Scribd
Upload
131 views2 pages

Lesson 3: Testing The Difference Between Two Population Means: Paired Sample

This document discusses hypothesis testing for the difference between two population means using paired sample data. It provides the steps and formulas for the paired t-test, including computing the mean difference (d-bar), standard deviation, and test statistic (tc). Two examples are given to demonstrate how to perform the test by stating the hypotheses, test statistic, critical region, computations, statistical decision, and conclusion. The examples test whether a new diet pill reduces weight by more than 4 kg and whether the mean grip is greater for the right versus left hand. Both examples fail to reject the null hypotheses at the 0.05 significance level.

Uploaded by

chloe frost
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
131 views2 pages

Lesson 3: Testing The Difference Between Two Population Means: Paired Sample

This document discusses hypothesis testing for the difference between two population means using paired sample data. It provides the steps and formulas for the paired t-test, including computing the mean difference (d-bar), standard deviation, and test statistic (tc). Two examples are given to demonstrate how to perform the test by stating the hypotheses, test statistic, critical region, computations, statistical decision, and conclusion. The examples test whether a new diet pill reduces weight by more than 4 kg and whether the mean grip is greater for the right versus left hand. Both examples fail to reject the null hypotheses at the 0.05 significance level.

Uploaded by

chloe frost
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Hypothesis Testing

Lesson 3: Testing the Difference between Two Population Means: Paired Sample

Two observations are considered as paired if there is some relationship between the two observations or
that the observations are taken from the same person or object. The data layout for paired observations is:
1 2 … N
𝑥1 𝑥11 𝑥12 … 𝑥1𝑛
𝑥2 𝑥21 𝑥22 … 𝑥2𝑛
𝑑𝑖 𝑑1 = 𝑥11 − 𝑥21 𝑑2 = 𝑥21 − 𝑥22 … 𝑑𝑛 = 𝑥1𝑛 − 𝑥2𝑛

The following quantities are to be computed before doing the test:


1. Take the difference for each pair, that is, 𝑑𝑖 = 𝑥1𝑖 − 𝑥2𝑖 for all 𝑖 = 1, 2, … , 𝑛 where 𝑛 is the number
of pairs.
2. Get the mean and standard deviation of the 𝑑𝑖 ’s where
𝑛 2 2
∑ 𝑑𝑖 𝑛 ∑𝑛 𝑛
𝑖=1 𝑑𝑖 −(∑𝑖=1 𝑑𝑖 )
𝑑̅ = 𝑖=1 ; 𝑠𝑑 = √
𝑛 𝑛(𝑛−1)

Table below provides the formula needed to perform the test for paired observations.
Testing the Difference between Two Population Means: Paired Sample

Test Statistic 𝑯𝟎 𝑯𝒂 Rejection Region


𝜇𝑑 ≤ 𝑑0 𝜇𝑑 > 𝑑0 𝑡𝑐 > 𝑡(𝛼,𝑛−1)
𝜇𝑑 ≥ 𝑑0 𝜇𝑑 < 𝑑0 𝑡𝑐 < −𝑡(𝛼,𝑛−1)
𝑑̅ − 𝑑0
𝑡𝑐 = 𝑠𝑑 𝑡𝑐 < −𝑡(𝛼,,𝑛−1)
2
√𝑛 𝜇𝑑 = 𝑑0 𝜇𝑑 ≠ 𝑑0 or
𝑡𝑐 > 𝑡(𝛼,𝑛−1)
2
Note: If the difference 𝒅𝟎 is not specified, use 𝒅𝟎 = 𝟎.
𝝁𝒅 stands for 𝝁𝟏 − 𝝁𝟐 .

Example 1. The weights in kilograms of five (5) women who took a new diet pill were recorded before and
after taking pill for a 2-week period. The data are recorded below.
Women 1 2 3 4 5
Weight before (𝑥1 ) 58.5 60.3 61.7 69.0 64.0
Weight after (𝑥2 ) 60.0 54.9 58.1 62.1 58.5
𝑑𝑖 = 𝑥1𝑖 − 𝑥2𝑖 -1.5 5.4 3.6 6.9 5.5
Test the hypothesis that the pills, on the average, reduce the weight by more than 4 kilograms at 𝛼 = 0.01.
Given: 𝑛 = 5, 𝛼 = 0.01, 𝑑0 = 4
∑𝑛𝑖=1 𝑑𝑖 −1.5 + 5.4 + 3.6 + 6.9 + 5.5 19.9
𝑑̅ = = = = 3.98
𝑛 5 5
𝑛 ∑𝑛 𝑑𝑖 2 − (∑𝑛𝑖=1 𝑑𝑖 )2 5[(−1.5)2 + (5.4)2 + (3.6)2 + (6.9)2 + (5.5)2 ] − (−1.5 + 5.4 + 3.6 + 6.9 + 5.5)2 5(122.23) − (19.9)2
𝑠𝑑 = √ 𝑖=1 =√ =√ = 3.28
𝑛(𝑛 − 1) 5(5 − 1) 5(4)

