Statistics For MGT II

Chapter 3

Hypothesis Testing

Lecture notes on Statistics for Management II Chap 3-1

 Learning Objectives

In this chapter, you learn:

 How to formulate null and alternative hypotheses for
applications involving a single population mean or
proportion
 Know what type I and Type II errors are
 How to correctly formulate a decision rule for testing a
hypothesis
 Know how to use the test statistic

Lecture notes on Statistics for Management II Chap 3-2

 Hypotheses Tests

 Hypotheses are assumptions or guesses about the probability

distribution of the population which may be true or may not be true.
There are two types of hypothesis
 Research hypotheses
 Statistical hypotheses.
Research hypothesis: A research hypothesis is the guess that motivates the
research. Research hypotheses lead directly to statistical hypotheses.
Statistical hypotheses: Statistical hypotheses evaluated by appropriate
statistical techniques

Lecture notes on Statistics for Management II Chap 3-3

 Formulating the Hypotheses

In hypothesis testing, two hypotheses are formulated

Null hypothesis (presented by Ho) is a claim (or statement) about a
population parameter that is assumed to be true until it is declared false.
 The null hypothesis will be rejected only if the sample data provide
substantial contradictory evidence. The null hypothesis contains an
equality sign, such as, “=,” “≤,” or “≥.”
Alternative Hypothesis (presented by HA) is a claim about a population
parameter that will be true if the null hypothesis is false.
Correctly specifying the null and alternative hypothesis is important. If
done incorrectly, the results obtained from the hypothesis tests may be
misleading

Lecture notes on Statistics for Management II Chap 3-4

 Formulating the Hypotheses
Example 1:
Suppose a university is considering changing its class schedule to
accommodate student’s working long hours. The registrar has stated a
change is needed because the mean number of hours worked by
undergraduate students at the university is more than 20 per week.
Establish the appropriate null and alternative hypothesis.
Solution 1:
 The registrar has made a claim stated that the mean hours worked is
“more than 20” per week, therefore
Ho : μ ≤ 20 hours
HA : μ > 20 hours (claim)

Lecture notes on Statistics for Management II Chap 3-5

 Formulating the Hypotheses
Example 2:
A company that produces several snacks and food products uses an
automatic filling machine to fill sacks with desired weight. For instances,
when the company is running potato chips on the filling line, the machine
is set to fill the sack with 20 ounces. Thus, if the machine is working
properly, the mean fill will be 20 ounces.
Each hour a sample of sacks is collected and weighted, and technicians
determine whether the machine is still operating correctly or whether it
needs adjustment.
Establish appropriate null and alternative hypotheses

Lecture notes on Statistics for Management II Chap 3-6

 Formulating the Hypotheses

Solution 2:
Step 1: Determine the population parameter of interest
The population parameter of interest is the mean weighted per sack, μ.
Step 2: Identify the hypothesis of interest
The machine is filling the sacks with the proper amount. Which is μ = 20
ounces
Step 3: Formulate the null and alternative hypothesis
Ho : μ = 20 ounces
HA : μ ≠ 20 ounces

Lecture notes on Statistics for Management II Chap 3-7

 Types of Hypothesis Tests

Hypothesis tests are formulate as either one-tailed or two-tailed

depending on how the null and alternative hypotheses are formulated
 One-tailed Test – A hypothesis test in which the entire rejection
region is located in one-tail of the sampling distribution.
In one-tail test, the entire alpha (α) level is located in one-tail of the
distribution
 Two-tailed Test – A hypothesis test in which the entire rejection
region is located in Two-tails of the sampling distribution.
In two-tailed test, the alpha (α) level is split evenly between the Two-tails
of the distribution

Lecture notes on Statistics for Management II Chap 3-8

 Types of Hypothesis Tests
Figure 3.1 Types of Hypothesis Tests
One-tailed
Two-tailed Left-tailed Right-tailed
𝐻𝑜 : 𝜇 = 25 𝐻𝑜 : 𝜇 ≥ 25 𝐻𝑜 : 𝜇 ≤ 25
𝐻𝐴 : 𝜇 ≠ 25 𝐻𝐴 : 𝜇 < 25 𝐻𝐴 : 𝜇 > 25

