Hypothesis

Testing: T-Test on
Two Sample
Means
 Lesson Objectives
At the end of the lesson, students should be able
to:
• Understand the concept of hypothesis testing
for two sample means.
• Identify the assumptions of the t-test for two
independent samples with equal variances.
• Solve problems involving hypothesis testing
for two sample means.
T-Test for Two Sample Means
Hypothesis testing for two sample means is used to
determine if there is a statistically significant
difference between the means if two independent
groups. When the population variances are assumed
to be equal, we use the pooled variance to estimate
the common variance.
Assumptions for T-Test for Two Sample
Means
1. Independence - the two samples are randomly
selected and independently assigned to groups.
2. Normality - the populations from which the
samples are drawn are normally distributed.
3. Equal Variances - the variances of the two
populations are equal. (to use a pooled t-test)
 T-Test for Two Sample Means
ഥ𝟏 − 𝒙
𝒙 ഥ𝟐 - the mean values of the sample groups 1 and
(Pooled T-test) 2
ഥ𝟏 − 𝒙
𝒙 ഥ𝟐 𝒔𝟏 − 𝒔𝟐 - the sample variance of the sample groups 1
𝒕= and 2
𝟏 𝟏 𝒏𝟏 − 𝒏𝟐 - the sample population of groups 1 and 2
𝒔𝒑 +
𝒏𝟏 𝒏𝟐 𝒔𝒑 - the pooled standard deviation, calculated as:

𝟐 𝟐
𝒏𝟏 − 𝟏 𝒔𝟏
+ 𝒏𝟐 𝒔 𝟐
𝒔𝒑 =
𝒏𝟏 + 𝒏𝟐 − 𝟐
Recall: Hypothesis Testing Procedure

Step 1: State the null and alternative hypothesis

Step 2: Select the level of significance
Step 3: Select the appropriate test statistic
Step 4: Formulate the decision rule
Step 5: Compute the value of the test statistic
Step 6: Make a decision
Recall: Hypothesis Testing Procedure

Step 6: Making a Decision

When writing a decision, use this Afterwards, you must include your
as your guide: conclusion. In your conclusion, follow thi
• if the 𝐻0 is rejected; guide:
“There is enough evidence to • if the 𝐻0 is rejected, your conclusion
reject the “ must be your 𝐻𝑎 statement.
• if the 𝐻0 is not rejected • if the 𝐻0 is not rejected, your
“There is not enough evidence to conclusion must be your 𝐻𝑎
reject the “ statement.
Example 1
A researcher wants to determine if there is a significant
difference in the test scores of two groups of students.
The data are as follows:

Group 1 Group 2
𝑥1ҧ = 85 𝑥ҧ2 = 80
𝑠1 = 5 𝑠2 = 6
𝑛1 = 10 𝑛2 = 12

Given an 𝑎 = 0.05, test the hypothesis. Assume that

population are approximately normally distributed.
Example 1
A researcher wants to determine if there is a significant difference in the test scores of two groups of
students. The data are as follows: Group 1 Group 2
Given an 𝑎 = 0.05, test the hypothesis. Assume that population 𝑥1ҧ = 85 𝑥ҧ2 = 80
𝑠1 = 5 𝑠2 = 6
are approximately normally distributed. 𝑛1 = 10 𝑛2 = 12
Example 2
A company wants to determine if employees in the IT
Department work more hours per week than those in
the HR Department. Two independent samples are
taken:
IT Dept HR Dept
𝑥1ҧ = 45 𝑥ҧ2 = 42
𝑠1 = 5 𝑠2 = 4
𝑛1 = 15 𝑛2 = 12

Given an 𝑎 = 0.05, does the IT Department work

significantly more hours per week than the HR
Department?
Example 2
A company wants to determine if employees in the IT Department work more hours per week than
those in the HR Department. Two independent samples are taken:
Group 1 Group 2
Given an 𝑎 = 0.05, does the IT Department work significantly
𝑥1ҧ = 85 𝑥ҧ2 = 80
more hours per week than the HR Department? 𝑠1 = 5 𝑠2 = 6
𝑛1 = 10 𝑛2 = 12
Example 3
A school is testing whether a new teaching method
results in higher test scores compared to the traditional
method. Two independent groups of students are
tested:
New Method Traditional Method
𝑥1ҧ = 78 𝑥ҧ2 = 72
𝑠1 = 10 𝑠2 = 9
𝑛1 = 20 𝑛2 = 18

Given an 𝑎 = 0.01, does the new teaching method

result in significantly higher scores?
Example 3
A school is testing whether a new teaching method results in higher test scores compared to the
traditional method. Two independent groups of students are tested:
Given an 𝑎 = 0.01, does the new teaching method result in New Method Traditional Method
𝑥1ҧ = 78 𝑥ҧ2 = 72
significantly higher scores? 𝑠1 = 10 𝑠2 = 9
𝑛1 = 20 𝑛2 = 18
Example 4
A nutritionist wants to test if a new diet reduces
cholesterol levels. Two groups of patients were tested.
Given an 𝑎 = 0.05, can it be concluded that the new
diet introduced could help reduce cholesterol levels on
patients? Assume normality in its population having
equal variances.
Control Group Diet Group
𝑥1ҧ = 200 𝑥ҧ2 = 190
𝑠1 = 10 𝑠2 = 12
𝑛1 = 14 𝑛2 = 16
Example 4
A nutritionist wants to test if a new diet reduces cholesterol levels.
Two groups of patients were tested. Given an 𝑎 = 0.05, can it be Control Group Diet Group
𝑥1ҧ = 200 𝑥ҧ2 = 190
concluded that the new diet introduced could help reduce 𝑠1 = 10 𝑠2 = 12
cholesterol levels on patients? Assume normality in its population 𝑛1 = 14 𝑛2 = 16

having equal variances.

Example 5
A researcher wishes to determine whether the monthly salary of
professional elementary teachers in private schools and elementary
teachers in public schools differs. He selects a sample of
elementary teachers. From each type of school, the means and
standard deviations of their salaries were calculated as shown in
the table below. At 𝑎 = 0.01, can it be concluded that the private
school teachers does not receive the same salary with the public-
school teachers? Assume that the populations are approximately
normally distributed.
Private Public
𝑥1ҧ = ₱16,400 𝑥ҧ2 = ₱15,170
𝑠1 = ₱700 𝑠2 = ₱800
𝑛1 = 15 𝑛2 = 9
Example 5
A researcher wishes to determine whether the monthly salary of professional elementary teachers in
private schools and elementary teachers in public schools differs. He selects a sample of elementary
teachers. From each type of school, the means and standard deviations of their salaries were
calculated as shown in the table below. At a=0.01, can it be concluded that the private school
teachers does not receive the same salary with the public-school teachers? Assume that the
populations are approximately normally distributed.
Private Public
𝑥1ҧ = ₱16,400 𝑥ҧ2 = ₱15,170
𝑠1 = ₱700 𝑠2 = ₱800
𝑛1 = 15 𝑛2 = 9
 Lesson Objectives
At the end of the lesson, students should be able
to:
• Understand the concept of hypothesis testing
for two sample means.
• Identify the assumptions of the t-test for two
independent samples with equal variances.
• Solve problems involving hypothesis testing
for two sample means.