Republic of the Philippines

Department of Education
MIMAROPA Region
SCHOOLS DIVISION OF ORIENTAL MINDORO
SAN MARIANO NATIONAL HIGH SCHOOL
San Mariano. Roxas, Oriental Mindoro

Statistics and Probability

Quarter 4 – Week 4

Self-Learning Module 4
TEST STATISTIC AND REJECTION
REGION OF POPULATION
PROPORTION
 The problem that challenged researchers is not so much the
approximation of a population parameter, but rather the development of a data
- based decision procedure that can yield a decision about some scientific
system. For instance, the BFAD must decide whether a new flu vaccine is
“effective” or “ineffective”. In this case the BFAD infer something about the
system. In addition, it must include the practice of experimental data and
decision making that is based on the data. Formally, the inferences can be put
in the form of statistical hypothesis. Procedures that lead to the acceptance or
rejection of statistical hypotheses such as these include a major role of
statistical inference.
After going through this module, you are expected to:
1. Formulates the appropriate null and alternative hypotheses on a
population proportion. (M11/12SP-IVe-2)
2. Identify the appropriate form of the test-statistic when the Central
Limit Theorem is to be used. (M11/12SP-IVe-3)
3. Identify the appropriate rejection region for a given level of
significance when the Central Limit Theorem is to be used.
(M11/12SP-IVe-4)

What I Know

Determine whether the statement is True or False by checking the appropriate

box. If false, modify the statement to make it true.

Statements True False

1. The area under the normal curve is 1.
2. The areas under the curve are considered probability
values.
3. The z-distribution applies to small sample cases
4. The notations µ and σ are sample values.
5. When the alternative hypothesis utilizes the > or the <
symbol, the test is said to be non-directional.
6. Percentages can be expressed as proportions.

1
 7. If n = 35, the t-test applies.
8. When the p-value is less than or equal to the significance
level, the null hypothesis is accepted.
9. A p-value less than 0.05 (typically ≤ 0.05) is statistically
significant.
10. When a p-value is less than 0.05, it means that there is
less than 5% probability the null is correct, thus
rejecting the null hypothesis

Formulating the Appropriate Null and

Lesson
5
Alternative Hypotheses on a Population
Proportion
In the previous module, you have compared sample mean and population
mean. There are some instances wherein what we want to compare are
proportions.
In these module, we shall learn how to determine if a proportion from
the sample differs significantly from a proportion from a population.

What’s In
Steps in hypothesis testing using the z-test statistic.
1. State the hypotheses
2. Identify the level of significance
3. Determine the critical values and rejection region
4. Compute the test statistic
5. State the decision rule
6. Make a decision.

What’s New

2
Activity 1
The principal of an elementary school believes that this year, there
would be more students from the school who would pass the National
Achievement Test (NAT), so that the proportion of students who passed the
NAT is greater than the proportion obtained in previous year, which is 0.75.
What will be the appropriate null and alternative hypotheses to test this belief?
Note: Second to Fifth steps of hypothesis testing procedure will be discussed
in the next lesson.

What is It

In the problem stated above, the parameter of interest is the proportion of

students at the school who passed the NAT this year. In symbol, this parameter
is denoted as P. As applied to the problem, the appropriate null and alternative
hypotheses are:
Ho: The proportion of students of the school who passed the NAT this year is
equal to 0.75. In symbols, Ho: P ≤ 0.75.
Ha: The proportion of students at the school who passed the NAT this year is
greater than 0.75. In symbols, Ha: P > 0.75.

Note:
• A statistical hypothesis is a statement about a parameter and deals with
evaluating the value of the parameter.
• The null and alternative hypotheses should be complementary and non-
overlapping.
• Generally, the null hypothesis is a statement of equality or includes the
equality condition as in the case of ‘at least’ (greater than or equal) or ‘at
most’ (less than or equal).