α/2 α/2 α α
Do not reject 𝑯𝒐 Do not reject 𝑯𝒐 Do not reject 𝑯𝒐

Reject 𝑯𝒐 Reject 𝑯𝒐 Reject 𝑯𝒐

Lecture notes on Statistics for Management II Chap 3-9

 Rejection & Non-rejection Region

The sampling distribution of the test statistic is divided into two regions, a
region of rejection (critical region) and a region of non-rejection.
 If the test statistic falls into the region of non-rejection, you do not
reject the null hypothesis.
 If the test statistic falls into the rejection region, you reject the null
hypothesis.

Lecture notes on Statistics for Management II Chap 3-10

 Rejection & Non-rejection Region
Figure 3.2 Rejection & Non-rejection Region

Critical Critical
Value Value

Rejection Rejection
Region Region
Non-rejection Region

µ
 To make a decision concerning the null hypothesis, you first determine the
critical value of the test statistic. The critical value divides the non-
rejection region from the rejection region.

Lecture notes on Statistics for Management II Chap 3-11

 Two Types of Errors

Because of the potential for extreme sampling error, two possible errors
can occur when hypothesis tested. These error show the relationship
between what actually exists and the decision made based on the sample
information.
Type I Error occurs when a true null hypothesis is rejected. The value of α
represents the probability of committing this type of error.

Type II Error occurs when a false null hypothesis is not rejected. The
value of β represents the probability of committing a Type II error.

Lecture notes on Statistics for Management II Chap 3-12

 Significance Level and Critical Value

Significance Level is the maximum allowable probability of committing a

type I error. The probability is denoted by α (alpha).
 The decision maker crying out the test specifies the significance level,
α. The value of α is determined based on the costs involved in
committing a Type I error. If making a Type I error is costly, we will
want the probability of a Type I error to be small. If a Type I error is
less costly, then we can allow a higher probability of a Type I error.
 However, in determining α, we must take into account the probability
of making a Type II error, which denoted by β (beta). The two errors α
and β are inversely related.

Lecture notes on Statistics for Management II Chap 3-13

 Significance Level and Critical Value
Having chosen a significance level, α, the decision maker then must
calculate the corresponding cutoff point, which is called critical value, z.
Critical Value is the value corresponding to a significance level that
determines those test statistic that lead to rejecting the null hypothesis and
those that lead the decision making not to reject the null hypothesis.
Here are some of most used values of α and the corresponding critical
values of z.
Conf. α Two-tailed one-tailed (<) one-tailed (>)
0.90 0.10 ± 1.645 - 1.28 1.28
0.95 0.05 ± 1.96 - 1.645 1.645
0.99 0.01 ± 2.58 - 2.33 2.33

Lecture notes on Statistics for Management II Chap 3-14

 Hypothesis Test for Population Mean, μ,
When σ is Known

To calculate the critical values corresponding to a chosen α, we need to

know the sampling distribution of the sample mean 𝑥.ҧ If the sampling
distribution satisfies the Central Limit Theorem or if the population is
normally distributed and we know the population standard deviation σ, the
sampling distribution of 𝑥ҧ is normally distributed with a mean equal to the
population mean μ and a standard deviation 𝜎ൗ 𝑛. With this information we
can calculate a critical z-value called 𝑧𝛼 .
In this text we will use the following two procedures to make tests of
hypothesis
 You can calculate a z-value and compare it to the critical value 𝑧∝

 Secondly, you can use a method called the p-value approach.

