Unit-5

❖ Introduction of Test of Hypothesis

• One Tail test and two tail test

• Type I and Type II errors

• Hypothesis concerning one and two means & proportions

❖ Test significance (Small samples)

• Hypothesis concerning one and two means by Students t-Test

• F-test

• 𝜒 2 - Test

In many circumstances, we are to make decisions about population on the basis of only sample
information.

• Example: A drug chemist is to decide whether a new drug is really effective in curing a
disease.

Statistical Hypothesis: To arrive at decisions about the population on the basis of sample
information, we make assumptions about the population parameters involved. Such an
assumption is called a Statistical Hypothesis which may or may not be true.

• Example: The majority of men in the city are smokers

The procedure which enables us to decide on the basis of sample results whether a hypothesis is
true or not, is called Test of Hypothesis or Test of significance.

Procedure for Testing Hypothesis

➢ step 1: Statement of hypothesis ( or assumption)

There are two types of hypothesis : (i) Null Hypothesis

(ii) Alternate Hypothesis

Null Hypothesis: It is a statement about population parameter. It is denoted by 𝐻0 . A Null

Hypothesis is the hypothesis which asserts that there is no significance difference between the
statistic and the population parameter.

Example: 𝐻0 : 𝜇 = 𝜇0

Alternate Hypothesis: Any hypothesis which contradicts the null hypothesis is called an Alternate
Hypothesis, usually denoted by 𝐻1 .

Example: If 𝐻0 : 𝜇 = 𝜇0

then 𝐻1 : 𝜇 ≠ 𝜇0

or 𝐻1 : 𝜇 > 𝜇0
or 𝐻1 : 𝜇 < 𝜇0

The alternate hypothesis 𝐻1 : 𝜇 ≠ 𝜇0 is known as two-tailed alternative and

𝐻1 : 𝜇 > 𝜇0 is known as right tailed and 𝐻1 : 𝜇 < 𝜇0 is known as left tailed alternate hypothesis.

www.Jntufastupdates.com 1
The setting of alternative hypothesis is very important to decide whether we have to use a single
tailed (right or left) or two- tailed test.

➢ Step 2: Specification of the level of significance:

The level of significance denoted by 𝛼 is the confidence with which we rejects or accepts the Null
hypothesis 𝐻0 .

Example: 5% L.O.S. in a test procedure indicates that there are 5 cases out of 100 that we reject the
null hypothesis when it is true. i.e. 95% confident that we have made right decision.

➢ Step 3: Identification of the Test statistic

There are several tests of significance by z -test(Normal) , t- test, F- test etc…. First we have to select
the right test depending on the nature of the information given in the problem. Then we construct
the test criterion and select the appropriate probability distribution.

➢ Step 4: Critical Region : The critical region is formed based on following factors.

i) Distribution of the statistic [ i.e., whether the statistic follows the normal, t or F distribution.

ii) Form of alternative hypothesis.

Two sided ( two-tailed)

left tailed Right tailed

➢ Step 5: Making decision : By comparing the computed value of statistic and the critical value
decision will be taken for accepting or rejecting 𝐻0 .

If the computed value (value from step 3)< critical value then we accept 𝐻0 , otherwise we reject 𝐻0 .

Errors in sampling: we decide to accept or to reject the null hypothesis on population after
examining a sample from it. As such we have two types of errors.

(i) Type I error : Reject 𝐻0 when it is true. If the null hypothesis 𝐻0 is true but it rejected by test
procedure, then the error made is called Type I error or 𝛼 error. 𝛼 = P(Type I error) = P(Rejecting a
good population) Producer’s risk

(ii) Type II error: Accept 𝐻0 when it is wrong. If the null hypothesis 𝐻0 is false but it accepted by test
procedure, then the error made is called Type II error or 𝛽 error. 𝛽 = P(Type II error) = P(Accepting a
bad population) Consumer’s risk

Two tailed test at level of significance 𝜶

When Alternative Hypothesis is 𝜇 ≠ 𝜇0 .

The critical region is distributed on both

sides of mean equally.

Thus,the critical area under the right-tail = The critical area under the left-tail

= half of the total critical area

1 𝛼
= 2 probability of rejection = 2

www.Jntufastupdates.com 2
Hence we find critical statistic with 𝑧𝛼⁄ .
2

Left tailed test at level of significance 𝛼 Right tailed test at level of significance 𝛼

When Alternative Hypothesis is 𝜇 > 𝜇0 or 𝜇 < 𝜇0 , in a test statistical hypothesis be one tailed then
the test is called one tailed test.

