 0 −z 0 0 z0 0 z0
Left-Tailed Two-Tailed Right-Tailed
z@Test for a Hypothesized Proportion p (Section 7.4)

Test statistic: pn Standardized test statistic: z
Study Tip Critical value: z0 (Use Table 4.) Sample Hypothesized
Sampling distribution of sample proportion pn - p proportion
When your standardized test z =
proportions is a normal distribution.
statistic is z or t, remember 2pqn
that these values measure
q = 1 - p Sample size
standard deviations from
the mean. Values that are
outside of {3 indicate that
H0 is very unlikely. Values that are t@Test for a Hypothesized Mean M (S Unknown) (Section 7.3)
outside of {5 indicate that H0 is
almost impossible. Test statistic: x Standardized test statistic: t
Critical value: t0 (Use Table 5.) Sample mean Hypothesized
Sampling distribution of sample means x - m mean
is approximated by a t@distribution t =
s 1n
with d.f. = n - 1.
Sample Sample size
standard deviation

1 1
α 2
α 2
α α
t t t
t0 0 −t0 0 t0 0 t0
Chi-Square Test for a Hypothesized Variance S 2 or Standard Deviation S

(Section 7.5)
Test statistic: s2 Standardized test statistic: x2
2
Critical value: x0 (Use Table 6.) Sample size Sample
Sampling distribution is approximated 1n - 12s 2 variance
by a chi-square distribution with x2 = 2
s
d.f. = n - 1. Hypothesized
variance

1
α α 1
2
2
α α
χ2 χ2 χ2
χ2 χ2 χ2 χ2
0 L R 0

USES AND Statistics in the Real World

ABUSES
Uses
Hypothesis testing is important in many different fields because it gives a
scientific procedure for assessing the validity of a claim about a population. Some
of the concepts in hypothesis testing are intuitive, but some are not. For instance,
the American Journal of Clinical Nutrition suggests that eating dark chocolate
can help prevent heart disease. A random sample of healthy volunteers were
assigned to eat 3.5 ounces of dark chocolate each day for 15 days. After 15 days,
the mean systolic blood pressure of the volunteers was 6.4 millimeters of mercury
lower. A hypothesis test could show whether this drop in systolic blood pressure
is significant or simply due to sampling error.
Careful inferences must be made concerning the results. The study only
examined the effects of dark chocolate, so the inference of health benefits cannot
be extended to all types of chocolate. You also would not infer that you should
eat large quantities of chocolate because the benefits must be weighed against
known risks, such as weight gain and acid reflux.
Abuses
Not Using a Random Sample The entire theory of hypothesis testing is based
on the fact that the sample is randomly selected. If the sample is not random,
then you cannot use it to infer anything about a population parameter.
Attempting to Prove the Null Hypothesis When the P@value for a hypothesis
test is greater than the level of significance, you have not proven the null
hypothesis is true—only that there is not enough evidence to reject it. For
instance, with a P@value higher than the level of significance, a researcher could
not prove that there is no benefit to eating dark chocolate—only that there is not
enough evidence to support the claim that there is a benefit.
Making Type I or Type II Errors Remember that a type I error is rejecting a
null hypothesis that is true and a type II error is failing to reject a null hypothesis
that is false. You can decrease the probability of a type I error by lowering the level
of significance a. Generally, when you decrease the probability of making a type I
error, you increase the probability b of making a type II error. Which error is more
serious? It depends on the situation. In a criminal trial, a type I error is considered
worse, as explained on page 352. If you are testing a person for a disease and they
are assumed to be disease-free 1H0 2, then a type II error is more serious because
you would fail to detect the disease even though the person has it. You can
decrease the chance of making both types of errors by increasing the sample size.
Do You Consider the Amount of
Federal Income Tax You Pay as Too
EX E R C I S E S
High, About Right, or Too Low?
Too low
In Exercises 1– 3, assume that you work for the Internal Revenue Service.
6% You are asked to write a report about the claim that 57% of U.S. adults
About right
37%
think the amount of federal income tax they pay is too high. (Source: Gallup)
1. What is the null hypothesis in this situation? Describe how your
report could be incorrect by trying to prove the null hypothesis.
Too high
57% 2. Describe how your report could make a type I error.
3. Describe how your report could make a type II error.

Chapter Summary 405
7 Chapter Summary
Review
What Did You Learn? Example(s) Exercises
Section 7.1
How to state a null hypothesis and an alternative hypothesis 1 1– 6
How to identify type I and type II errors 2 7–10
How to know whether to use a one-tailed or a two-tailed statistical test and 3 7–10
find a P@value
How to interpret a decision based on the results of a statistical test 4 7–10
How to write a claim for a hypothesis test 5 7–10
Section 7.2
How to find and interpret P@values 1–3 11, 12
How to use P@values for a z@test for a mean m when s is known 4 – 6 25, 26
How to find critical values and rejection regions in the standard normal 7, 8 13–16
distribution
How to use rejection regions for a z@test for a mean m when s is known 9, 10 17–24, 27, 28
Section 7.3
How to find critical values in a t@distribution 1–3 29–34
How to use the t@test to test a mean m when s is not known 4, 5 35–42
How to use technology to find P@values and use them with a t@test to test a 6 43, 44
mean m when s is not known
Section 7.4
How to use the z@test to test a population proportion p 1, 2 45– 50
Section 7.5
How to find critical values for a chi-square test 1–3 51–54
4 – 6 55–62
How to use the chi-square test to test a variance s2 or a standard deviation s