Lecture notes on Statistics for Management II Chap 3-15

 Hypothesis Test for Population Mean, μ,
When σ is Known

z-Test Statistic for Hypothesis Tests For μ, When σ is Known

𝑥ҧ − 𝜇
𝑧= 𝜎
𝑛
where:
𝑥ҧ = Sample mean
μ = Hypothesized value for the population mean
σ = Population standard deviation
n = Sample size

Lecture notes on Statistics for Management II Chap 3-16

 Hypothesis Test for Population Mean, μ,
When σ is Known
To test the hypothesis, perform the following steps:
Step 1: Formulate the null hypothesis and the alternative hypothesis in
terms of the population mean, μ.
Step 2: Specify the desired significance level (α)
Step 3: Construct the rejection region. (We strongly suggest you draw a
picture showing where in the distribution the rejection region is located)
Step 4: Computed the test statistic 𝑥ҧ − 𝜇
𝑧= 𝜎
𝑛
Step 5: Reach a decision, compare the test statistic with 𝑧𝛼 .
Step 6: Draw a conclusion regarding the null hypothesis

Lecture notes on Statistics for Management II Chap 3-17

 Hypothesis Test for Population Mean, μ,
When σ is Known

Example 3:
A hospital performs many knee replacement surgery procedures each year.
Recently, research physicians at the hospital have developed a surgery
process they believe will reduce the average patient recovery time. The
hospital board will not recommend the new procedure unless there is
substantial evidence to suggest that it is better than the existing procedure.
Records indicate that the current mean recovery rate for the standard
procedure is 142 days, with a standard deviation of 15 days. The procedure
was performed on a random sample of 36 patients and the sample mean is
140.2 days. Using 5% significance level, test whether the new procedure
results in a lower mean recovery time.

Lecture notes on Statistics for Management II Chap 3-18

 Hypothesis Test for Population Mean, μ,
When σ is Known

Solution 3:
Step 1: Formulate the null and alternative hypotheses
𝐻0 : µ ≥ 142 days
𝐻𝐴 : µ < 142 days
Step 2: Specify the desired significance level (α)
The researchers wish to test the hypothesis using a 0.05 significance level
Step 3: Construct the rejection region.
This will be one tailed test, with rejection region in the lower tail of the
sampling distribution. The critical value is
−𝑧0.05 = −1.645, therefore, the decision rule is
if 𝑧 < −1.645, reject 𝐻0 , otherwise don’t reject

Lecture notes on Statistics for Management II Chap 3-19

 Hypothesis Test for Population Mean, μ,
When σ is Known
Figure 3.3 Left-tailed test

Rejection region
α = 0.05

0
z
−𝑧0.05 = −1.645 µ=142

Step 4: Compute the test statistic 𝜎 15 15

𝜎𝑥ҧ = = = = 2.5
𝑥ҧ − 𝜇 140.2 − 142 −1.8 𝑛 36 6
𝑧= 𝜎 = = = −𝟎. 𝟕𝟐
2.5 2.5
𝑛

Lecture notes on Statistics for Management II Chap 3-20

 Hypothesis Test for Population Mean, μ,
When σ is Known

Step 5: Reach a decision, compare the test statistic with 𝑧𝛼 .

The decision rule is
If 𝑧 < −1.645, reject 𝐻0 , otherwise don’t reject, therefore,
−𝟎. 𝟕𝟐 > −𝟏. 𝟔𝟒𝟓 so, don’t reject 𝐻0
Step 6: Draw conclusion
There is no sufficient evidence to conclude that the new knee
injury replacement procedure results in a shorter average recovery
period. Thus, the hospital will not able to recommend the new
procedure on the grounds that it reduces recovery time

Lecture notes on Statistics for Management II Chap 3-21

 Hypothesis Test for Population Mean, μ,
When σ is Known
Example 4:
The mayor of a large city claims that the average net worth of families
living in this city is at least $300,000. A random sample of 25 families
selected from this city produced a mean net worth of $288,000. Assume
that the net worths of all families in this city have a normal distribution
with the population standard deviation of $80,000. Using the 1%
significance level, can you conclude that the mayor’s claim is false?.
Solution 4:
Step 1: Formulate the null and alternative hypotheses
𝐻0 : µ ≥ $300,000 (the mayor’s claim is true)
𝐻𝐴 : µ < $300,000 (the mayor’s claim is false)