The critical region lies entirely in the right tail or left tail of the sampling distribution with area equal
to level of significance 𝛼.

Hence we find critical statistic with 𝑧𝛼 .

Test significance of large samples: If the sample size is 𝑛 ≥ 30 then we consider such samples as
large samples. For large samples the sampling distribution of a statistic is approximately a normal
distribution.

Model 1:Suppose we wish to test the hypothesis that the probability of success in such trails is p.
Assuming it to be true, the mean 𝜇 and the standard deviation 𝜎 of the sampling distribution of
number of successes are 𝑛𝑝 𝑎𝑛𝑑 √𝑛𝑝𝑞 respectively.

If x be the observed number of successes in the sample and Z is standard normal variate then 𝑍 =
𝑥−𝜇
𝜎
.

Problem 1: A die is tossed 960 times and it falls with 5 upwards 184 times. Is the die unbiased at a
level of significance of 0.01?
1 1 5 1
Solution: Given 𝑛 = 960, p = P(getting 5 in one trail) = 6 ⟹ 𝑞 = 1 − 6 = 6 ⟹ 𝜇 = 𝑛𝑝 = 960 × 6 =
1 5
160 𝑎𝑛𝑑 𝜎 = √960 × × = 11.55 , 𝑥 = number of successes = 184
6 6

Null Hypothesis 𝐻0 : The die is Unbiased

Alternative Hypothesis 𝐻1 : The die is Biased.

Level of significance: 𝛼 = 0.01 ⇒ 𝑧𝛼⁄2 = 𝑧0.005 = 2.58 ( t-distribution table at ∞)

𝑥−𝜇 184−160
The test statistic is 𝑍 = = = 2.08
𝜎 11.55

Decision: As |𝑍| = 2.08 < 2.58 (𝑧0.005 ) the Null Hypothesis 𝐻0 has to be accepted at 1% level of
significance and conclude that the die is unbiased.

Problem 2: A coin is tossed 400 times and it returns head 216 times. Test the hypothesis that the
coin is unbiased. Use a 0.05 level of significance.
1 1 1
Solution: Given 𝑛 = 400, p = P(getting head in one trail) = 2 ⟹ 𝑞 = 1 − 2 = 2 ⟹ 𝜇 = 𝑛𝑝 =
1 1 1
400 × 2 = 200 𝑎𝑛𝑑 𝜎 = √400 × 2 × 2 = 10 , 𝑥 = number of successes = 216

Null Hypothesis 𝐻0 : The coin is Unbiased

Alternative Hypothesis 𝐻1 : The coin is Biased.

Level of significance: 𝛼 = 0.05 ⇒ 𝑧𝛼⁄2 = 𝑧0.025 = 1.96

www.Jntufastupdates.com 3
 𝑥−𝜇 216−200
The test statistic is 𝑍 = 𝜎
= 10
= 1.6

Decision: As |𝑍| = 1.6 < 1.96 (𝑧0.025 ) the Null Hypothesis 𝐻0 has to be accepted at 5% level of
significance and conclude that the coin is unbiased.

Modal 2: Test Significance of a Single Mean – Large Samples

Let a random sample size ‘n’ has the sample mean 𝑥̅ , and 𝜇 be the population mean. Also the
population mean 𝜇 has a specified value 𝜇0 .

Procedure for calculating test statistic:

𝑥̅ −𝜇
➢ When the S.D. (𝜎) of population is known then test statistic 𝑧 = 𝜎 .
⁄ 𝑛
√

➢ When the S.D. (𝜎) of population is not known then we take s.d. of sample (s) will be used in
𝑥̅ −𝜇
test statistic formula. i.e., 𝑧 = 𝑠 .
⁄ 𝑛
√

The confidence interval for the mean of the population corresponding to the given sample is 𝑥̅ ±
𝜎
𝑧𝛼 𝑛.
√

Problem 2.1: A sample of 400 items is taken from a population whose standard deviation is 10. The
mean of the sample is 40. Test whether the sample has come from a population with mean 38. Also
calculate 95% confidence interval for the population.

