Test of Significance

Number of degrees of freedom is defined as the number of values in a set which may be assigned
arbitrarily.
Ex:- Let 𝑥 + 𝑦 + 𝑧 = 6. If we assign any values to two variables (say) 𝑥, 𝑦 then 𝑧 can be determined.
Therefore, number of degrees of freedom for this equation is 2.

 In general, if we have 𝑛 variables then the number of degrees of freedom is denoted by 𝜈 = 𝑛 − 1

Test of Significance Concerning One Mean

𝑥−𝜇
Test Statistic: 𝑡 =
𝑠⁄√𝑛−1

Problem: A sample of 26 bulbs gives a mean life of 990 hours with a standard deviation of 20 hours. The
manufacturer claims that the mean life of bulbs is 1000 hours. Is the sample not upto the standard?

Solution: Given that, Population mean, 𝜇 = 1000 Sample size, 𝑛 = 26

Sample mean, 𝑥 = 990 Sample standard deviation, 𝑠 = 20

Null Hypothesis, 𝑯𝟎 : The sample is upto the standard i.e. 𝜇 = 1000

Alternative Hypothesis, 𝑯𝟏 : The sample is not upto the standard i.e. 𝜇 < 1000

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝜈 = 𝑛 − 1 = 25, 𝑡α = 1.708

𝑥−𝜇 990 − 1000

Test Statistic: 𝑡 = = = −2.5
𝑠⁄√𝑛−1 20 ⁄ √25

Conclusion: Here |𝑡| = 2.5 > 1.708 i.e. |𝑡| > 𝑡𝛼

Since, |𝑡| > 𝑡𝛼 null hypothesis, 𝐻0 is rejected.

∴ The sample is not upto the standard.

Problem: The mean life time of a sample of 25 fluorescent bulbs produced by company is computed to be
1570 hours with a standard deviation of 120 hours. The company claims that the average life of the bulbs
produced by company is 1600 hours. Using level of significance 5%, Is the claim acceptable?

Solution: Given that, Population mean, 𝜇 = 1600 Sample size, 𝑛 = 25

Sample mean, 𝑥 = 1570 Sample standard deviation, 𝑠 = 120

Null Hypothesis, 𝑯𝟎 : The average life of the bulbs is 1600 hours i.e. 𝜇 = 1600

K.KIRAN KUMAR 1
 Alternative Hypothesis, 𝑯𝟏 : The average life of the bulbs is not 1600 hours i.e. 𝜇 ≠ 1600

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝜈 = 𝑛 − 1 = 25, 𝑡α⁄2 = 2.06

𝑥−𝜇 1570 − 1600

Test Statistic: 𝑡 = = = −1.22
𝑠⁄√𝑛−1 120 ⁄ √24

Conclusion: Here |𝑡| = 1.22 < 2.06 i.e. |𝑡| < 𝑡α⁄2

Since, |𝑡| < 𝑡α⁄2 null hypothesis, 𝐻0 is accepted.

∴ The average life of the bulbs produced by company is 1600 hours.

Problem: A certain injection administered to each of 12 patients resulted in the following increases of

blood pressure : 5, 2, 8, -1, 3, 0,6, -2, 1, 5, 0, 4.

Can it be concluded that the injection will be in general, accompanied by an increase in BP.

Solution: Given that, Sample size, 𝑛 = 12

∑ 𝑥𝑖 5 + 2 + 8 −1 + 3 + 0 + 6 − 2 + 1 + 5 + 0 + 4 31
Sample mean, 𝑥 = = = 12 = 2.58
𝑛 12

∑(𝑥𝑖 −𝑥)2
Sample standard deviation, 𝑠 = √ 𝑛−1

2(5 − 2.58)2 + (2 − 2.58)2 + (8 − 2.58)2 + (−1 − 2.58)2 + (3 − 2.58)2 + 2(0 − 2.58)2

√ +(6 − 2.58)2 + (−2 − 2.58)2 + (1 − 2.58)2 + (4 − 2.58)2
=
12 − 1

116.5168
=√ = 3.2546
11

Null Hypothesis, 𝑯𝟎 : The injection will not result in increase in BP i.e. 𝑥 = 𝜇

Alternative Hypothesis, 𝑯𝟏 : The injection will result in increase in BP i.e. 𝑥 > 𝜇

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝜈 = 𝑛 − 1 = 12 − 1 = 11, 𝑡α = 1.796

𝑥−𝜇 2.58 − 0
Test Statistic: 𝑡 = = = 2.7461
𝑠⁄√𝑛 3.2546 ⁄ √12

Conclusion: Here |𝑡| = 2.7461 > 1.796 i.e. |𝑡| > 𝑡𝛼

K.KIRAN KUMAR 2
 Since, |𝑡| > 𝑡𝛼 null hypothesis, 𝐻0 is rejected.

i.e. we can conclude that the injection will be, in general accompained by an increase in BP.