7 Review Exercises
1. H0: m … 375 (claim); Ha: m 7 375 Section 7.1
2. H0: m = 82 (claim); Ha: m ≠ 82
In Exercises 1– 6, the statement represents a claim. Write its complement and state
3. H0: p Ú 0.205 which is H0 and which is Ha.
Ha: p 6 0.205 (claim)
4. H0: m = 150,020 1. m … 375 2. p 6 0.205
m = 82 3.
Ha: m ≠ 150,020 (claim) 4. m ≠ 150,020 5. s 7 1.9 6. p Ú 0.64
5. H0: s … 1.9; Ha: s 7 1.9 (claim)
In Exercises 7–10, (a) state the null and alternative hypotheses and identify which
6. H0: p Ú 0.64 (claim); Ha: p 6 0.64
represents the claim, (b) describe type I and type II errors for a hypothesis test of the
7. See Odd Answers, page A72. claim, (c) explain whether the hypothesis test is left-tailed, right-tailed, or two-tailed,
8. See Selected Answers, page A102. (d) explain how you should interpret a decision that rejects the null hypothesis, and
9. See Odd Answers, page A72. (e) explain how you should interpret a decision that fails to reject the null hypothesis.
10. See Selected Answers, page A102. 7. A polling organization reports that the proportion of U.S. adults who have
11. 0.1736; Fail to reject H0. volunteered their time or donated money to help clean up the environment
12. 0.0102; Reject H0. is 65%. (Source: Rasmussen Reports)
13. See Odd Answers, page A72. 8. An agricultural cooperative guarantees that the mean shelf life of a type of
14. See Selected Answers, page A102. dried fruit is at least 400 days.
15. See Odd Answers, page A72. 9. A nonprofit consumer organization says that the standard deviation of the
16. See Selected Answers, page A102. fuel economies of its top-rated vehicles for a recent year is no more than
17. Fail to reject H0 because 9.5 miles per gallon. (Adapted from Consumer Reports)
-1.645 6 z 6 1.645. 10. An energy bar maker claims that the mean number of grams of carbohydrates
18. Reject H0 because z 7 1.645. in one bar is less than 25.
19. Fail to reject H0 because
-1.645 6 z 6 1.645. Section 7.2
20. Reject H0 because z 6 - 1.645.
21. Fail to reject H0. There is not In Exercises 11 and 12, find the P-value for the hypothesis test with the standardized
enough evidence at the 5% test statistic z. Decide whether to reject H0 for the level of significance a.
level of significance to reject the 11. Left-tailed test, z = -0.94, a = 0.05
claim.
12. Two-tailed test, z = 2.57, a = 0.10
In Exercises 13 –16, find the critical value(s) and rejection region(s) for the type of
z-test with level of significance a. Include a graph with your answer.
13. Left-tailed test, a = 0.02 14. Two-tailed test, a = 0.005
15. Right-tailed test, a = 0.025 16. Two-tailed test, a = 0.03
z
−3 −2 −1 0 1 2 3
In Exercises 17 –20, state whether the standardized test statistic z allows you to
− z0 = − 1.645 z0 = 1.645 reject the null hypothesis. Explain your reasoning.
FIGURE FOR EXERCISES 17–20 17. z = 1.631 18.
z = 1.723 19. z = -1.464 20. z = -1.655
In Exercises 21 –24, test the claim about the population mean m at the level of
significance a. Assume the population is normally distributed.
significance to support the 21. Claim: m … 45; a = 0.05; s = 6.7. Sample statistics: x = 47.2, n = 22
claim.
22. Claim: m ≠ 8.45; a = 0.03; s = 1.75. Sample statistics: x = 7.88, n = 60
enough evidence at the 1% level 23. Claim: m 6 5.500; a = 0.01; s = 0.011. Sample statistics: x = 5.497, n = 36
of significance to support the 24. Claim: m = 7450; a = 0.10; s = 243. Sample statistics: x = 7495, n = 27
claim.

Review Exercises 407
25. (a) The claim is “the mean In Exercises 25 and 26, (a) identify the claim and state H0 and Ha, (b) find the
annual production of cotton standardized test statistic z, (c) find the corresponding P-value, (d) decide whether
is 3.5 million bales per to reject or fail to reject the null hypothesis, and (e) interpret the decision in the
country.” context of the original claim.

