Hypothesis Testing

(Population Proportion II)

April 15 – 19, 2024

DR. CESAR R. CAIRO

Instructor
At the end of this lesson, the learner should be
able to:
• compute for the test-statistic value (population
proportion). M11/12SP-IVf-1
• draw conclusion about the population proportion
based on the statistical test value and rejection
region. M11/12SP-IVf-2; and
• solve problems involving test of hypothesis on the
population proportion. M11/12SP-IVf-g-1
 Test Statistic
used to assess the strength of evidence in support of a null hypothesis

Example:
The test statistic used in a hypothesis test for population proportion is the
𝑧-statistic.

Test Statistic for the Population Proportion

the formula for the test statistic value for the population proportion is as follows.

𝑝Ƹ − 𝑝
𝑧=
𝑝𝑞
𝑛

where 𝑝Ƹ is the sample proportion, 𝑝 is the hypothesized population proportion,

𝑞 = 1 − 𝑝, and 𝑛 is the sample size.
Example:
Let a hypothesized population proportion of 34% be given.
From a random sample of 100, the proportion obtained is
36%.
𝑝Ƹ − 𝑝
𝑧=
𝑝𝑞
𝑛
0.36 − 0.34
=
0.34 0.66
100
≈ 0.42
Example 1: Illustrate a test statistic value for population
proportion of 𝑧 = 1.77 in the sampling distribution.
Example 2: The population proportion is claimed to be 56%
and is tested using a random sample of size 240. The
obtained sample proportion is 51%. What is the value of the
test statistic?

𝑝Ƹ − 𝑝
Solution: 𝑧=
𝑞 =1−𝑝 𝑝𝑞
= 1 − 0.56 𝑛
= 0.44 0.51 − 0.56
=
0.56 ⋅ 0.44
240
𝒛 ≈ −𝟏. 𝟓𝟔
 Interpretation of the Population Proportion
Null Hypothesis
a statement which states that there is no difference between a parameter and a
specific value; denoted by 𝐻𝑜

Example:
𝐻0 : The proportion of students who have pets is 58%. (𝑝 = 0.58)

Alternative Hypothesis
a statement which states that there is a difference between a parameter and a
specific value; it is the negation of the null hypothesis

Example:
𝐻𝑎 : The proportion of students who have pets is not 58%. (𝑝 ≠ 0.58)
 One-Tailed Test
a type of hypothesis test that makes use of only one side or tail of the
distribution. It can either be a right-tailed or left-tailed test.

Example:

𝐻𝑜 : The proportion of students who have pets is at most 58%.

(𝑝 ≤ 0.58)

𝐻𝑎 : The proportion of students who have pets is more than

58%. (𝑝 > 0.58)
 Two-Tailed Test
a type of hypothesis test that makes use of two opposite sides or tails of the
distribution; it is used if the alternative hypothesis contains the “not equal to”
symbol.

Example:

𝐻𝑜 : The proportion of students who have pets is 58%.

(𝑝 = 0.58)

𝐻𝑎 : The proportion of students who have pets is not 58%.

(𝑝 ≠ 0.58)
 Level of Significance
the probability of making an error in rejecting the null hypothesis when it is
actually true

Example:
A significance level of 𝛼 = 0.01 means that there is a 1% chance of
rejecting a true null hypothesis.
Critical Values
𝑧-scores that are boundaries of the rejection region

Level of Significance
Type of Test
𝛼 = 0.01 𝛼 = 0.05
One-tailed ±2.33 ±1.65
Two-tailed ±2.58 ±1.96

Decision in Hypothesis Testing

when the test statistic value falls in the rejection region, we reject the null
hypothesis; otherwise, we do not reject the null hypothesis.
Example 1: Construct the rejection region for a right-tailed
test at 0.05 level of significance.

Solution:
Example 2: A claim about a population proportion is tested
using a left-tailed test at 0.05 level of significance. The test
statistic value is computed to be 𝑧 = −1.78. Should the null
hypothesis be rejected or not?

Solution:
1. Determine the critical values.
2. Illustrate the rejection region.
3. Determine if the test statistic
value falls in the rejection region.
4. Determine whether the null
hypothesis should be rejected or not.
 Solving Problems Involving Test of
Hypothesis on the Population Proportion
Steps in Testing the Hypothesis of a Population
Proportion

Step 1: Formulate the null and alternative hypothesis.

Step 2: Determine if the distribution is approximately a

normal distribution.

𝑛𝑝 ≥ 5
𝑛𝑞 ≥ 5
Step 3: Determine the rejection region.

Step 4: Compute for the test statistic.

𝑝Ƹ − 𝑝
𝑧=
𝑝𝑞
𝑛

Step 5: Form a decision on whether to reject 𝐻𝑜 or not.

Step 6: Make a conclusion on the hypothesis.

Example 1: It is claimed that the population proportion is
equal to 30%. A sample of size 100 is used to test the claim.
Check if the sampling distribution is approximately normal.

Solution:

1. Solve for 𝑞. 2. Check if 𝑛𝑝 ≥ 5 and 𝑛𝑞 ≥ 5.

𝑞 =1−𝑝
= 1 − 0.30 𝑛𝑝 = 100 0.30
= 0.70 = 𝟑𝟎

𝑛𝑞 = 100 0.70
= 𝟕𝟎
Example 2: It is believed that at most 50% of Filipinos have been out of
the country within the past year. To test this claim, a research institution
interviewed 200 Filipinos and found out that 120 of them have been out
of the country within the past year. Test the claim at 0.05 level of
significance.