Problem: The heights of 10 persons of a given locality are found to be :

70, 67, 62, 68, 61, 68, 70, 64,64, 66. Is it reasonable that the average height is greater than 64 inches?

Test at 5% significance level assuming that for 9 degrees of freedom.

Solution: Given that, Sample size, 𝑛 = 10

∑ 𝑥𝑖 70 + 67 + 62 + 68 + 61 + 68 + 70 + 64 + 64 + 66 660
Sample mean, 𝑥 = = = = 66
𝑛 10 10

∑(𝑥𝑖 −𝑥)2
Sample standard deviation, 𝑠 = √ 𝑛−1

(70 − 66)2 + (67 − 66)2 + (62 − 66)2 + 2(68 − 66)2 + (61 − 66)2
√ +(70 − 66)2 + 2(64 − 66)2 + (66 − 66)2
=
10 − 1

90
=√ = √10 = 3.16
9

Null Hypothesis, 𝑯𝟎 : Suppose that average height is 64 inches i.e. 𝜇 = 64

Alternative Hypothesis, 𝑯𝟏 : Average height is more than 64 inches i.e. 𝜇 > 64

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝜈 = 10 − 1 = 9, 𝑡α = 1.833

𝑥−𝜇 66 − 64
Test Statistic: 𝑡 = = = 2.0014
𝑠⁄√𝑛 3.16 ⁄ √10

Conclusion: Here |𝑡| = 2.0014 > 1.833 i.e. |𝑡| > 𝑡𝛼

Since, |𝑡| > 𝑡𝛼 null hypothesis, 𝐻0 is rejected.

i.e. we can conclude that the average height is greater than 64 inches .

Problem: Prices of shares of a company on the different days in a month were found to be :

66, 65, 69, 70, 69, 71, 70, 63,63, 64, 68. Discuss whether the mean price of the shares in the

month is 65?

K.KIRAN KUMAR 3
 Test of Significance for difference of Two Means

𝑥−𝑦−𝛿 𝑛1 , 𝑛2 are sample sizes

Test Statistic: 𝑡 = 1 1
where
𝑠√ + 𝑥1 , 𝑥2 are sample means
𝑛1 𝑛2

∑(𝑥𝑖 −𝑥)2 + ∑(𝑦𝑗 −𝑦)

2 𝜇 is population mean
2
Here 𝑠 = 𝑛1 + 𝑛2 − 2

Problem: Two independent samples of 8 & 7 items respectively by the following data.

Sample 1 11 11 13 11 15 9 12 14
Sample 2 9 11 10 13 9 8 10 -

Is the difference between the mean of the samples significant?

Solution: Given that, First sample size, 𝑛1 = 8 Second sample size, 𝑛2 = 7

Let, 𝑥 and 𝑦 be the means of first and second samples respectively.

∑ 𝑥𝑖 11 + 11 + 13 + 11 + 15 + 9 + 12 + 14 96
Then, 𝑥 = 𝑛
= 8
= 8
= 12

∑ 𝑦𝑖 9 + 11 + 10 + 13 + 9 + 8 + 10 70
𝑦= = = = 10
𝑛 7 7

Also, ∑(𝑥𝑖 − 𝑥)2 = 1 + 1 + 1 + 1 + 9 + 9 + 0 + 4 = 26

2
∑(𝑦𝑗 − 𝑦) = 1 + 1 + 0 + 9 + 1 + 4 + 0 = 16
2
∑(𝑥𝑖 −𝑥)2 + ∑(𝑦𝑗 −𝑦)
Sample standard deviation, 𝑠 = √ 𝑛1 + 𝑛2 − 2

26 + 16 42
=√ = √ = √3.2308 = 1.7974 ≅ 1.8
13 13

Null Hypothesis, 𝑯𝟎 : There is no significant difference between the means. i.e. 𝑥 = 𝑦