H0: m = 3.5 (claim)
Ha: m ≠ 3.5 25. Cotton Production A researcher claims that the mean annual production
of cotton is 3.5 million bales per country. A random sample of 44 countries
(b)
- 2.06 (c) 0.0394
has a mean annual production of 2.1 million bales. Assume the population
(d) Reject H0.
standard deviation is 4.5 million bales. At a = 0.05, can you reject the
(e) There is enough evidence at claim? (Source: U.S. Department of Agriculture)
to reject the researcher’s 26. Cotton Consumption A researcher claims that the mean annual consumption
claim that the mean annual of cotton is greater than 1.1 million bales per country. A random sample of
production of cotton is 67 countries has a mean annual consumption of 1.0 million bales. Assume
3.5 million bales per country. the population standard deviation is 4.3 million bales. At a = 0.01, can you
26. See Selected Answers, page A102. support the claim? (Source: U.S. Department of Agriculture)
27. See Odd Answers, page A72. In Exercises 27 and 28, (a) identify the claim and state H0 and Ha, (b) find the
28. See Selected Answers, page A102. critical value(s) and identify the rejection region(s), (c) find the standardized test
29. Critical values: - t0 = - 2.093, statistic z, (d) decide whether to reject or fail to reject the null hypothesis, and
t0 = 2.093 (e) interpret the decision in the context of the original claim.
t 7 2.093 27. An environmental researcher claims that the mean amount of sulfur dioxide
in the air in U.S. cities is 1.15 parts per billion. In a random sample of
134 U.S. cities, the mean amount of sulfur dioxide in the air is 0.93 parts per
billion. Assume the population standard deviation is 2.62 parts per billion.
At a = 0.01, is there enough evidence to reject the claim? (Source: U.S.
Environmental Protection Agency)
Rejection region: t 6 -1.678 28. A travel analyst claims that the mean price of a round trip flight from New
York City to Los Angeles is less than $507. In a random sample of 55 round
Rejection region: t 6 -2.977 trip flights from New York City to Los Angeles, the mean price is $502.
Assume the population standard deviation is $111. At a = 0.05, is there
34. Critical values: - t0 = - 2.718,
enough evidence to support the travel analyst’s claim? (Adapted from Expedia)
t0 = 2.718
t 7 2.718 Section 7.3
evidence at the 0.5% level of In Exercises 29 –34, find the critical value(s) and rejection region(s) for the type of
significance to support the t-test with level of significance a and sample size n.
claim. 29. Two-tailed test, a = 0.05, n = 20
30. Right-tailed test, a = 0.01, n = 33
enough evidence at the 10%
level of significance to reject the 31. Right-tailed test, a = 0.02, n = 63
claim.
32. Left-tailed test, a = 0.05, n = 48
evidence at the 1% level of 33. Left-tailed test, a = 0.005, n = 15
significance to reject the claim. 34. Two-tailed test, a = 0.02, n = 12
In Exercises 35 –40, test the claim about the population mean m at the level of
enough evidence at the 2.5%
level of significance to support significance a. Assume the population is normally distributed.
the claim. 35. Claim: m 7 12,700; a = 0.005.
39. Fail to reject H0. There is not Sample statistics: x = 12,855, s = 248, n = 21
enough evidence at the 10%
36. Claim: m Ú 0; a = 0.10. Sample statistics: x = -0.45, s = 2.38, n = 31
claim. 37. Claim: m … 51; a = 0.01. Sample statistics: x = 52, s = 2.5, n = 40
40. Reject H0. There is enough 38. Claim: m 6 850; a = 0.025. Sample statistics: x = 875, s = 25, n = 14
significance to support the 39. Claim: m = 195; a = 0.10. Sample statistics: x = 190, s = 36, n = 101
claim. 40. Claim: m ≠ 3,330,000; a = 0.05.
Sample statistics: x = 3,293,995, s = 12,801, n = 35

41. (a) The claim is “the mean In Exercises 41 and 42, (a) identify the claim and state H0 and Ha, (b) find the
monthly cost of joining a critical value(s) and identify the rejection region(s), (c) find the standardized test
health club is $25.” statistic t, (d) decide whether to reject or fail to reject the null hypothesis, and

H0: m = 25 (claim) (e) interpret the decision in the context of the original claim. Assume the population
Ha: m ≠ 25 is normally distributed.
(b) - t0 = -1.740, t0 = 1.740
41. A fitness magazine advertises that the mean monthly cost of joining a health
Rejection regions:
t 6 -1.740, t 7 1.740 club is $25. You want to test this claim. You find that a random sample of
18 clubs has a mean monthly cost of $26.25 and a standard deviation of $3.23.
At a = 0.10, do you have enough evidence to reject the advertisement’s
(e) There is not enough claim?
evidence at the 10% level
of significance to reject the 42. A fitness magazine claims that the mean cost of a yoga session is no more
advertisement’s claim that than $14. You want to test this claim. You find that a random sample of
the mean monthly cost of 32 yoga sessions has a mean cost of $15.59 and a standard deviation of
joining a health club is $25. $2.60. At a = 0.025, do you have enough evidence to reject the magazine’s
42. (a) The claim is “the mean cost claim?
of a yoga session is no more
than $14.” In Exercises 43 and 44, (a) identify the claim and state H0 and Ha, (b) use
technology to find the P-value, (c) decide whether to reject or fail to reject the