Solution:
1. Formulate the null and alternative hypotheses.

𝐻𝑜 : The proportion of Filipinos who have been out of the

country within the past year is at most 50%. 𝑝 ≤ 0.5

𝐻𝑎 : The proportion of Filipinos who have been out of the

country within the past year is more than 50%. (𝑝 > 0.5)
Example 2: It is believed that at most 50% of Filipinos have been out of the country within
the past year. To test this claim, a research institution interviewed 200 Filipinos and found
out that 120 of them have been out of the country within the past year. Test the claim at
0.05 level of significance.

2. Determine whether the sampling distribution is

approximately normal.
𝑞 =1−𝑝
= 1 − 0.5 Verify if 𝑛𝑝 ≥ 5 and 𝑛𝑞 ≥ 5 holds.
= 0.5
𝑛𝑝 = 200 0.5
= 100

𝑛𝑞 = 200 0.5
= 100
Example 2: It is believed that at most 50% of Filipinos have been out of the country within
the past year. To test this claim, a research institution interviewed 200 Filipinos and found
out that 120 of them have been out of the country within the past year. Test the claim at
0.05 level of significance.

3. Determine the rejection region.

4. Compute for the test statistic value. 𝑝Ƹ − 𝑝

𝑧=
𝑝𝑞
120
𝑝Ƹ = = 0.6 𝑛
200
𝑝 = 0.5 0.6 − 0.5
=
𝑞 = 0.5 0.5 ⋅ 0.5
𝑛 = 200 200
≈ 𝟐. 𝟖𝟑
5. Form a decision on whether to reject 𝐻𝑜 or not.

6. Make a conclusion on the hypothesis.

 Practice Problems
1. Based on a survey, 48.9% of women in the child-bearing
age have used a family planning method. This claim will be
tested using a random sample of 25 women. Is this number
enough to test the hypothesis?
Solution:
1. Solve for 𝑞.
𝑞 =1−𝑝
= 1 − 0.489
= 0.511

2. Determine if 𝑛𝑝 ≥ 5 and 𝑛𝑞 ≥ 5 holds.

𝑛𝑝 = 25 0.489
= 12.225

𝑛𝑞 = 25 0.511
= 12.775
Example 2: A movie producer claimed that 65% of the
population watched their latest movie. This claim was tested,
and it was found out that 247 out of a random sample of 450
people watched the movie. Test the claim using a 0.05 level of
significance.
Solution:
1. Formulate the null and alternative hypotheses.

𝐻𝑜 : The proportion of people who watched the movie

producer’s latest movie is 65%. (𝑝 = 0.65)

𝐻𝑎 : The proportion of people who watched the movie

producer’s latest movie is not 65%. (𝑝 ≠ 0.65)
 Example 2: A movie producer claimed that 65% of the population watched their latest
movie. This claim was tested, and it was found out that 247 out of a random sample of 450
people watched the movie. Test the claim using a 0.05 level of significance.

2. Determine whether the sampling

distribution is approximately normal.

Verify if 𝑛𝑝 ≥ 5 and 𝑛𝑞 ≥ 5 holds.

𝑞 =1−𝑝
= 1 − 0.65 𝑛𝑝 = 450 0.65
= 𝟎. 𝟑𝟓 = 292.5

𝑛𝑞 = 450 0.35
= 157.5
3. Determine the rejection region.

4. Compute for the test statistic value.

𝑝Ƹ − 𝑝
𝑝Ƹ =
247 𝑧= 5. Form a decision on
450 𝑝𝑞
𝑝 = 0.65 𝑛 whether to reject 𝐻𝑜
𝑞 = 0.35 247 or not.
− 0.65
𝑛 = 450 = 450
0.65 ⋅ 0.35 6. Make a conclusion
450 on the hypothesis.
≈ −𝟒. 𝟓
KEY POINTS
Steps in Testing the Hypothesis of a Population
1
Proportion
Step 1: Formulate the null and alternative hypothesis.
Step 2: Determine if the distribution is approximately a normal distribution.
Step 3: Determine the rejection region.
Step 4: Compute for the test statistic.
Step 5: Form a decision on whether to reject 𝐻𝑜 or not.
Step 6: Make a conclusion on the hypothesis.
 Test Statistic
2 used to assess the strength of evidence in support of a null hypothesis

3 Test Statistic for the Population Proportion

the formula for the test statistic value for the population proportion is as follows.

𝑝Ƹ − 𝑝
𝑧=
𝑝𝑞
𝑛

where 𝑝Ƹ is the sample proportion, 𝑝 is the hypothesized population proportion,

𝑞 = 1 − 𝑝, and 𝑛 is the sample size.
 Null Hypothesis
4 a statement which states that there is no difference between a parameter and a
specific value; denoted by 𝐻𝑜

Alternative Hypothesis
5 a statement which states that there is a difference between a parameter and a
specific value; it is the negation of the null hypothesis

One-Tailed Test
6 a type of hypothesis test that makes use of only one side or tail of the
distribution. It can either be a right-tailed or left-tailed test.
 Two-Tailed Test
7 a type of hypothesis test that makes use of two opposite sides or tails of the
distribution; it is used if the alternative hypothesis contains the “not equal to”
symbol.

Level of Significance
8 the probability of making an error in rejecting the null hypothesis when it is
actually true

Critical Values
9 𝑧-scores that are boundaries of the rejection region

Decision in Hypothesis Testing

10 when the test statistic value falls in the rejection region, we reject the null
hypothesis; otherwise, we do not reject the null hypothesis.
THANK YOU
FOR
LISTENING!