Test Concerning Proportions

In the previous section, population mean is the primary concern. It was
made sure that the given population mean is no longer true based on a certain
test like the z-test or the t-test. In this section, checking of the population
proportion is the main concern, if it still holds true or no longer true. For
instance, we may check that the percentage of females in the province is still
3
significantly greater than 50%. Since sample proportions are normally

standardized. Hence, if 𝑝̂ is a random sample proportion, then it can be

distributed, a given random sample proportion from a population can be

transformed into a z-score using the formula:

Test statistic z for proportions

p− p 0

√
z= p0 (1−p 0)
n
Where: p =
x
= sample proportion
n
x = the number of successes
n = the sample size
po = given population proportion
In general,
• For a one-tailed test:
H0: p = po
Ha: p > po and the rejection region is z > + z0
Or (Ha: p < p0) and the rejection region is z < - z0
• For a two-tailed test:

H0: p = p0
Ha: p ≠ p0
The rejection region is z < -zα/2 or z > zα/2

Sometimes, the sample proportion 𝑝 is given directly such as “60% of

the respondents” which may be written as 𝑝 = 0.60. When we have to
calculate 𝑝, as in “70 out of 100 respondents were interviewed,” we use the
. Thus, p = =
x x 70
computing formula p = = 0.70. The critical values of
n n 100
z are found in the Table of Areas under the normal curve by using the same
procedures as presented in the previous topic.

4
Example:
Previous evidence show that majority of the students are happy and
contented with the university’s policies. This year, a random sample of 100
students was drawn. They were asked if they were happy and contented with
the university’s policies. Out of 100 students, 65 said so. Formulate the
appropriate null and alternative hypotheses to test this claim.
Answer:
Ho: At most, half of the student population are happy and contended with
the university’s policies. In symbols, P ≤ 0.50 while
Ha: Majority of the student population are happy and contended with the
university’s policies. In symbols, P > 0.50.

What’s More

“Suppose that the average passing percentage in the College of Nursing in

the last 10 years in board exams is 97% and this school year there were 300
students who took the exam and the passing percentage is 98% since 294
passed. What would be the null and alternative hypotheses?”

What I Have Learned

Test statistic z for proportions

p− p 0

√
z= p0 (1−p 0)
n
• For a one-tailed test:
H0: p = po
Ha: p > po and the rejection region is z > + z0
Or (Ha: p < p0) and the rejection region is z < - z0
• For a two-tailed test:
H0: p = p0
Ha: p ≠ p0
5
 The rejection region is z < -zα/2 or z > zα/2

Lesson Test-Statistic and Rejection Region of a

6 Population Proportion
In this lesson, you are going to learn about test direction, rejection
region, and level of significance which are very important in making decisions
about the claim or hypothesis. Recall that the normal curve evolved from the
probability distribution. With the area under the curve being equal to 1, it has
become a mathematical model in hypothesis testing.

What’s In

Defective Bulbs
“Mr. Sy asserts that fewer than 5% of the bulbs that he sells are
defective. Suppose 300 bulbs are randomly selected, each are tested and 10
defective bulbs are found. Does this provide sufficient evidence for Mr. Sy to
conclude that the fraction of defective bulbs is less than 0.05? Use α = 0.01.”

Formulate the null hypothesis and the alternative hypothesis

H0: p = p0
H0: p = 0.05 null hypothesis
Ha: p < 0.05 alternative hypothesis

What is It

The null hypothesis and alternative hypothesis are formulated from the
above problem. But in hypothesis testing, it does not just end in formulating of
hypothesis. We also need to identify the appropriate test statistic and rejection
region of a population proportion.
Next step is to check for assumptions:
• Is the sample size large enough for the Central Limit Theorem (CLT) to
apply?
6
 When n = 300, the Central Limit Theorem applies.
Choose a significance level size for α (alpha). Make α small when the
consequences of rejecting a true H0 is severe.
α = 0.01
Select the appropriate test statistic.
The test statistic to be used is
p− p 0

√
z= p0 (1−p 0)
n
P-values in Hypothesis Test
The p-value is the probability that the test statistic will take on a value
that is at least as extreme as the observed value of the statistic when the null
hypothesis is assumed to be true. Thus, a p value conveys much information
about the weight of evidence against Ho and so a decision maker can draw a
conclusion at any specified level of significance. Formally, we define the p-
value as the smallest level of significance that would lead to the rejection of
the null hypothesis given the observed data.

