ST.

JOHN PAUL II INSTITUTE OF TECHNOLOGY

TRAINING ASSESSMENT AND LEARNING CENTER INC.
FRA Bldg. Carmen West Rosales Pangasinan / Aguila Road, Sevilla, San Fernando
City La Union

STATISTICS and
PROBABILITY
– Fourth Quarter –
Module 9: Testing Hypothesis
(Week 9)

1
 Subject: Statistics and Probability
Grade & Section: Grade 11
Module No. 9
Week: 9
Subject Teacher: Ms. Lorena Obedoza

Objectives:

1. define and illustrate the null hypothesis, alternative hypothesis,

level of significance, rejection region, and types of errors in
hypothesis testing;
2. identify the rejection and non-rejection regions and the critical
values; and
3. differentiate Type I and Type II errors in claims and decisions.

Lesson
Testing Hypothesis
1

Have you at a certain time asked yourself how you could possibly decide to put a
business in place and gain your expected profit? Or wonder if a judge in a trial could
have given a wrong decision in determining who’s guilty? Or think if your classmates’
average weights differ significantly among your age? Or imagine how a newly discovered
medicine is being tested for human treatment?
This lesson will help you make sound decisions in dealing with these situations.

Hypothesis testing is a statistical method applied in making decisions using

experimental data. Hypothesis testing is basically testing an assumption that we make
about a population.
A hypothesis is a proposed explanation, assertion, or assumption about a
population parameter or about the distribution of a random variable.

Here are the examples of questions you can answer with a hypothesis test:
 Does the mean height of Grade 12 students differ from 66
inches?
 Do male and female Grade 7 and Grade 12 students differ
in height on average?
 Is the proportion of senior male students’ height
significantly higher than that of senior female students?

2
Key Terms and Concepts Used in Test Hypothesis

The Null and Alternative Hypothesis

 The null hypothesis is an initial claim based on previous analyses, which
the researcher tries to disprove, reject, or nullify. It shows no
significant difference between two parameters. It is denoted by 𝐻𝑜 .
 The alternative hypothesis is contrary to the null hypothesis, which
shows that observations are the result of a real effect. It is denoted
by𝐻𝑎 .

Note: You can think of the null hypothesis as the current value of the population parameter,
which you hope to disprove in favor of your alternative hypothesis.

Example 1.
The school record claims that the mean score in Math of the incoming
Grade 11 students is 81. The teacher wishes to find out if the claim is true. She
tests if there is a significant difference between the batch mean score and the
mean score of students in her class.
Solution:
Let 𝜇 be the population mean score and 𝑥
̅ be the mean score of students in
her class.
You may select any of the following statements as your null and
alternative hypothesis as shown in Option 1 and Option 2.

Option 1:

Option 2:

𝐻𝑜: The mean score of the incoming Grade 11 students has no significant
difference with the mean score of her students or 𝜇 = 𝑥.
𝐻𝑎: The mean score of the incoming Grade 11 students has a significant
difference with the mean score of her students or 𝜇 ≠ 𝑥.

Here is another key term you should know!

Level of Significance
 The level of significance denoted by alpha or 𝛂 refers to the degree of
significance in which we accept or reject the null hypothesis.
 100% accuracy is not possible in accepting or rejecting a hypothesis.
 The significance level α is also the probability of making the wrong
decision when the null hypothesis is true.

3
 Do you know that the most common levels of significance used are 1%, 5%, or
10%?
Some statistics books can provide us table of values for these levels of
significance.

Example 2.
Maria uses 5% level of significance in proving that there is no significant
change in the average number of enrollees in the 10 sections for the last two
years. It means that the chance that the null hypothesis (𝐻𝑜) would be rejected
when it is true is 5%.

𝛼 = 0.05

-3 -2.5 -2 -1.5 -1 -0.5 0 0.5 1 1.5 2 2.5 3

Here is another key term you should know!

Two-Tailed Test vs One-Tailed Test
 When the alternative hypothesis is two-sided like 𝐻𝑎: 𝜇 ≠ 𝜇0, it is
called two-tailed test.
 When the given statistics hypothesis assumes a less than or greater
than value, it is called one-tailed test.

Example 3.
The school registrar believes that the average number of enrollees this
school year is not the same as the previous school year.
In the above situation,
let 𝜇0 be the average number of enrollees last year.
𝐻𝑜: 𝜇 = 𝜇0
𝐻 𝑎: 𝜇 ≠ 𝜇0

If 𝐻𝑎 uses ≠, use a
two- tailed test.
𝛼 𝛼
2 2

4
 However, if the school registrar believes that the average number of
enrollees this school year is less than the previous school year, then you will have:
𝐻𝑜: 𝜇 = 𝜇0
𝐻 𝑎: 𝜇 < 𝜇0

Use the left-tailed when

𝐻𝑎 contains the symbol <.