Lecture notes on Statistics for Management II Chap 3-22

 Hypothesis Test for Population Mean, μ,
When σ is Known

Step 2: Specify the desired significance level (α)

The desired significance level is α = 0.01
Step 3: Construct the rejection region.
This will be one tailed test, with rejection region in the lower tail of the
sampling distribution. The critical value is
−𝑧0.01 = −2.33, therefore, the decision rule is
if 𝑧 < −2.33, reject 𝐻0 , otherwise don’t reject

Lecture notes on Statistics for Management II Chap 3-23

 Hypothesis Test for Population Mean, μ,
When σ is Known
Figure 3.4 Left-tailed test

Rejection region
α = 0.01

0
z
−𝑧0.01 = −2.33 µ = $300,000

𝜎 80,000
Step 4: Compute the test statistic 𝜎𝑥ҧ = = = 16,000
𝑛 25
𝑥ҧ − 𝜇 288,000 − 300,000 −12,000
𝑧= 𝜎 = = = −𝟎. 𝟕𝟓
16,000 16,000
𝑛

Lecture notes on Statistics for Management II Chap 3-24

 Hypothesis Test for Population Mean, μ,
When σ is Known

Step 5: Reach a decision, compare the test statistics with 𝑧𝛼 .

The decision rule is
If 𝑧 < −2.33, reject 𝐻0 , otherwise don’t reject, therefore,
−𝟎. 𝟕𝟐 > −𝟐. 𝟑𝟑 so, don’t reject 𝐻0
Step 6: Draw conclusion
The value of the test statistic z = - 0.75 is greater than the critical value of z
= -2.33. As a result, we fail to reject H0. Therefore, we can state that based
on the sample information, it appears that the mean net worth of families in
this city is not less than $300,000.

Lecture notes on Statistics for Management II Chap 3-25

 Hypothesis Test for Population Mean, μ,
When σ is Known

Example 5:
According to a Telephone Company that provides long-distance telephone
service in an area, the average length of all long-distance calls placed
through this company last year was μ = 12.44 minutes. The company’s
management wanted to check if the mean length of the current long-
distance calls is different from 12.44 minutes.
A sample of n = 150 such calls placed through this company produced a
mean length of 𝒙 ഥ =13.71 minutes. The standard deviation of all such calls
is σ = 2.65 minutes. Using the 5% significance level, can you conclude
that the mean length of all current long-distance calls is different from
12.44 minutes?

Lecture notes on Statistics for Management II Chap 3-26

 Hypothesis Test for Population Mean, μ,
When σ is Known
Solution 5:
Step 1: Formulate the null and alternative hypotheses
𝐻0 : µ = 12.44 minutes
𝐻𝐴 : µ ≠ 12.44 minutes
Step 2: Specify the desired significance level (α)
The desired significance level is α = 0.05
Step 3: Construct the rejection region.
This will be two-tailed test. The decision rule is
if –z < −1.96, reject 𝑯𝟎 and if z >1.96 reject 𝑯𝟎 . Otherwise don’t reject

Lecture notes on Statistics for Management II Chap 3-27

 Hypothesis Test for Population Mean, μ,
When σ is Known
Figure 3.5 Two-tailed test

Rejection region Rejection region

∝/2 = 0.025 ∝/2 = 0.025

z
0
−𝑧α/2 = −1.96 µ = 12.44 𝑧α/2 =1.96

σ 2.65 2.65
Step 5: Compute the test statistic σ𝑥ҧ = = = = 𝟎. 𝟐𝟏𝟔
𝑛 150 12.25
𝑥ҧ − 𝜇 13.71 − 12.44 1.27
𝑧= σ = = = 𝟓. 𝟖𝟕
0.216 0.216
𝑛

Lecture notes on Statistics for Management II Chap 3-28

 Hypothesis Test for Population Mean, μ,
When σ is Known

Step 6: Reach a decision, compare the test statistics with 𝑧𝛼/2 .