H0: m … 14 (claim)
null hypothesis, and (d) interpret the decision in the context of the original claim.
Ha: m 7 14
Assume the population is normally distributed.
(b) t0 = 2.040
Rejection region: t 7 2.040 43. An education publication claims that the mean score for grade 12
(c) 3.46 (d) Reject H0. students on a science achievement test is more than 145. You want
(e) There is enough evidence at to test this claim. You randomly select 36 grade 12 test scores. The
the 2.5% level of significance results are listed below. At a = 0.1, can you support the publication’s
to reject the fitness claim? (Adapted from National Center for Education Statistics)
magazine’s claim that the 188 80 175 195 201 143 119 81 118 119 165 222
mean cost of a yoga session 109 134 200 110 199 181 79 135 124 205 90 120
is no more than $14.
216 167 198 183 173 187 143 166 147 219 206 97
43. (a) The claim is “the mean score
for grade 12 students on a 44.
An education researcher claims that the overall average score of
science achievement test is 15-year-old students on an international mathematics literacy test is
more than 145.” 494. You want to test this claim. You randomly select the average

H0: m … 145 scores of 33 countries. The results are listed below. At a = 0.05, do you
Ha: m 7 145 (claim) have enough evidence to reject the researcher’s claim? (Source: National
(b) 0.0824 (c) Reject H0. Center for Education Statistics)
(d) There is enough evidence at 561 554 536 531 523 518 515 511 506 500 499
the 10% level of significance 493 490 489 485 482 482 479 477 466 453 448
to support the education 439 432 423 421 413 407 394 388 386 376 368
publication’s claim that
the mean score for grade
12 students on a science Section 7.4
achievement test is more
than 145. In Exercises 45– 48, determine whether a normal sampling distribution can be used
to approximate the binomial distribution. If it can, test the claim.
45. See Odd Answers, page A72. 45. Claim: p = 0.15; a = 0.05
46. Can use normal distribution. Sample statistics: pn = 0.09, n = 40
Reject H0. There is enough 46. Claim: p = 0.65; a = 0.03
evidence at the 3% level of Sample statistics: pn = 0.76, n = 116
47. Claim: p 6 0.70; a = 0.01
47. Can use normal distribution.
Sample statistics: pn = 0.50, n = 68
Reject H0. There is enough
evidence at the 1% level of 48. Claim: p Ú 0.04; a = 0.10
significance to support the Sample statistics: pn = 0.03, n = 30
claim.
48. Cannot use normal distribution.

Review Exercises 409
49. (a) The claim is “over 40% of In Exercises 49 and 50, (a) identify the claim and state H0 and Ha, (b) find the
U.S. adults say they are less critical value(s) and identify the rejection region(s), (c) find the standardized test
likely to travel to Europe in statistic z, (d) decide whether to reject or fail to reject the null hypothesis, and
the next six months for fear (e) interpret the decision in the context of the original claim.
of terrorist attacks.”

H0: p … 0.40 49. A polling agency reports that over 40% of U.S. adults say they are less likely
Ha: p 7 0.40 (claim) to travel to Europe in the next six months for fear of terrorist attacks. In a
(b) z0 = 2.33 random sample of 1000 U.S. adults, 42% said they are less likely to travel
Rejection region: z 7 2.33 to Europe in the next six months for fear of terrorist attacks. At a = 0.01,
is there enough evidence to support the agency’s claim? (Adapted from
Rasmussen Reports)
evidence at the 1% level of 50. A labor researcher claims that 6% of U.S. employees say it is likely they
significance to support the will be laid off in the next year. In a random sample of 547 U.S. employees,
polling agency’s claim that 44 said it is likely they will be laid off in the next year. At a = 0.05, is there
over 40% of U.S. adults say enough evidence to reject the researcher’s claim? (Adapted from Gallup)
they are less likely to travel
to Europe in the next six
months for fear of terrorist Section 7.5
attacks.
In Exercises 51–54, find the critical value(s) and rejection region(s) for the type of
50. See Selected Answers, page A103. chi-square test with sample size n and level of significance a.
Rejection region: x2 7 30.144 51. Right-tailed test, n = 20, a = 0.05
52. Critical values:x2L= 3.565, 52. Two-tailed test, n = 14, a = 0.01
x2R = 29.819 53. Two-tailed test, n = 41, a = 0.10
x2 7 29.819 54. Left-tailed test, n = 6, a = 0.05
53. Critical values:x2L= 26.509, In Exercises 55–58, test the claim about the population variance s2 or standard
x2R = 55.758 deviation s at the level of significance a. Assume the population is normally
distributed.
x2 7 55.758
54. Critical value: x20 = 1.145 55. Claim: s2 7 2; a = 0.10. Sample statistics: s2 = 2.95, n = 18
Rejection region: x2 6 1.145 56. Claim: s2 … 60; a = 0.025. Sample statistics: s2 = 72.7, n = 15
57. Claim: s = 1.25; a = 0.05. Sample statistics: s = 1.03, n = 6
significance to support the 58. Claim: s ≠ 0.035; a = 0.01. Sample statistics: s = 0.026, n = 16
claim.
In Exercises 59 and 60, (a) identify the claim and state H0 and Ha, (b) find the
critical value(s) and identify the rejection region(s), (c) find the standardized test
enough evidence at the 2.5%
statistic x2, (d) decide whether to reject or fail to reject the null hypothesis, and
claim. (e) interpret the decision in the context of the original claim. Assume the population
is normally distributed.
enough evidence at the 5% 59. A bolt manufacturer makes a type of bolt to be used in airtight containers.
level of significance to reject the The manufacturer claims that the variance of the bolt widths is at most 0.01.
claim. A random sample of 28 bolts has a variance of 0.064. At a = 0.005, is there
58. Fail to reject H0. There is not enough evidence to reject the claim?
enough evidence at the 1% level
60. A restaurant claims that the standard deviation of the lengths of serving
of significance to support the
claim. times is 3 minutes. A random sample of 27 serving times has a standard
deviation of 3.9 minutes. At a = 0.01, is there enough evidence to reject the
claim?
61. In Exercise 59, is there enough evidence to reject the claim at the a = 0.01
61. You can reject H0 at the 1%
level? Explain.
level of significance because
x2 = 172.8 7 46.963 62. In Exercise 60, is there enough evidence to reject the claim at the a = 0.05
62. You can reject H0 at the 5% level? Explain.
level of significance because
x2 = 43.94 7 41.923.