Solution: Given 𝑛 = 400, 𝜎 = 10, 𝑥̅ = 40, 𝜇 = 38 𝑎𝑛𝑑 𝛼 = 1 − 0.95 = 0.05

Null Hypothesis 𝐻0 : 𝜇 = 38

Alternative Hypothesis 𝐻1 : 𝜇 ≠ 38

Level of significance 𝛼 = 0.05 ⇒ 𝑧𝛼⁄ = 1.96 ( from Normal table)

2
𝑥̅ −𝜇 40−38
The test statistic 𝑧 = 𝜎 = 10 =4
⁄ 𝑛 ⁄
√ √400

Decision: Since 𝑧 > 𝑧𝛼⁄2 , we reject the null hypothesis 𝐻0 .

𝜎 10 10
The confidence interval is (𝑥̅ ± 𝑧𝛼⁄2 ) = (40 − 1.96 ∗ , 40 + 1.96 ∗ ) = (39.02, 40.98)
√𝑛 √400 √400

Problem 2.2: An ambulance service claims that it taken on the average less than 10 minutes to reach
its destination in emergency calls. A sample of 36 calls has a mean of 11 minutes and the variance of
16 minutes. Test the claim at 0.05 level of significance.

Solution: Given 𝜇 = 10, 𝑛 = 36, 𝑥̅ = 11, 𝜎 = √16 = 4 𝑎𝑛𝑑 𝛼 = 0.05

Null Hypothesis 𝐻0 : 𝜇 =10

Alternative Hypothesis 𝐻1 : 𝜇 < 10

Level of significance 𝛼 = 0.05 ⇒ 𝑧𝛼 = 1.645 ( from Normal table)

𝑥̅ −𝜇 11−10
The test statistic 𝑧 = 𝜎 = 4⁄ = 1.5
⁄ 𝑛
√ √36

Decision: Since 𝑧 < 𝑧𝛼 , we accept the null hypothesis 𝐻0 .

www.Jntufastupdates.com 4
Problem 2.3: A sample of 900 members has a mean of 3.4 cms and S.D. 2.61 cms. Is this sample has
been taken from a large population of mean 3.25 cms and S.D. 2.61 cms. If the population is normal
and its mean is unknown find the 95% fiducial (confidence) limits of true mean.

Solution: Given n = 900, 𝑥̅ = 3.4, 𝑠 = 2.61, 𝜇 = 3.25, 𝜎 = 2.61 𝑎𝑛𝑑 𝛼 = 0.05

Null Hypothesis 𝐻0 : 𝜇 = 3.25

Alternative Hypothesis 𝐻1 : 𝜇 ≠ 3.25

Level of significance 𝛼 = 0.05 ⇒ 𝑧𝛼/2 = 1.96 ( from Normal table)

𝑥̅ −𝜇 3.4−3.25
The test statistic 𝑧 = 𝜎 = 2.61 = 1.724
⁄ 𝑛 ⁄
√ √900

Decision: Since 𝑧 < 𝑧𝛼/2 , we accept the null hypothesis 𝐻0 .

𝜎 2.61 2.61
The confidence interval is (𝑥̅ ± 𝑧𝛼⁄2 ) = (3.4 − 1.96 ∗ , 3.4 + 1.96 ∗ ) = (3.2295, 3.57)
√𝑛 √900 √900

Modal 3: Test Significance of a two Mean – Large Samples

Let ̅̅̅
𝑥1 and ̅̅̅
𝑥2 be the sample means of two independent large random samples of sizes 𝑛1 and 𝑛2
drawn from two populations having means 𝜇1 and 𝜇2 and standard deviations 𝜎1 and 𝜎2 .

To test whether the two population means are not equal, Procedure for calculating test statistic:
|𝑥
̅̅̅̅−𝑥
1 ̅̅̅̅|−|𝜇1 −𝜇2 |
➢ When the S.D. (𝜎) of population is known then test statistic 𝑧 = 2
.
𝜎 𝜎2 2
√ 1+ 2
𝑛1 𝑛2

➢ When the S.D. (𝜎) of population is not known then we take s.d. of sample (s) will be used in
|𝑥
̅̅̅̅−𝑥
1 ̅̅̅̅|−|𝜇
2 1 −𝜇2 | |𝑥
̅̅̅̅−𝑥
1 ̅̅̅̅|−|𝜇
2 1 −𝜇2 | 𝑛1 𝑆12 +𝑛2 𝑆22
test statistic formula. i.e., 𝑧 = OR 𝑧 = 1 1
where 𝜎 = 𝑛1 +𝑛2
𝑠 2𝑠 2 𝜎√ 2+ 2
√ 1+ 2 𝑛 𝑛1 2
𝑛1 𝑛2

Problem 3.1: The means of two large samples of sizes 1000 and 2000 members are 67.5 and 68
inches respectively. Can the samples be regarded as drawn from the same population of S.D. 2.5
inches.