Solution: Following the steps in hypothesis testing, we have:


Steps:
1. Hypotheses:
𝐻0 : The pills can reduce the weight by less than or equal to 4 kilograms, that is, 𝝁𝒅 ≤ 𝟒. 𝟎.
𝐻𝑎 : The pills can reduce the weight by more than 4 kilograms, that is, 𝝁𝒅 > 𝟒. 𝟎.
2. Significance Level: 𝛼 = 0.01
3. Test Statistic: The appropriate test statistic is
̅ − 𝒅𝟎
𝒅
𝒕𝒄 = 𝒔𝒅
√𝒏
4. Critical Regions: We have a one-tailed test with critical region, as follows

𝑡𝑐 > 𝑡(𝛼,𝑛−1) which is 𝑡𝑐 > 𝑡(0.01,4) where 𝑡(0.01,4) = 3.747 refer to t-table

Thus, we reject 𝑯𝟎 if 𝒕𝒄 > 𝟑. 𝟕𝟒𝟕.


5. Computation: Using the formula in step 3, the actual value of the test statistic is:

̅ − 𝒅𝟎
𝒅 𝟑. 𝟗𝟖 − 𝟒. 𝟎
𝒔𝒅 𝒕𝒄 =
= = −𝟎. 𝟎𝟏𝟒
𝟑. 𝟐𝟖
√𝒏 √𝟓
6. Statistical Decision: Since 𝒕𝒄 = −𝟎. 𝟎𝟏𝟒 is NOT greater than 𝟑. 𝟕𝟒𝟕 (meaning, it is NOT in the critical
region), the null hypothesis 𝑯𝟎 is NOT rejected.

7. Conclusion: The test result does not provide sufficient evidence that the pills can reduce the
weight by more than 4 kilograms at 𝜶 = 𝟎. 𝟎𝟏.

Example 2. A random sample of five (5) male students was selected from a university. Each student was asked
to determined both his left-hand and right-hand grip on an instrument designed to measure grip in pounds.
Students 1 2 3 4 5
Right-hand (𝑥1 ) 45 42 30 46 37
Grip in
Left-hand (𝑥2 ) 42 41 29 45 29
Pounds
𝑑𝑖 = 𝑥1𝑖 − 𝑥2𝑖 3 1 1 1 8
Test the hypothesis that the mean grip in the right-hand is greater than the mean grip in the left-hand. Use a 0.05
level of significance.

Given: 𝑛 = 5, 𝛼 = 0.05, 𝑑0 = 0
∑𝑛𝑖=1 𝑑𝑖 3 + 1 + 1 + 1 + 8 14
𝑑̅ = = = = 2.8
𝑛 5 5
𝑛 ∑𝑛 𝑑𝑖 2 − (∑𝑛𝑖=1 𝑑𝑖 )2 5[(3)2 + (1)2 + (1)2 + (1)2 + (1)2 ] − (3 + 1 + 1 + 1 + 8)2 5(76) − (14)2
𝑠𝑑 = √ 𝑖=1 =√ =√ = 3.03
𝑛(𝑛 − 1) 5(5 − 1) 5(4)

Solution: Following the steps in hypothesis testing, we have:


Steps:
1. Hypotheses:
𝐻0 : The mean grip in the right-hand is less than or equal to the mean grip in the left hand, that is, 𝝁𝒅 ≤ 𝟎.
𝐻𝑎 : The mean grip in the right-hand is greater than the mean grip in the left hand, that is, 𝝁𝒅 > 𝟎.
2. Significance Level: 𝛼 = 0.05
3. Test Statistic: The appropriate test statistic is
̅ − 𝒅𝟎
𝒅
𝒕𝒄 = 𝒔𝒅
√𝒏
4. Critical Regions: We have a one-tailed test with critical region, as follows

𝑡𝑐 > 𝑡(𝛼,𝑛−1) which is 𝑡𝑐 > 𝑡(0.05,4) where 𝑡(0.05,4) = 2.132 refer to t-table

Thus, we reject 𝑯𝟎 if 𝒕𝒄 > 𝟐. 𝟏𝟑𝟐.

5. Computation: Using the formula in step 3, the actual value of the test statistic is:

̅ − 𝒅𝟎
𝒅 𝟐. 𝟖 − 𝟎
𝒕𝒄 =
𝒔𝒅 = 𝟑. 𝟎𝟑 = 𝟐. 𝟎𝟔𝟔
√𝒏 √𝟓
6. Statistical Decision: Since 𝒕𝒄 = 𝟐. 𝟎𝟔𝟔 is NOT greater than 𝟐. 𝟏𝟑𝟐 (meaning, it is NOT in the critical
region), the null hypothesis 𝑯𝟎 is NOT rejected.

7. Conclusion: The test result does not provide sufficient evidence that the mean grip in the right-
hand is greater than the mean grip in the left hand at 𝜶 = 𝟎. 𝟎𝟓.

Reference: Supe, A., et. al., (2013). Elementary Statistics. Central Book Supply Inc.

Prepared by:
JOBELLE S. SIMBLANTE

You might also like