Alternative Hypothesis, 𝑯𝟏 : There is significant difference between the means. i.e. 𝑥 ≠ 𝑦

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝜈 = 𝑛1 + 𝑛2 − 2 = 13, 𝑡α/2 = 2.16

𝑥−𝑦 12 − 10 2
Test Statistic: 𝑡 = 1 1
= = = 2.1469
𝑠√𝑛 +𝑛 1 1 15
(1.8)√ + (1.8)√
1 2 8 7 56

K.KIRAN KUMAR 4
 Conclusion: Here |𝑡| = 2.1469 < 2.16 i.e. |𝑡| < 𝑡𝛼/2

Since, |𝑡| < 𝑡𝛼/2 null hypothesis, 𝐻0 is accepted.

i.e. There is no significant difference between the means.

Problem: To examine the hypothesis that the husbands are more than intelligent than the wives, an

investigation took a sample of 10 couples and administered them a test which measures the IQ. The

results are as follows:

Husbands 117 105 97 105 123 109 86 78 103 107

Wives 106 98 87 104 116 95 90 69 108 85

Test the hypothesis with a reasonable test at the level of significance 0.05

Solution: Given that, First sample size, 𝑛1 = 10 Second sample size, 𝑛2 = 10

Let, 𝑥 and 𝑦 be the means of first and second samples respectively.

∑ 𝑥𝑖 117 + 105 + 97 + 105 + 123 + 109 + 86 + 78 +103 + 107 1030
Then, 𝑥 = 𝑛
= 10
= 10
= 103

∑ 𝑦𝑖 106 + 98 + 87 + 104 + 116 + 95 + 90 + 69 +108 + 85 958

𝑦= = = = 95.8
𝑛 10 10

2
Also, ∑(𝑥𝑖 − 𝑥)2 = 1606 , ∑(𝑦𝑗 − 𝑦) = 1679.6

2
∑(𝑥𝑖 −𝑥)2 + ∑(𝑦𝑗 −𝑦)
Sample standard deviation, 𝑠 = √ 𝑛1 + 𝑛2 − 2

1606 + 1679.6 3285.6

=√ =√ = √182.53 = 13.5104 ≅ 13.51
18 18

Null Hypothesis, 𝑯𝟎 : There is no significant difference between the IQ’s of husbands and wives.

i.e. 𝑥 = 𝑦

Alternative Hypothesis, 𝑯𝟏 : Husbands are more intelligent than the wives. i.e. 𝑥 > 𝑦

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝜈 = 𝑛1 + 𝑛2 − 2 = 18, 𝑡α = 1.734

𝑥−𝑦 103 − 95.8 7.2

Test Statistic: 𝑡 = 1 1
= = = 1.1916
𝑠√𝑛 +𝑛 1 1 2
(13.51)√ + (13.51)√
1 2 10 10 10

Conclusion: Here |𝑡| = 1.1916 < 1.734 i.e. |𝑡| < 𝑡𝛼

K.KIRAN KUMAR 5
 Since, |𝑡| < 𝑡𝛼 null hypothesis, 𝐻0 is accepted.

i.e. There is no significant difference between the IQ’s of husbands and wives.

Problem: The following data relate to the marks obtained by 11 students in two tests, one held at

beginning of a year and the other at the end of the year after intensive coaching.

Test 1 19 23 16 24 17 18 20 18 21 19 20
Test 2 17 24 20 24 20 22 20 20 18 22 19

Do the data indicate that the students have benefited by coaching?

Solution: Here the given data relate to the marks obtained in two tests by the same set of students.

So that t-test for paired values can be used as follows:

Let 𝑑 = 𝑥1 − 𝑥2 , denotes the difference between the marks 𝑥1 and 𝑥2 .

Then 𝑑 ∶ 2, −1, −4, 0, −3, −4, 0, −2, 3, −3, 1.