7 Chapter Quiz
1. (a) The claim is “the mean hat Take this quiz as you would take a quiz in class. After you are done, check your
size for a male is at least work against the answers given in the back of the book.
7.25.” For each exercise, perform the steps below.
H0: m Ú 7.25 (claim)

Ha: m 6 7.25 (a) Identify the claim and state H0 and Ha.
(b) Left-tailed because the (b) Determine whether the hypothesis test is left-tailed, right-tailed, or two-tailed,
alternative hypothesis and whether to use a z-test, a t-test, or a chi-square test. Explain your reasoning.
contains 6; z-test because s (c) Choose one of the options.
is known and the population
is normally distributed. Option 1: Find the critical value(s), identify the rejection region(s), and find
the appropriate standardized test statistic.
(c) Sample answer: z0 = - 2.33;
Rejection region: z 6 - 2.33; Option 2: Find the appropriate standardized test statistic and the P-value.
- 1.28 (d) Decide whether to reject or fail to reject the null hypothesis.
(d) Fail to reject H0. (e) Interpret the decision in the context of the original claim.
evidence at the 1% level of 1. A hat company claims that the mean hat size for a male is at least 7.25.
significance to reject the A random sample of 12 hat sizes has a mean of 7.15. At a = 0.01, can you
company’s claim that the reject the company’s claim? Assume the population is normally distributed
mean hat size for a male is and the population standard deviation is 0.27.
at least 7.25. 2. A travel analyst claims the mean daily base price for renting a full-size or less
2. (a) The claim is “the mean expensive vehicle in Vancouver, Washington, is more than $36. You want to
daily base price for renting test this claim. In a random sample of 40 full-size or less expensive vehicles
a full-size or less expensive available to rent in Vancouver, Washington, the mean daily base price is $42.
vehicle in Vancouver,
Assume the population standard deviation is $19. At a = 0.10, do you have
Washington, is more than
enough evidence to support the analyst’s claim? (Adapted from Expedia)
$36.”
H0: m … 36
3. A government agency reports that the mean amount of earnings for full-time
Ha: m 7 36 (claim) workers ages 18 to 24 with a bachelor’s degree in a recent year is $47,254.
(b) Right-tailed because the In a random sample of 15 full-time workers ages 18 to 24 with a bachelor’s
alternative hypothesis degree, the mean amount of earnings is $50,781 and the standard deviation is
contains 7; z-test because s $5290. At a = 0.05, is there enough evidence to support the claim? Assume
is known and n Ú 30. the population is normally distributed. (Adapted from U.S. Census Bureau)
(c) Sample answer: z0 = 1.28; 4. A weight loss program claims that program participants have a mean
Rejection region: z 7 1.28; weight loss of at least 10.5 pounds after 1 month. The weight losses after
1.997 1 month (in pounds) of a random sample of 40 program participants
(d) Reject H0. are listed below. At a = 0.01, is there enough evidence to reject the
(e) There is enough evidence at program’s claim?
the 10% level of significance 4.7 6.0 7.2 8.3 9.2 10.1 14.0 11.7 12.8 10.8
to support the travel
11.0 7.2 8.0 4.7 11.8 10.7 6.1 8.8 7.7 8.5
analyst’s claim that the mean
9.5 10.2 5.6 6.9 7.9 8.6 10.5 9.6 5.7 9.6
daily base price for renting
a full-size or less expensive 12.6 12.9 6.8 12.0 5.1 14.0 9.7 10.8 9.1 12.9
vehicle in Vancouver, 5. A nonprofit consumer organization says that less than 18% of the vehicles
Washington, is more than the organization rated in a recent year have an overall score of 78 or more.
$36. In a random sample of 90 vehicles the organization rated in a recent year,
3. See Odd Answers, page A73. 20% have an overall score of 78 or more. At a = 0.05, can you support the
4. See Odd Answers, page A73. organization’s claim? (Adapted from Consumer Reports)
5. See Odd Answers, page A73. 6. In Exercise 5, the nonprofit consumer organization says that the standard
6. See Odd Answers, page A73. deviation of the vehicle rating scores is 11.90. A random sample of 90 vehicle
rating scores has a standard deviation of 11.96. At a = 0.10, is there enough
evidence to reject the organization’s claim? Assume the population is
normally distributed. (Adapted from Consumer Reports)

Chapter Test 411
7 Chapter Test
1. (a) The claim is “more than 30% Take this test as you would take a test in class.
of adults have purchased a For each exercise, perform the steps below.
meal kit in a recent year.”