The decision rule is
If –z < −1.96, reject 𝐻0 , and if
z > 1.96 reject 𝐻0 , otherwise don’t reject, therefore,
5.87 >1.96. Therefore, reject 𝐻0
Step 7: Draw conclusion
This value of z = 5.87 is greater than the critical value of z = 1.96, and it
falls in the rejection region in the right tail in Figure 7.5. Hence, we reject
𝐻0 and conclude that based on the sample information, it appears that the
mean length of all such calls is not equal to 12.44 minutes.

Lecture notes on Statistics for Management II Chap 3-29

 Hypothesis Test for Population Mean, μ,
When σ is Not Known

t-Test Statistic for Hypothesis Tests For μ, When σ is Unknown

𝑥ҧ − 𝜇
𝑡= 𝑠
𝑛
where:
𝑥ҧ = Sample mean
μ = Hypothesized value for the population mean
s = Sample standard deviation
n = Sample size

Lecture notes on Statistics for Management II Chap 3-30

 Hypothesis Test for Population Mean, μ,
When σ is Not Known

Example 6:
Grand Auto Corporation produces auto batteries. The company claims that
its top-of-the-line Never Die batteries are good, on average, for at least 65
months. A consumer protection agency tested 45 such batteries to check
this claim.
It found that the mean life of these 45 batteries is 63.4 months, and the
standard deviation is 3 months. Find the test that the mean life of all such
batteries is less than 65 months. What will your conclusion be if the
significance level is 1%?

Lecture notes on Statistics for Management II Chap 3-31

 Hypothesis Test for Population Mean, μ,
When σ is Not Known
Solution 6:
Step 1: Formulate the null and alternative hypotheses
𝐻0 : µ ≥ 65 months (The mean life of batteries is at least 65 months.)
𝐻𝐴 : µ < 65 months (The mean life of batteries is less than 65 months.)
Step 2: Select the distribution to use
In this example, we do not know the population standard deviation, and the
sample size is large (n > 30), so we will use t-distribution
Step 3: Specify the desired significance level (α) α = 0.01
Step 4: Construct the rejection region
This will be one tailed test, with rejection region in the lower tail. The critical value
is from the t-distribution with 45 – 1 = 44 degree of freedom is −𝑡0.01 = −2.414,
therefore, the decision rule is if -𝑡 < −2.414, reject 𝐻0 , otherwise don’t reject.

Lecture notes on Statistics for Management II Chap 3-32

 Hypothesis Test for Population Mean, μ,
When σ is Not Known
Figure 3.6 Left-tailed t-test

Rejection region
α = 0.01

t
0
−𝑡0.01 = −2.414 µ = 65

𝑠 3 3
Step 5: Compute the test statistic 𝑠𝑥ҧ = = = = 0.447
𝑛 45 6.708

𝑥ҧ − 𝜇 63.4 − 65 −1.6
𝑡= = = = −𝟑. 𝟓𝟕9
𝑠𝑥ҧ 0.447 0.447

Lecture notes on Statistics for Management II Chap 3-33

 Hypothesis Test for Population Mean, μ,
When σ is Not Known

Step 6: Reach a decision, compare the test statistics with 𝑡𝛼 .

The decision rule is
If –t < −2.414, reject 𝐻0 , otherwise don’t reject, therefore,
−𝟑. 𝟓𝟕𝟖 < −𝟐. 𝟒14 so, reject 𝐻0
Step 7: Draw conclusion
We reject 𝐻0 and conclude that the mean life of such batteries is less than
65 months. Therefore, we can state that the difference between the
hypothesized population mean of 65 months and the sample mean of 63.4
is too large to be attributed to sampling error alone.