∑ 𝑑𝑖 2−1−4+0 −3−4+0−2 +3−3+1 11

𝑑= = = − 11 = −1
𝑛 11

2
∑(𝑑𝑖 −𝑑)
Sample standard deviation, 𝑠𝑑 = √ 𝑛−1

9 + 0 + 9 + 1 + 4 + 9 + 1 + 1 + 16 + 4 + 4
=√
10

58
=√ = √5.8 = 2.41
10

Null Hypothesis, 𝑯𝟎 : The students doesn’t benefited by coaching. i.e. 𝑑 = 0

Alternative Hypothesis, 𝑯𝟏 : The students benefited by coaching. i.e. 𝑑 < 0

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝜈 = 𝑛 − 1 = 10, 𝑡α = 1.81

𝑑 −1 √11
Test Statistic: 𝑡 = = =− = −1.3762
𝑠𝑑 ⁄√𝑛 2.41⁄√11 2.41

Conclusion: Here |𝑡| = 1.3762 < 1.81 i.e. |𝑡| < 𝑡𝛼

Since, |𝑡| < 𝑡𝛼 null hypothesis, 𝐻0 is accepted.

K.KIRAN KUMAR 6
 i.e. The students haven’t been benefited by coaching.

Problem: Memory capacity of 10 students was tested before and after training. State whether training
was effective or not from the following data:

Before 12 14 11 8 7 10 3 0 5 6
After 15 16 10 7 5 12 10 2 3 8

Test of Significance for Equality of Variances

F-test
∑(𝑥𝑖 − 𝑥)2
𝑆12 =
𝑆12 𝑛1 − 1
Test Statistic: 𝐹 = ∋ 𝑆12 > 𝑆22 where
𝑆22 2
∑(𝑦𝑗 − 𝑦)
𝑆22 =
𝑛2 − 1

Problem: Two random samples gave the following results.

Sample Size of the Sample Mean Sum of Squares of

Sample Deviation from the Mean
1 10 15 90
2 12 14 108

Test whether the samples came from the same population?

Solution: To test whether the samples came from the same population, we have to test
1. The equality of variances using F-test
2. The equality of means using t-test

Given that, First sample size, 𝑛1 = 10 Second sample size, 𝑛2 = 12

First sample mean, 𝑥 = 15 Second sample mean 𝑦 = 14

2
Also, ∑(𝑥𝑖 − 𝑥)2 = 90 ∑(𝑦𝑗 − 𝑦) = 108

2
∑(𝑥𝑖 −𝑥)2 90 ∑(𝑦𝑗 −𝑦) 108
𝑆12 = = = 10 𝑆22 = = = 9.8181 ≅ 9.82
𝑛1 − 1 9 𝑛2 −1 11
F - test

Null Hypothesis, 𝑯𝟎 : There is no significant difference between the variances. i.e. 𝜎21 = 𝜎22

Alternative Hypothesis, 𝑯𝟏 : There is significant difference between the variances. i.e. 𝜎21 ≠ 𝜎22

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝐹𝛼 (𝜈1 , 𝜈2 ) = 𝐹𝛼 (9 , 11 ) = 2.9

K.KIRAN KUMAR 7
 𝑆12 10
Test Statistic: 𝐹 = = = 1.018
𝑆22 9.82

Conclusion: Here 𝐹 = 1.018 < 2.9 i.e. 𝐹 < 𝐹𝛼

Since, 𝐹 < 𝐹𝛼 null hypothesis, 𝐻0 is accepted.

i.e. There is no significant difference between the variances.

t - test

Null Hypothesis, 𝑯𝟎 : There is no significant difference between the means. i.e. 𝜇1 = 𝜇2

Alternative Hypothesis, 𝑯𝟏 : There is significant difference between the means. i.e. 𝜇1 ≠ 𝜇2

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝜈 = 𝑛1 + 𝑛2 − 2 = 20, 𝑡α/2 = 2.09

2
∑(𝑥𝑖 −𝑥)2 + ∑(𝑦𝑗 −𝑦)
Sample standard deviation, 𝑠 = √ 𝑛1 + 𝑛2 − 2

90 + 108 198
=√ =√ = √9.9 = 3.15
20 20

𝑥−𝑦 15 − 14 1
Test Statistic: 𝑡 = 1 1
= = = 0.74
𝑠√𝑛 +𝑛 1 1 22
(3.15)√ + (3.15)√
1 2 10 12 120

Conclusion: Here |𝑡| = 0.74 < 2.09 i.e. |𝑡| < 𝑡𝛼/2

Since, |𝑡| < 𝑡𝛼/2 null hypothesis, 𝐻0 is accepted.

i.e. There is no significant difference between the means.

Hence, the two samples drawn from the same population.

Problem: The nicotine contents in milligrams in two samples of tobacco were found to be as follows:

Sample A 24 27 26 21 25 -
Sample B 27 30 28 31 22 36

Can it be said that two samples came from same normal population?