Solution: Let 𝜇1 and 𝜇2 be the means of the two populations.

Given 𝑛1 = 1000, 𝑛2 = 2000, ̅̅̅

𝑥1 = 67.5, ̅̅̅
𝑥2 = 68, 𝜎 = 2.5 𝑎𝑛𝑑 𝛼 = 1 − 0.95 = 0.05 (say)

Null Hypothesis 𝐻0 : 𝜇1 = 𝜇2

Alternative Hypothesis 𝐻1 : 𝜇1 ≠ 𝜇2

Level of significance 𝛼 = 0.05 ⇒ 𝑧𝛼⁄2 = 1.96 ( from Normal table)

|𝑥
̅̅̅̅−𝑥
1 ̅̅̅̅|−|𝜇
2 1 −𝜇2 | |67.5−68|−0 0.5
The test statistic 𝑧 = = 2 2
= 0.0968 = 5.16
𝜎2 𝜎2 √ 2.5 + 2.5
√ 1+ 2 1000 2000
𝑛1 𝑛2

Decision: Since 𝑧 > 𝑧𝛼⁄2 , we reject the null hypothesis 𝐻0 .

Problem 3.2: In a survey of buying habits, 400 women shoppers are chosen at random in super
market A located in a certain section of the city. Their average weekly food expenditure is Rs 250

www.Jntufastupdates.com 5
with a S.D. of Rs. 40. For 400 women shoppers chosen at random in super market B in another
section of the city, the average weekly food expenditure is Rs. 220 with a S.D. of Rs. 55. Test at 1%
level of significance whether the average weekly food expenditure of the two populations of
shoppers are equal.

Solution: Let 𝜇1 and 𝜇2 be the means of the two populations.

Given 𝑛1 = 400, ̅̅̅

𝑥1 = 250, 𝑆1 = 40

𝑛2 = 400, ̅̅̅
𝑥2 = 220, 𝑆2 = 55 𝑎𝑛𝑑 𝛼 = 1% = 0.01
Null Hypothesis 𝐻0 : 𝜇1 = 𝜇2

Alternative Hypothesis 𝐻1 : 𝜇1 ≠ 𝜇2

Level of significance 𝛼 = 0.01 ⇒ 𝑧𝛼⁄ = 𝑧0.005 = 2.58 ( from Normal table)

2

|𝑥
̅̅̅̅−𝑥
1 ̅̅̅̅|−|𝜇
2 1 −𝜇2 | 250−220−0 30
The test statistic 𝑧 = = 2 2
= 3.4 = 8.82
𝑆 2
𝑆 2 √40 +55
√ 1+ 2 400 400
𝑛1 𝑛2

Decision: Since 𝑧 > 𝑧𝛼⁄2 , we reject the null hypothesis 𝐻0 .

Problem 3.3: The average marks scored by 32 boys is 72 with a S.D. of 8. While that for 36 girls is 70
with a S.D. of 6. Does this indicate that the boys perform better than girls at level of significance 0.05
?

Solution: Let 𝜇1 and 𝜇2 be the means of the two populations.

Given 𝑛1 = 32, ̅̅̅

𝑥1 = 72, 𝑆1 = 8

𝑛2 = 36, ̅̅̅
𝑥2 = 70, 𝑆2 = 6 𝑎𝑛𝑑 𝛼 = 0.05
Null Hypothesis 𝐻0 : 𝜇1 = 𝜇2

Alternative Hypothesis 𝐻1 : 𝜇1 > 𝜇2

Level of significance 𝛼 = 0.05 ⇒ 𝑧𝛼 = 𝑧0.05 = 1.645 ( from Normal table)

|𝑥
̅̅̅̅−𝑥
1 ̅̅̅̅|−|𝜇
2 1 −𝜇2 | 72−70−0 2
The test statistic 𝑧 = = = = 1.1547
2
√8 +6
2 √3
𝑆2 𝑆2
√ 1+ 2 32 36
𝑛1 𝑛2

Decision: Since 𝑧 < 𝑧𝛼 , we accept the null hypothesis 𝐻0 .