Lecture notes on Statistics for Management II Chap 3-34

 Hypothesis Test for Population Mean, μ,
When σ is Not Known
Example 7:
A computer company thinks it takes customers on average 15 minutes to
set up their computer. A newly redesigned model has been launched, and
the manager wants to know if it takes user different from 15 minutes to
set up their computers.
They sample 20 users who report on average of 14.1 minutes with
standard deviation of 1.9 minutes. Test the claim at 5% level of
significance.
Solution 7:
Step 1: Formulate the null and alternative hypotheses
𝐻0 : µ = 15 minutes
𝐻𝐴 : µ ≠ 15 minutes

Lecture notes on Statistics for Management II Chap 3-35

 Hypothesis Test for Population Mean, μ,
When σ is Not Known

Step 2: Select the distribution to use

In this example, we do not know the population standard deviation, and
the sample size is large (n < 30), so we will use t-distribution.
Step 3: Specify the desired significance level
Here the manager wants to use level of significance α = 0.05
Step 4: Construct the rejection region
This will be two-tailed test. The critical value is from the t-distribution
with 20 – 1 = 19 degree of freedom is 𝒕𝜶/𝟐 = 𝒕𝟎.𝟎𝟓/𝟐 = 𝒕𝟎.𝟎𝟐𝟓 = 2.09.
The decision rule is if -𝒕 < −𝟐.09, reject 𝑯𝟎 and if 𝒕 > 𝟐.09 reject 𝑯𝟎 .
Otherwise don’t reject

Lecture notes on Statistics for Management II Chap 3-36

 Hypothesis Test for Population Mean, μ,
When σ is Not Known
Figure 3.7 Two-tailed t-test

Rejection region Rejection region

∝/2 = 0.025 ∝/2 = 0.025

t
0
−𝑡α/2 = −2.09 µ = 15 𝑡α/2 = 2.09

𝑠 1.9 1.9
Step 5: Compute the test statistic 𝑠𝑥ҧ = = = = 0.425
𝑛 20 4.47
𝑥ҧ − 𝜇 14.1 − 15 −0.9
𝑡= = = = −𝟐. 𝟏𝟐
𝑠𝑥ҧ 0.425 0.425

Lecture notes on Statistics for Management II Chap 3-37

 Hypothesis Test for Population Mean, μ,
When σ is Not Known

Step 6: Reach a decision, compare the test statistics with 𝑡𝛼/2 .

The decision rule is
If –t < −2.09, reject 𝐻0 ,
t > 2.09, reject 𝐻0 , otherwise don’t reject, therefore,
−2.12 < −2.09 so, reject 𝐻0
Step 7: Draw conclusion
We reject 𝐻0 and conclude that it does not take customers 15 minutes to set
up their computer.

Lecture notes on Statistics for Management II Chap 3-38

 Hypothesis Test for Population Mean, μ,
When σ is Not Known
Example 8:
A pizza advertises they will deliver your pizza in no more than 20
minutes from when you place the order. You don’t believe this and decide
to test the clam at 95% level of confidence. You sample n = 7 friends who
report and average of 𝒙ഥ = 22.7 min delivery time with standard deviation
of s = 4.3 min. Test the claim?

Solution 8:
Step 1: Formulate the null and alternative hypotheses
𝐻0 : µ ≤ 20 minutes
𝐻𝐴 : µ > 20 minutes

Lecture notes on Statistics for Management II Chap 3-39

 Hypothesis Test for Population Mean, μ,
When σ is Not Known

Step 2: Select the distribution to use

In this example, we do not know the population standard deviation, and
the sample size is large (n < 30), so we will use t-distribution.
Step 3: Specify the desired significance level
Here the manager wants to use level of significance α = 0.05
Step 4: Construct the rejection region
This will be one-tailed test. The critical value is from the t-distribution
with 7 – 1 = 6 degree of freedom is 𝒕𝜶 = 𝒕𝟎.𝟎𝟓 = 1.94.
The decision rule is if 𝒕 > 𝟏.94, reject 𝑯𝟎 . Otherwise don’t reject

Lecture notes on Statistics for Management II Chap 3-40

 Hypothesis Test for Population Mean, μ,
When σ is Not Known
Figure 3.8 Right-tailed t-test

Rejection region
α = 0.05

t
0
µ = 20 𝑡α = 1.96

𝑠 4.3 4.3
Step 5: Compute the test statistic 𝑠𝑥ҧ = = = = 1.62
𝑛 7 2.65
𝑥ҧ − 𝜇 22.7 − 20 2.7
𝑡= = = = 𝟏. 𝟔𝟕
𝑠𝑥ҧ 1.62 1.62

Lecture notes on Statistics for Management II Chap 3-41

 Hypothesis Test for Population Mean, μ,
When σ is Not Known

Step 6: Reach a decision, compare the test statistics with 𝑡𝛼/2 .