Solution: To test whether the samples came from the same population, we have to test
1. The equality of variances using F-test
2. The equality of means using t-test

Given that, First sample size, 𝑛1 = 5 Second sample size, 𝑛2 = 6

K.KIRAN KUMAR 8
 ∑ 𝑥𝑖 24 + 27 + 26 + 21 + 25 123
First sample mean, 𝑥 = = = = 24.6
𝑛 5 5

∑ 𝑦𝑖 27 + 30 + 28 + 31 + 22 + 36 123
Second sample mean 𝑦 = = = = 29
𝑛 6 6

2
Also, ∑(𝑥𝑖 − 𝑥)2 = 21.2 ∑(𝑦𝑗 − 𝑦) = 108

2
∑(𝑥𝑖 −𝑥)2 21.2 ∑(𝑦𝑗 −𝑦) 108
𝑆12 = = = 5.3 𝑆22 = = = 21.6
𝑛1 − 1 4 𝑛2 −1 5
F - test

Null Hypothesis, 𝑯𝟎 : There is no significant difference between the variances. i.e. 𝜎21 = 𝜎22

Alternative Hypothesis, 𝑯𝟏 : There is significant difference between the variances. i.e. 𝜎21 ≠ 𝜎22

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝐹𝛼 (𝜈1 , 𝜈2 ) = 𝐹𝛼 (5 , 4 ) = 6.26

𝑆22 21.6
Test Statistic: 𝐹 = = = 4.0755
𝑆12 5.3

Conclusion: Here 𝐹 = 4.0755 < 6.26 i.e. 𝐹 < 𝐹𝛼

Since, 𝐹 < 𝐹𝛼 null hypothesis, 𝐻0 is accepted.

i.e. There is no significant difference between the variances.

t - test

Null Hypothesis, 𝑯𝟎 : There is no significant difference between the means. i.e. 𝜇1 = 𝜇2

Alternative Hypothesis, 𝑯𝟏 : There is significant difference between the means. i.e. 𝜇1 ≠ 𝜇2

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝜈 = 𝑛1 + 𝑛2 − 2 = 9, 𝑡α/2 = 2.26

2
∑(𝑥𝑖 −𝑥)2 + ∑(𝑦𝑗 −𝑦)
Sample standard deviation, 𝑠 = √ 𝑛1 + 𝑛2 − 2

21.2 + 108 129.2

=√ =√ = √14.36 = 3.7895
9 9

𝑥−𝑦 24.6 − 29 4.4

Test Statistic: 𝑡 = 1 1
= =− = − 1.9198
𝑠√𝑛 +𝑛 1 1 11
(3.7895)√ + (3.7895)√
1 2 5 6 30

K.KIRAN KUMAR 9
 Conclusion: Here |𝑡| = 1.9198 < 2.26 i.e. |𝑡| < 𝑡𝛼/2

Since, |𝑡| < 𝑡𝛼/2 null hypothesis, 𝐻0 is accepted.

i.e. There is no significant difference between the means.

Hence, the two samples drawn from the same population.

Problem: The measurements of the output of two units have given the following results. Assuming

that both samples have been obtained from the normal population at 5% level of significance, test

whether the two populations have the same variance?

Unit A 14.1 10.1 14.7 13.7 14

Unit B 14 14.5 13.7 12.7 14.1

Solution: Given that, First sample size, 𝑛1 = 5 Second sample size, 𝑛2 = 5

∑ 𝑥𝑖 14.1 + 10.1 + 14.7 + 13.7 + 14 66.6

First sample mean, 𝑥 = = = = 13.32
𝑛 5 5

∑ 𝑦𝑖 14 + 14.5 + 13.7 + 12.7 + 14.1 69

Second sample mean 𝑦 = = = = 13.8
𝑛 5 5

2
Also, ∑(𝑥𝑖 − 𝑥)2 = 13.488 ∑(𝑦𝑗 − 𝑦) = 1.84

2
∑(𝑥𝑖 −𝑥)2 13.488 ∑(𝑦𝑗 −𝑦) 1.84
𝑆12 = = = 3.372 𝑆22 = = = 0.46
𝑛1 − 1 4 𝑛2 −1 4

Null Hypothesis, 𝑯𝟎 : There is no significant difference between the variances. i.e. 𝜎21 = 𝜎22

Alternative Hypothesis, 𝑯𝟏 : There is significant difference between the variances. i.e. 𝜎21 ≠ 𝜎22

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝐹𝛼 (𝜈1 , 𝜈2 ) = 𝐹𝛼 (4 , 4 ) = 6.39

𝑆12 3.372
Test Statistic: 𝐹 = = = 7.33
𝑆22 0.46

Conclusion: Here 𝐹 = 7.33 > 6.39 i.e. 𝐹 > 𝐹𝛼

Since, 𝐹 > 𝐹𝛼 null hypothesis, 𝐻0 is rejected.

i.e. There is significant difference between the variances.