Modal 4: Test significance for single proportion

Suppose a large random sample of size n has a sample proportion p of members possessing a certain
attribute (i.e. proportion of successes).

To test the hypothesis that the proportion p in the population has a specified value P. The test
𝑝−𝑃
statistic 𝑧 = where Q = 1-P
𝑃𝑄
√
𝑛

Problem 4.1: In a big city 325 men out of 600 men were found to be smokers. Does this information
support the conclusion that the majority of men in this city are smokers ?

www.Jntufastupdates.com 6
 325
Solution: Given 𝑛 = 600, 𝑝 = = 0.5417
600
1
Null Hypothesis 𝐻0 : The number of smokers and non-smokers are equal in the city. i.e., P = 2 ⇒
1 1
𝑄 =1− =
2 2
1
Alternative Hypothesis 𝐻1 : 𝑃 > 2 ( majority of men)

Level of significance : 𝛼 = 0.05 (say) ⇒ 𝑍𝛼 = 𝑍0.05 = 1.645

𝑝−𝑃 0.5417−0.5
Test statistic: 𝑧 = = 0.5×0.5
= 2.04
𝑃𝑄
√ √
𝑛 600

Decision: Since 𝑧 > 𝑧𝛼 , we reject the Null hypothesis.

Problem 4.2: Experience had shown that 20% of a manufactured product is of the top quality. In one
day’s production of 400 articles only 50 are of top quality. Test the hypothesis at 0.05 level.
50
Solution: Given P = 20% = 0.2, 𝑛 = 400, 𝑝 = 400 = 0.125

Null Hypothesis 𝐻0 : P = 0.2 ⇒ 𝑄 = 1 − 0.2 = 0.8

Alternative Hypothesis 𝐻1 : 𝑃 ≠ 0.2

Level of significance : 𝛼 = 0.05 ⇒ 𝑍𝛼⁄2 = 𝑍0.025 = 1.96

𝑝−𝑃 0.125−0.2
Test statistic: 𝑧 = = 0.2×0.8
= −3.75 ⇒ |𝑧| = 3.75
𝑃𝑄
√ √
𝑛 400

Decision: Since |𝑧| > 𝑧𝛼⁄ , we reject the Null hypothesis.

2

Problem 4.3: Among 900 people in a state 90 are found to be chapati eaters. Construct 99%
confidence interval for the true proportion.
90
Solution: Given 𝑛 = 900, 𝑝 = 900 = 0.1 ⇒ 𝑞 = 1 − 𝑝 = 0,

𝛼 = 1 − 0.99 = 0.01 ⇒ 𝑧𝛼⁄ = 𝑧0.005 = 2.576

2

𝑝𝑞 0.1×0.9
Now √ 𝑛 = √ 900
= 0.01

𝑝𝑞 𝑝𝑞
Confidence interval is (𝑝 − 𝑧𝛼⁄2 √ 𝑛 , 𝑝 + 𝑧𝛼⁄2 √ 𝑛 )

= (0.1 − 2.576 × 0.01, 0.1 + 2.576 × 0.01) = (0.07, 0.13)

Modal 5: Test significance for two proportions

Let 𝑝1 and 𝑝2 be the sample proportions in two large random samples of sizes 𝑛1 and 𝑛2 drawn from
|𝑝1 −𝑝2 |−|𝑃1 −𝑃2 |
two populations having proportions 𝑃1 and 𝑃2 . The test statistic 𝑧 = 𝑃 𝑄 𝑃2 𝑄2
where Q = 1-P
√ 1𝑛 1+ 𝑛
1 2

|𝑝1 −𝑝2 | |𝑝1 −𝑝2 | 𝑛1 𝑝1 +𝑛2 𝑝2

OR 𝑧 = where q = 1 – p OR 𝑧 = where 𝑝 =
𝑝1 𝑞 1 𝑝2 𝑞 2 1 1 𝑛1 +𝑛2
√ 𝑛 + 𝑛 √𝑝𝑞(𝑛 +𝑛 )
1 2 1 2

www.Jntufastupdates.com 7
Problem 5.1: In two large populations, there are 30% and 25% respectively of fair haired people. Is
this difference likely to be hidden in samples of 1200 and 900 respectively from the two populations.