The decision rule is
t > 1.94, reject 𝐻0 , otherwise don’t reject, therefore,
1.67 < 1.94. Therefore, we fail to reject 𝐻0
Step 7: Draw conclusion
We fail to reject the 𝐻0 and conclude that the pizza delivery time is more
than 20 minutes

Lecture notes on Statistics for Management II Chap 3-42

 Hypothesis Tests About a Population Proportion:
Large Samples
Although many decision problems involve a test of a population mean,
there are also cases in which the parameter of interest is the population
proportion.
 For example, a production manager might consider the proportion of
defective items produced on an assembly line to determine whether the
line should be restructured.
 A life insurance salesperson’s performance assessment might include
the proportion of existing clients who renew their policies.
 As another example, a mail-order company claims that 90% of all
orders it receives are shipped within 72 hours. The company’s
management may want to determine from time to time whether or not
this claim is true.

Lecture notes on Statistics for Management II Chap 3-43

 Hypothesis Tests About a Population Proportion:
Large Samples
The basic concept of hypothesis testing for proportions are the same as for
means.
1: The null and alternative hypotheses are stated in terms of a population
ෝ.
parameter, now p, and the sample statistics 𝒑
2: The null hypothesis should be a statement concerning the parameter
that includes the equality.
3: The significance level of the hypothesis determines the size of the
rejection region.
4: The test can be one or two-tailed, depending on how the alternative
hypothesis is formulated

Lecture notes on Statistics for Management II Chap 3-44

 Hypothesis Tests About a Population Proportion:
Large Samples
z-Test Statistic for Proportion

𝑝Ƹ − 𝑝
𝑧=
𝑝(1 − 𝑝)
𝑛
where 𝑝Ƹ = Sample Proportion
p = Hypothesized population proportion
n = Sample size
NOTE: the sample is considered to be large when np ≥ 5 and n(1 – p) ≥ 5

Lecture notes on Statistics for Management II Chap 3-45

 Hypothesis Tests About a Population Proportion:
Large Samples
Testing Hypotheses about a Single Population Proportion
Step 1: Formulate the null and alternative hypotheses
Step 2: Check whether the sample is large enough & specify the
significance level for testing the null hypothesis
Step 3: Construct the rejection region.
For a one-tail test, determine the critical value, 𝑧∝ , from the standard
normal table. For two-tail test, determine the critical values 𝑧(∝/2) from
the standard normal table
Step 4: Compute test statistic
𝑝Ƹ − 𝑝
𝑧=
𝑝(1 − 𝑝)
𝑛

Lecture notes on Statistics for Management II Chap 3-46

 Hypothesis Tests About a Population Proportion:
Large Samples
Step 5: Reach decision by comparing z test to 𝑧∝
Step 6: Draw a conclusion

Example 9:
Direct Mailing Company sells computers and computer parts by mail. The
company claims that at least 90% of all orders are mailed within 72 hours
after they are received.
The quality control department at the company often takes samples to
check if this claim is valid. A recently taken sample of 150 orders showed
that 129 of them were mailed within 72 hours. Do you think the
company’s claim is true? Use a 5% significance level.

Lecture notes on Statistics for Management II Chap 3-47

 Hypothesis Tests About a Population Proportion:
Large Samples
Solution 9:
Step 1: Formulate the null and alternative hypotheses
𝐻0 : p ≥ 0.90 (The company’s claim is true)
𝐻𝐴 : p < 0.90 (The company’s claim is false)
Step 2: Check whether the sample is large enough & specify the
significance level for testing the null hypothesis
 We first check if np and n(1 – p) is both greater than 5
np = 150(0.90) = 130 > 5 and n(1 – p) = 150(0.10) = 15 > 5
The sample size is large
 The significance level for testing null hypothesis is α = 0.05

Lecture notes on Statistics for Management II Chap 3-48

 Hypothesis Tests About a Population Proportion:
Large Samples
Step 3: Construct the rejection region.
The significance level is 0.05. and the alternative hypothesis indicates that
the test is left (see < sign). The critical value of z, obtained from normal
distribution table for 0.05 area in the left tail is -1.645.