Problem: Pumpkins were grown under two experimental conditions. Two random samples of 11 and 9

pumpkins whose sample standard deviations of their weights are 0.8 and 0.5 respectively. Assuming that

the weight distributions are normal, test hypothesis that the true variances are equal.

K.KIRAN KUMAR 10
Solution: Given that, First sample size, 𝑛1 = 11 Second sample size, 𝑛2 = 9

First sample standard deviation, 𝑠1 = 0.8 Second sample standard deviation, 𝑠2 = 0.5

We have to determine the variances, 𝑆12 and 𝑆22 as follows:

𝑛 𝑠2 11(0.8)2 𝑛 𝑠2 9(0.5)2
𝑆12 = 𝑛 1 −1 1 = = 0.704 𝑆22 = 𝑛 2−1
2
= = 0.28125 ≅ 0.2813
1 10 2 8

Null Hypothesis, 𝑯𝟎 : There is no significant difference between the variances. i.e. 𝜎21 = 𝜎22

Alternative Hypothesis, 𝑯𝟏 : There is significant difference between the variances. i.e. 𝜎21 ≠ 𝜎22

Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝐹𝛼 (𝜈1 , 𝜈2 ) = 𝐹𝛼 (10 ,8 ) = 3.35

𝑆12 0.704
Test Statistic: 𝐹 = = = 2.5027
𝑆22 0.2813

Conclusion: Here 𝐹 = 2.5027 < 3.35 i.e. 𝐹 < 𝐹𝛼

Since, 𝐹 < 𝐹𝛼 null hypothesis, 𝐻0 is accepted.

i.e. There is no significant difference between the variances.

Problem: The following random samples are measurements of the heat-producing capacity of specimens

of coal from two mines. Whether the two populations have the same variance?

Mine A 8260 8130 8350 8070 8340 --

Mine B 7950 7890 7900 8140 7920 7840

Solution: Given that, First sample size, 𝑛1 = 5 Second sample size, 𝑛2 = 6

∑ 𝑥𝑖 8260 + 8130 + 8350 + 8070 + 8340 41150

First sample mean, 𝑥 = = = = 8230
𝑛 5 5

∑ 𝑦𝑖 7950 + 7890 + 7900 + 8140 + 7920 + 7840 47640

Second sample mean 𝑦 = = = = 7940
𝑛 6 6

Also, ∑(𝑥𝑖 − 𝑥)2 = 900 + 10000 + 14400 + 25600 + 12100 = 63000

2
∑(𝑦𝑗 − 𝑦) = 100 + 2500 + 1600 + 40000 + 400 + 10000 = 54600

2
∑(𝑥𝑖 −𝑥)2 63000 ∑(𝑦𝑗 −𝑦) 54600
𝑆12 = = = 15750 𝑆22 = = = 10920
𝑛1 − 1 4 𝑛2 −1 5

Null Hypothesis, 𝑯𝟎 : There is no significant difference between the variances. i.e. 𝜎21 = 𝜎22

Alternative Hypothesis, 𝑯𝟏 : There is significant difference between the variances. i.e. 𝜎21 ≠ 𝜎22

K.KIRAN KUMAR 11
Level of significance, 𝜶: α = 5 % = 0.05

For 5 % level of significance with 𝐹𝛼 (𝜈1 , 𝜈2 ) = 𝐹𝛼 (4 , 5 ) = 5.19

𝑆12 15750
Test Statistic: 𝐹 = = = 1.4423 ≅ 1.44
𝑆22 10920

Conclusion: Here 𝐹 = 1.44 < 5.19 i.e. 𝐹 < 𝐹𝛼

Since, 𝐹 < 𝐹𝛼 null hypothesis, 𝐻0 is accepted.

i.e. There is no significant difference between the variances.

K.KIRAN KUMAR 12