One-Tailed and Two-Tailed Test

In hypothesis testing, the set of all values of test statistic is divided into
two regions, the rejection and acceptance region. If the value of the test
statistic falls in the rejection region, then we reject the null hypothesis.
Otherwise, we do not reject it. If the region rejections are located at the tails of
the distribution of the test statistic, then we have a two-tailed test.
Figure 1. Two-tailed test

Ha: p ≠ 𝑝𝑜
7
Otherwise, we have a one-tailed test. The figure below depicts two one- tailed
tests using statistic.
Figure 2. One-Tailed test
a. Left-tailed

Ha: 𝑝 < 𝑝𝑜

b. Right-tailed

Ha: 𝑝 > 𝑝𝑜

Example: It is believed that 10% of the children enrolled in the elementary

schools are left-handed. Suppose that in a random survey of the
children it will turn out that 141 out of 800 are left-handed, would
you still believe that 10% of the children are left-handed? Use 0.05
level of significance.
Formulate the appropriate null and alternative hypotheses.
Answer: Ho: p = 0.10
Ha: p ≠ 0.10 (since we want to check whether the actual is
different from the prevailing belief)
Test Statistic to use
8
 p− p 0

√
z= p0 (1−p 0)
n
Critical Region: z > 1.96 or z < -1.96 (since this is two-tailed test)

-1.96 μ 1.96

What’s More

Supply the missing parts of the solution to the following problem.

A school administrator claims that less than 50% of the students of the school
are dissatisfied by the community cafeteria service. Test this claim by using
sample data obtained from a survey of 500 students of the school where 54%
indicated their dissatisfaction of the community cafeteria service. Use α = 0.05

STEPS SOLUTION
1. Describe the parameter of interest. The parameter of interest is the
(1) .
2. Formulate the hypotheses: the null Ho: p = 𝑝0
hypothesis and the alternative
hypothesis. That is, state a null Ho: p = 0.05
hypothesis, Ho, in such a way that a (2) Ha: _______
Type I error can be calculated.
3. Check the assumptions. With n = (3) _______ ,
Is the sample size large enough for the Central Limit
the Central Limit Theorem (CLT) to Theorem applies.
apply?

9
 4. Choose a significance level for α. α = 0.05
Make α small when the
consequences of rejecting a true H0
is severe.
(4)________________
Is the test two-tailed or one-tailed?
5. Select the appropriate test statistic (5)___________
What I Have Learned

Null Hypothesis- It is a statement about the population that either is

believed to be true or is used to put forth an argument unless it can be shown
to be incorrect beyond a reasonable doubt.
Alternate Hypothesis- The alternate hypothesis is just an alternative to
the null.

The central limit theorem states that if you have a population with mean
μ and standard deviation σ and take sufficiently large random samples from
the population with replacement, then the distribution of the sample means will
be approximately normally distributed.
If population standard deviation is unknown and n < 30, then t-test is
appropriately used.
The significance level and the rejected region are crucial in the process
of hypothesis testing. The level of significance conducts the accuracy of
prediction. The rejection region helps us decide whether to reject the null
hypothesis.

References
Books:
Belecina, R.R.; Baccay, E.S.; Mateo, E.B., Statistics and Probability, First
Edition, Rex Book Store
Frost, Jim. Statistics by Jim: Making Statistics Intuitive.
[Link]
10
Sevilla, Consuelo G. Research Methods. (C.M. Recto Avenue Manila,
Philippines: Rex Bookstore, 2009) 14 – 19.
Statistics for analytics and data science: Hypothesis testing and Z-test vs. T-
test. (2020, August 6). Analytics Vidhya.
[Link] 2020/06/statistics-analytics-
hypothesis-testing-z-test-t-test/.
Department of Education. Division of Pasig City
Department of Education – Region IV-A CALABARZON

11