Step 4: Compute the test statistic

𝑝Ƹ − 𝑝 𝑝Ƹ − 0.90 𝑥 129
𝑧= = Therefore, 𝑝Ƹ = = = 0.86
𝑝(1 − 𝑝) 0.90(1 − 0.90) 𝑛 150
𝑛 150

Lecture notes on Statistics for Management II Chap 3-49

 Hypothesis Test for Population Mean, μ, When σ is
Known
Figure 3.9 Left-tailed test
Rejection region
α = 0.05

0
z
−𝑧0.05 = −1.645 p =0.90

𝑝Ƹ − 0.90 0.86 − 0.90 −0.04 −0.04 −0.04

𝑧= = = = 𝑧= = −𝟏. 𝟔𝟑
0.90(1 − 0.90) 0.90(0.10) 0.09 0.0006 0.0245
150 150 150

Lecture notes on Statistics for Management II Chap 3-50

 Hypothesis Tests About a Population Proportion:
Large Samples

Step 5: Draw conclusion

The value of the test statistics z = -1.63, is greater than the critical value
of z = -1.645, therefore, we fail to reject the null hypothesis. The
proportion of all orders that are mailed within 72 hours is at least 90%,
and the company's claim is true.

Lecture notes on Statistics for Management II Chap 3-51

 Hypothesis Tests About a Population Proportion:
Large Samples
Example 10:
A report states that at least 75% of women likes red roses. The owner of a
shop that sells roses thinks this figure is too high. She asks 125 women if
they like red roses and find out of that 92 do like red roses.
At a 0.10 level of significance, test the claim.

Solution 10:
Step 1: Formulate the null and alternative hypotheses
𝐻0 : p ≥ 0.75 (The report’s claim is true)
𝐻𝐴 : p < 0.90 (The report’s claim is false)

Lecture notes on Statistics for Management II Chap 3-52

 Hypothesis Tests About a Population Proportion:
Large Samples

Step 2: Check whether the sample is large enough & specify the
significance level for testing the null hypothesis
 We first check if np and n(1 – p) is both greater than 5
np = 125(0.75) = 93.75 > 5 and n(1 – p) = 125(0.25) = 31.25 > 5
The sample size is large
 The significance level for testing null hypothesis is α = 0.10
Step 3: Construct the rejection region.
The significance level is 0.10. and the alternative hypothesis indicates that
the test is left (see < sign). The critical value of z, obtained from normal
distribution table for 0.10 area in the left tail is -1.28

Lecture notes on Statistics for Management II Chap 3-53

 Hypothesis Test for Population Mean, μ, When σ is
Not Known
Figure 3.10 Left-tailed test

Rejection region
α = 0.01

z
0
−𝑡0.01 = −1.28 p = 0.75

𝑥 92
Step 5: Compute the test statistic Where, 𝑝ො = = = 0.736
𝑛 125

𝑝Ƹ − 𝑝 𝑝Ƹ − 0.75 0.736 − 0.75 −0.014

𝑧= = 𝑧= = = −𝟎. 𝟑𝟓𝟗
𝑝(1 − 𝑝) 0.75(1 − 0.75) 0.75(0.25) 0.1875
𝑛 125 125 125

Lecture notes on Statistics for Management II Chap 3-54

 Hypothesis Tests About a Population Proportion:
Large Samples
Step 5: Draw conclusion
The value of the test statistics z = -0.359, is greater than the critical value
of z = -1.28, therefore, we fail to reject the null hypothesis.

Lecture notes on Statistics for Management II Chap 3-55