H0: p … 0.30 (a) Identify the claim and state H0 and Ha.
Ha: p 7 0.30 (claim) (b) Determine whether the hypothesis test is left-tailed, right-tailed, or two-tailed,
(b) Right-tailed because the and whether to use a z-test, a t-test, or a chi-square test. Explain your reasoning.
alternative hypothesis (c) Choose one of the options.
contains 7; z-test because
Option 1: Find the critical value(s), identify the rejection region(s), and find
np Ú 5 and nq Ú 5.
the appropriate standardized test statistic.
(c) Sample answer: z0 = 1.28;
Rejection region: z 7 1.28; Option 2: Find the appropriate standardized test statistic and the P-value.
- 0.65 (d) Decide whether to reject or fail to reject the null hypothesis.
(d) Fail to reject H0. (e) Interpret the decision in the context of the original claim.
1. A retail grocery chain owner claims that more than 30% of adults have
significance to support the purchased a meal kit in a recent year. In a random sample of 36 adults, 25%
retail grocery chain’s claim have purchased a meal kit in a recent year. At a = 0.10, is there enough
that more than 30% of adults evidence to support the owner’s claim? (Adapted from Harris Interactive)
have purchased a meal kit in 2. A travel analyst claims that the mean of the room rates for two adults at
a recent year. three-star hotels in Salt Lake City is $134. In a random sample of 37 three-star
2. (a) The claim is “the mean hotels in Salt Lake City, the mean room rate for two adults is $143. Assume
of the room rates for two the population standard deviation is $30. At a = 0.10, is there enough
adults at three-star hotels in evidence to reject the analyst’s claim? (Adapted from Expedia)
Salt Lake City is $134.”
3. A travel analyst says that the mean price of a meal for a family of 4 in a resort

H0: m = 134 (claim)
Ha: m ≠ 134 restaurant is at most $100. A random sample of 33 meal prices for families of
4 has a mean of $110 and a standard deviation of $19. At a = 0.01, is there
(b) Two-tailed because the
enough evidence to reject the analyst’s claim?
alternative hypothesis
contains ≠; z-test because s 4. A research center claims that more than 80% of U.S. adults think that
is known and n Ú 30. mothers should have paid maternity leave. In a random sample of 50 U.S.
(c) Sample answer: adults, 82% think that mothers should have paid maternity leave. At
- z0 = - 1.645, z0 = 1.645; a = 0.05, is there enough evidence to support the center’s claim? (Adapted
Rejection regions: from Pew Research Center)
z 6 -1.645, z 7 1.645; 1.82 5. A nutrition bar manufacturer claims that the standard deviation of the
(d) Reject H0. number of grams of carbohydrates in a bar is 1.11 grams. A random sample
(e) There is enough evidence at of 26 bars has a standard deviation of 1.19 grams. At a = 0.05, is there
the 10% level of significance enough evidence to reject the manufacturer’s claim? Assume the population
to reject the travel analyst’s is normally distributed.
claim that the mean of the
room rates for two adults at 6. A nonprofit consumer organization says that the mean price of the vehicles
three-star hotels in Salt Lake the organization rated in a recent year is at least $41,000. In a random sample
City is $134. of 150 vehicles the organization rated in a recent year, the mean price is
3. See Selected Answers, page A103. $40,600 and the standard deviation is $17,300. At a = 0.01, is there enough
evidence to reject the organization’s claim? (Adapted from Consumer Reports)
5. See Selected Answers, page A103. 7.
A researcher claims that the mean age of the residents of a small
town is more than 38 years. The ages (in years) of a random sample
of 30 residents are listed below. At a = 0.10, is there enough evidence
7. See Selected Answers, page A103. to support the researcher’s claim? Assume the population standard
deviation is 9 years.
41 44 40 30 29 46 42 53 21 29 43 46 39 35 33
42 35 43 35 24 21 29 24 25 85 56 82 87 72 31

REAL STATISTICS Putting it all together

REAL DECISIONS
The charts show results of studies on four-year colleges in the United States.
You want to portray your college in a positive light for an advertising campaign
designed to attract high school students. You decide to use hypothesis tests to
show that your college is better than the average in certain aspects.
EXER CI SES
College Success
1. What Would You Test? Freshman retention rate
What claims could you test if you wanted to convince a student to come 73.9%
4-year graduation rate
to your college? Suppose the student you are trying to convince is mainly 39.8%
concerned with (a) affordability, (b) having a good experience, and (c) 5-year graduation rate
55.3%
graduating and starting a career. List one claim for each case. State the null 6-year graduation rate
59.6%
and alternative hypotheses for each claim. Recent graduate employment rate
2. Choosing a Random Sample 94.4%
x
Classmates suggest conducting the following sampling techniques to test 0 20 40 60 80 100
various claims. Determine whether the sample will be random. If not, Percent
suggest an alternative.
(a) Survey all the students you have class with and ask about the average
College Cost
time they spend daily on different activities.
Annual tuition, public, In-state
(b) Randomly select former students from a list of recent graduates and $9130
Annual tuition, public, Out-of-state
ask whether they are employed. $21,303
Annual tuition, private
(c) Randomly select students from a directory, ask how much debt money $33,635
they borrowed to pay for college this year, and multiply by four. Amount borrowed
$29,411
3. Supporting a Claim Need-based scholarship or grants
$14,719
You want your test to support a positive claim about your college, not just x
fail to reject one. Should you state your claim so that the null hypothesis 0 10,000 20,000 30,000
contains the claim or the alternate hypothesis contains the claim? Explain. Amount
4. Testing a Claim