On the other hand, if the school registrar believes that the average number
of enrollees this school year is greater than the previous school year, then you
will have:
𝐻𝑜: 𝜇 = 𝜇0
𝐻 𝑎: 𝜇 > 𝜇0

Use the right-tailed when 𝐻𝑎

contains the symbol >.

Here is the other concept!

Illustration of the Rejection Region

 The rejection region (or critical region) is the set of all values of the test
statistic that causes us to reject the null hypothesis.
 The non-rejection region (or acceptance region) is the set of all values of
the test statistic that causes us to fail to reject the null hypothesis.
 The critical value is a point (boundary) on the test distribution that is
compared to the test statistic to determine if the null hypothesis would be
rejected.

5
 Critical Value

Example 4.

Now, let’s take a look at Sofia’s first claim. She assumed that the average
online usage of her friends is the same as the global usage (𝐻𝑜).

She computed for the t-value using the formula 𝑡 = (𝒙̅ − 𝝁)/(𝒔/√𝒏)
where 𝜇 = 142, 𝑥̅ = 152, 𝑠 = 19.855, and 𝑛 = 10.

𝒙̅ − 𝝁
𝑡= 𝑠
√𝑛 Use a scientific
This t- test formula calculator to
152 − 142
was discussed in the 𝑡=
19.855
verify the
previous module. computed t-
√10
value.
10
𝑡=
6.2787

𝒕 = 𝟏. 𝟓𝟗𝟑

The table of t-values

can be found at the last
part of this module.

6
Now, you can sketch a t distribution curve and label showing the rejection area
(shaded part), the non-rejection region, the critical value, and the computed t-
value. This is how your t distribution curve should look like!

1.593 1.833

As you can see from your previous illustration, the computed t- value of 1.593
is at the left of the critical value 1.833. So, in which region do you think the
computed value falls?

The computed value is less than the critical value.

𝐻𝑜: The average online usage of

her friends is the same as the The computed
global usage. We fail to reject
t-value is at the
𝐻𝑎: The average online usage of her the null
non-rejection
friends is higher than the global hypothesis, 𝐻𝑜.
region.
usage.

Example 5.
A medical trial is conducted to test whether or not a certain drug reduces
cholesterol level. Upon trial, the computed z-value of 2.715 lies in the rejection
area.

-3 -2.5 -2 -1.5 -1 -0.5 0 0.5 11.5 2 2.5 3

The computed z-value of

2.715 can be found here!

The computed value is greater than the critical value.

𝐻𝑜: The certain drug is effective in We reject the

The computed
reducing cholesterol level by 60%. null hypothesis,
z-value is at the
𝐻𝑎: The certain drug is not effective in 𝐻𝑜 in favour of
rejection region.
reducing cholesterol level by 60%. 𝐻𝑎.

7
Example 6.
Sketch the rejection region of the test hypothesis with critical values of
±1.753 and determine if the computed t-value of –1.52 lies in that region.
Solution:
Draw a t-distribution curve. Since there are two critical values, it is a two
tailed test. Locate the critical values and shade the rejection regions.
Now, locate the computed t-value of –1.52. You can clearly see that it is
not at the rejection region as shown in the following figure. The computed t-value
is at the non-rejection region. Therefore, we fail to reject the null hypothesis,
𝐻𝑜.

– 1.52

-1.753 1.753
(critical value) (critical value)

Type I and Type II Errors

 Rejecting the null hypothesis when it is true is called a Type I error
with probability denoted by alpha (𝜶). In hypothesis testing, the
normal curve that shows the critical region is called the alpha region.
 Accepting the null hypothesis when it is false is called a Type II
error with probability denoted by beta (𝛃). In hypothesis testing,
the normal curve that shows the acceptance region is called the beta
region.
 The larger the value of alpha, the smaller is the value of beta.

This is the region of Type I error.

α = P [Type I error]
= P [𝐻𝑜 is true, Reject 𝐻𝑜]
Region where 𝐻𝑜

is true

8
 β = P [type II error]

To summarize the difference between the Type I and Type II errors, take a
look at the table below.

Null Hypothesis Fail to Reject 𝑯𝒐 Reject 𝑯𝒐

𝑯𝒐
Correct Decision Type I Error
True - Failed to reject 𝐻𝑜 when - Rejected 𝐻𝑜 when it
it is true is true
Type II Error Correct Decision
False - Failed to reject 𝐻𝑜 when - Rejected 𝐻𝑜 when it
it is false is false

Example 7.

Bryan is starting his own food cart

business and he is choosing cities where
he will run his business. He wants to
survey residents and test at 5% level of
significance whether or not the demand is
high enough to support his business
before he applies for the necessary
permits to operate in his selected city. He
will only choose a city if there is strong
evidence that the demand there is high
enough. We can state the null hypothesis
for his test as:
𝐻𝑜: The demand is high enough.