You want to claim that students at your college graduate with an average Student Daily Life
debt of less than $25,000. A random sample of 40 recent graduates has a Sleeping
mean amount borrowed of $23,475 and a standard deviation of $8000. At 8.8
Leisure and sports
a = 0.05, is there enough evidence to support your claim? 4.0
Educational Activities
5. Testing a Claim 3.5
Working
You want to claim that your college has a freshmen retention rate of at least 2.3
80%. You take a random sample of 60 of last year’s freshmen and find that Traveling
1.4
54 of them still attend your college. At a = 0.05, is there enough evidence Dining
to reject your claim? 1.0
Other
3.0
6. Conclusion x
Test one of the claims you listed in Exercise 1 and interpret the results. 0 2 4 6 8 10
Discuss any limits of your sampling process. Average (in hours)

TECHNOLOGY MINITAB EXCEL T I - 8 4 PLUS
The Case of the Vanishing Women

53% Stage 1. The clerk of the Federal District Court selected
29% 9% 0%
350 people “at random” from the Boston City Directory.
From 1966 to 1968, Dr. Benjamin Spock and others were The directory contained several hundred names, 53% of
tried for conspiracy to violate the Selective Service Act by whom were women. However, only 102 of the 350 people
encouraging resistance to the Vietnam War. By a series of selected were women.
three selections, no women ended up being on the jury. Stage 2. The trial judge, Judge Ford, selected 100 people
In 1969, Hans Zeisel wrote an article in The University “at random” from the 350 people. This group was called
of Chicago Law Review using statistics and hypothesis a venire and it contained only nine women.
testing to argue that the jury selection was biased against
Dr. Spock. Dr. Spock was a well-known pediatrician Stage 3. The court clerk assigned numbers to the members
and author of books about raising children. Millions of of the venire and, one by one, they were interrogated by
mothers had read his books and followed his advice. the attorneys for the prosecution and defense until 12
Zeisel argued that, by keeping women off the jury, the members of the jury were chosen. At this stage, only
court prejudiced the verdict. one potential female juror was questioned, and she
The jury selection process for Dr. Spock’s trial is was eliminated by the prosecutor under his quota of
shown at the right. peremptory challenges (for which he did not have to give
a reason).
EXE R CI S E S
1.
The Minitab display below shows a hypothesis test 4. Describe a hypothesis test for Judge Ford’s “random”
for a claim that the proportion of women in the selection of the venire. Use a claim of
city directory is p = 0.53. In the test, n = 350 and 102
pn ≈ 0.291. Should you reject the claim? What is the p = ≈ 0.291.
350
level of significance? Explain.
(a) Write the null and alternative hypotheses.
2. In Exercise 1, you rejected the claim that p = 0.53.
But this claim was true. What type of error is this? (b) Use technology to perform the test.
3. When you reject a true claim with a level of significance (c) Make a decision.
that is virtually zero, what can you infer about the (d) Interpret the decision in the context of the original
randomness of your sampling process? claim. Could Judge Ford’s selection of 100 venire
members have been random?
MINITAB
Test and CI for One Proportion
Test of p = 0.53 vs p ≠ 0.53
Sample X N Sample p 99 % CI Z-Value P-Value

1 102 350 0.291429 (0.228862, 0.353995) - 8.94 0.000
Using the normal approximation.
Extended solutions are given in the technology manuals that accompany this text.
Technical instruction is provided for Minitab, Excel, and the TI-84 Plus.
Technology 413

7 Using Technology to Perform Hypothesis Tests

Here are some Minitab and TI-84 Plus printouts for some of the examples in this chapter.
See Example 5, page 367.
Display Descriptive Statistics... MINITAB

Store Descriptive Statistics...
Graphical Summary... One-Sample Z
1-Sample Z... Test of μ = 68.3 vs ≠ 68.3

1-Sample t... The assumed standard deviation = 3.5
2-Sample t...
Paired t... N Mean SE Mean 95% CI Z P
25 67.200 0.700 (65.828, 68.572) - 1.57 0.116
1 Proportion...
2 Proportions...
Correlation...
Covariance...
Normality Test...

Graphical Summary... One-Sample T
1-Sample Z... Test of μ = 21000 vs < 21000

1-Sample t...
2-Sample t... N Mean StDev SE Mean 95% Upper Bound T P
Paired t... 14 19189 2950 788 20585 - 2.30 0.019
1 Proportion...
2 Proportions...
Correlation...
Covariance...
Normality Test...

Graphical Summary... Test and CI for One Proportion
1-Sample Z... Test of p = 0.51 vs p ≠ 0.51

1-Sample t...
2-Sample t... Sample X N Sample p 90% CI Z-Value P-Value
Paired t... 1 1161 2202 0.527248 (0.509748, 0.544748) 1.62 0.105
Using the normal approximation.
1 Proportion...
2 Proportions...
Correlation...
Covariance...
Normality Test...

See Example 9, page 371. See Example 5, page 381. See Example 1, page 389.
EDIT CALC TESTS EDIT CALC TESTS EDIT CALC TESTS

1: Z–Test... 1: Z–Test... 1: Z–Test...
2: T–Test... 2: T–Test... 2: T–Test...
3: 2–SampZTest... 3: 2–SampZTest... 3: 2–SampZTest...
4: 2–SampTTest... 4: 2–SampTTest... 4: 2–SampTTest...
5: 1–PropZTest... 5: 1–PropZTest... 5: 1–PropZTest...
6: 2–PropZTest... 6: 2–PropZTest... 6: 2–PropZTest...
7â ZInterval... 7â ZInterval... 7â ZInterval...
Z-Test T-Test 1-PropZTest

Inpt:Data Stats Inpt:Data Stats p0:.45
µ0:88200 µ0:6.8 x:41
s:9500 x:6.7 n:100
x:85900 Sx:.35 prop≠p0 <p0 >p0
n:20 n:39 Calculate Draw
µ:≠µ0 <µ0 >µ0 µ: ≠µ0 <µ0 >µ0
Calculate Draw Calculate Draw
Z-Test T-Test 1-PropZTest

µ<88200 µ≠6.8 prop<.45
z=- 1.082727652 t=- 1.784285142 z=- .8040302522
p=.1394646984 p=.0823638462 p=.2106896879
x=85900 x=6.7 p
n =.41
n=20 Sx=.35 n=100
n=39
z=-1.0827 p=.1395 t=-1.7843 p=.0824 z=-.804 p=.2107
Using Technology to Perform Hypothesis Tests 415

Hypothesis I

Uploaded by

Copyright:

Available Formats

Hypothesis I

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Hypothesis I

Uploaded by

Copyright:

Available Formats

SAMPLE CHAPTER. NOT FOR DISTRIBUTION.

Copyright Pearson. All Rights Reserved.

Where You’ve Been

Where You’re Going

Copyright Pearson. All Rights Reserved.

7.1 Introduction to Hypothesis Testing

Copyright Pearson. All Rights Reserved.

Determine a null hypothesis and . . . greater than or equal to k. . . . less than k.

. . . less than or equal to k. . . . greater than k.

. . . equal to k. . . . not equal to k.

Copyright Pearson. All Rights Reserved.

TRY IT YOU RS ELF 1

In Example 1, notice that the claim is represented by either the null

Copyright Pearson. All Rights Reserved.

Types of Errors and Level of Significance

1. reject the null hypothesis

So, the null hypothesis is

The table shows the four possible outcomes of a hypothesis test.

Decision H0 is true. H0 is false.

Do not reject H0. Correct decision Type II error

Reject H0. Type I error Correct decision

Copyright Pearson. All Rights Reserved.

Hypothesis testing is sometimes compared to the legal system used in the

1. A carefully worded accusation is written.

Identifying Type I and Type II Errors

and the alternative hypothesis is

TRY IT YOU RS ELF 2

Copyright Pearson. All Rights Reserved.

Statistical Tests and P -Values

Population Test Standardized

One way to decide whether to reject the null hypothesis is to determine

Copyright Pearson. All Rights Reserved.

3. If the alternative hypothesis Ha contains the not-equal-to symbol 1 ≠ 2,

Copyright Pearson. All Rights Reserved.

Identifying the Nature of a Hypothesis Test

Copyright Pearson. All Rights Reserved.

Making a Decision and Interpreting the Decision

Study Tip Decision Rule Based on P-Value

Decision Claim is H0. Claim is Ha.

Copyright Pearson. All Rights Reserved.

Steps for Hypothesis Testing

2. Specify the level of significance.

3. Determine the standardized This sampling distribution

4. Calculate the test statistic and its

5. Find the P@value.

Is the P-value less than or

7. Write a statement to interpret the decision in the context of the original

Copyright Pearson. All Rights Reserved.

Strategies for Hypothesis Testing

Writing the Hypotheses

TRY IT YOU RS ELF 5

Copyright Pearson. All Rights Reserved.

7.1 EXERCISES For Extra Help: MyLab Statistics

1. The two types of hypotheses

14. H0: s2 Ú 1.2 (claim); Ha: s2 6 1.2 1 2 3 4

15. H0: p Ú 0.45; Ha: p 6 0.45 (claim) 18. Ha: m 6 3 (b) μ

18. d; H0: m Ú 3 20. Ha: m 7 2 (d) μ

20. a; H0: m … 2 21. H0: m … 8.0 22. H0: s Ú 5.2

Copyright Pearson. All Rights Reserved.

1. A carefully worded accusation is written.

3. If the alternative hypothesis Ha contains the not-equal-to symbol 1 ≠ 2,

2. Specify the level of significance.

3. Determine the standardized This sampling distribution

4. Calculate the test statistic and its

5. Find the P@value.

7. Write a statement to interpret the decision in the context of the original

59. (a) Reject H0 because the