What would be the consequence of a Type I error in this setting?

He doesn't choose a city where demand is actually high enough.
He chooses a city where demand is actually high enough.
He chooses a city where demand isn't actually high enough.

The Type I error is the first statement because he

rejected the true null hypothesis.

9
What would be the consequence of a Type II error in this setting?
He doesn't choose a city where demand is actually high enough.
He chooses a city where demand is actually high enough.
He chooses a city where demand isn't actually high enough.

The Type II error is the third statement because he

failed to reject the false null hypothesis.

What is the probability of Type I error?

0.10 0.25 0.05 0.01

The probability of Type I error is 0.05 because it is the

level of significance used.

10
Activity 1.
Directions: Choose the best answer to the given questions or
statements. Write the letter of your answer on a separate sheet
of paper.
1. It is the statistical method used in making decisions using
experimental data.
A. observation C. analytical testing
B. simple analysis D. hypothesis testing

2. What term is being used to describe a proposed explanation,

assertion, or assumption about a population parameter or about
the distribution of a random variable?
A. statistic B. decision C. hypothesis D. probability

3. It is also referred to as a probability of committing an

incorrect decision about the null hypothesis.
A. level of error C. level of acceptance
B. level of hypothesis D. level of significance

4. Which of the following would be an appropriate null hypothesis?

A. The mean of a sample is equal to 80.
B. The mean of a population is equal to 80.
C. The mean of a population is not equal to 80.
D. The mean of a population is greater than 80.

5. Which of the following describes a null hypothesis using two-

tailed test?
A. 𝐻0: 𝜇 = 𝜇0 B. 𝐻0: 𝜇 ≠ 𝜇0 C. 𝐻0: 𝜇 ≥ 𝜇0 D. 𝐻0: 𝜇 ≤ 𝜇0

6. Which of the following describes an alternative hypothesis

using two- tailed test?
A. 𝐻𝑎: 𝜇 < 50 𝑦𝑒𝑎𝑟𝑠 𝑜𝑙𝑑 C. 𝐻𝑎: 𝜇 ≠ 50 𝑦𝑒𝑎𝑟𝑠 𝑜𝑙𝑑
𝐵. 𝐻𝑎: 𝜇 > 50 𝑦𝑒𝑎𝑟𝑠 𝑜𝑙𝑑 D. 𝐻𝑎: 𝜇 = 50 𝑦𝑒𝑎𝑟𝑠 𝑜𝑙𝑑

7. Which of the following must be used as the significance level if

we want a lower possibility of correct decision?
A. 1% C. 5%
B. 2% D. 10%

8. Which of the following would be an appropriate alternative

hypothesis for one-tailed test?
A. 𝐻𝑎:𝜇 = 85 B. 𝐻𝑎: 𝜇 ≥ 85 C. 𝐻𝑎: 𝜇 ≥ 85 D. 𝐻𝑎: 𝜇 < 85

9. In a one-tailed test, in which critical values below will the computed z

of 2.312 falls in the non-rejection region?
A. 1.383 B. 1.533 C. 2.228 D. 2.354

11
10. When is a Type I error committed?
A. We reject a null hypothesis that is true.
B. We reject a null hypothesis that is false.
C. We fail to reject a null hypothesis that is true.
D. We fail to reject a null hypothesis that is false.

11. When is a Type II error committed?

A. We reject a null hypothesis that is true.
B. We reject a null hypothesis that is false.
C. We fail to reject a null hypothesis that is true.
D. We fail to reject a null hypothesis that is false.

12. Which of the following is a Type I error?

A. 𝐻0 is true; reject 𝐻0. C. 𝐻0 is true; fail to reject 𝐻0.
B. 𝐻0 is false; reject 𝐻0. D. 𝐻0 is false; fail to reject 𝐻0.

13. If the computed z-value is 1.286 and the critical value is 1.383,
which of the following statements could be true?
A. It lies in the rejection region, 𝐻𝑜 must be rejected.
B. It lies in the rejection region, hence we fail to reject𝐻𝑜.
C. It lies in the non-rejection region, 𝐻𝑜 must be rejected.
D. It lies in the non-rejection region, hence we fail to reject𝐻𝑜.

14. Using a left-tailed test, which of the following value of z will not
fall in the rejection region where the critical value is – 1.638?
A. – 1.637 B. – 1.639 C. – 1.641 D. – 1.706

15. If the computed z-value is 1.915 and the critical value is 1.812,
which of the following statements could be true?
A. It lies in the rejection region, 𝐻𝑜 must be rejected.
B. It lies in the rejection region, hence we fail to reject𝐻𝑜.
C. It lies in the non-rejection region, 𝐻𝑜 must be rejected.
D. It lies in the non-rejection region, hence we fail to reject𝐻𝑜.

12
13