Solution: Given 𝑛1 = 1200, 𝑛2 = 900, 𝑝1 = 30% = 0.3, 𝑝2 = 25% = 0.25

Null Hypothesis 𝐻0 : 𝑃1 = 𝑃2

Alternative Hypothesis 𝐻1 : 𝑃1 ≠ 𝑃2

Level of significance : 𝛼 = 0.05 (say) ⇒ 𝑍𝛼⁄2 = 𝑍0.025 = 1.96

|𝑝1 −𝑝2 | 0.3−0.25 0.05
Test statistic: 𝑧 = = = = 2.55
𝑝1 𝑞 1 𝑝 2 𝑞 2 0.3×0.7 0.25×0.75 0.0195
√ 𝑛 + 𝑛 √ +
1 2 1200 900

Decision: Since 𝑧 > 𝑧𝛼⁄2 , we reject the Null hypothesis.

Problem 5.2:In an investigation on the machine performance the following results are obtained.

Test whether there is any significance difference in the performance of two machines at 0.05 level.
17 22
Solution: Given 𝑛1 = 375, 𝑛2 = 450, 𝑝1 = = 0.045, 𝑝2 = = 0.049
375 450

Null Hypothesis 𝐻0 : 𝑃1 = 𝑃2 Alternative Hypothesis 𝐻1 : 𝑃1 ≠ 𝑃2

Level of significance : 𝛼 = 0.05 (say) ⇒ 𝑍𝛼⁄2 = 𝑍0.025 = 1.96

|𝑝1 −𝑝2 | |0.045−0.049| 0.004
Test statistic: 𝑧 = 𝑝1 𝑞 1 𝑝 2 𝑞 2
= 0.045×0.955 0.049×0.951
= 0.0147 = 0.27
√ 𝑛 + 𝑛 √ +
1 2 375 450

Decision: Since 𝑧 < 𝑧𝛼⁄ , we accept the Null hypothesis.

2

Problem 5.3:A machine puts out 16 imperfect articles in a sample of 500 articles. After the machine
is overhauled it puts out 3 imperfect articles in a sample of 100 articles. Has the Machine improved ?
16 3
Solution: Given 𝑛1 = 500, 𝑛2 = 100, 𝑝1 = 500 = 0.032, 𝑝2 = 100 = 0.03

Null Hypothesis 𝐻0 : 𝑃1 = 𝑃2

Alternative Hypothesis 𝐻1 : 𝑃1 > 𝑃2

Level of significance : 𝛼 = 0.05 (say) ⇒ 𝑍𝛼⁄2 = 𝑍0.025 = 1.96

|𝑝1 −𝑝2 | 0.032−0.03 0.002
Test statistic: 𝑧 = 𝑝1 𝑞 1 𝑝 2 𝑞 2
= 0.032×0.968 0.03×0.97
= 0.0187 = 0.106
√ 𝑛 + 𝑛 √ +
1 2 500 100

Decision: Since 𝑧 < 𝑧𝛼⁄2 , we accept the Null hypothesis.

Test significance for small samples: when size of sample is <30 then we say that sample is small
sample.

We can use normal distribution to test for a specified population mean or difference of two
population means as in large sample tests only when the sample is drawn from a normal population
whose S.D is known.

If a population is normally distributed, the sampling distribution of the sample mean for any sample
size is also normally distributed whether S.D. is known or not.

www.Jntufastupdates.com 8
Degree of freedom (𝜈): The difference between the total number of observations in the sample and
the number of independent constraints imposed on observations.

t – distribution OR Student’s t-distribution

➢ It is used for testing of hypothesis when the sample size is small and population S.D. is not
known.

➢ Modal 6: Test Significance of a Single Mean If {𝑥1 , 𝑥2 , … 𝑥𝑛 } be any random sample of size n
drawn from a normal population with mean 𝜇 and variance 𝜎 2 , then the test statistic t is
𝑥̅ −𝜇 1
defined by 𝑡 = 𝑆 where 𝑥̅ is sample mean and 𝑆 2 = 𝑛−1 ∑(𝑥𝑖 − 𝑥̅ )2 and degree of
⁄
√𝑛−1
freedom is 𝜈 = 𝑛 − 1.

➢ we find critical value from t- distribution table at given level of significance at degree of
freedom 𝜈 = 𝑛 − 1.

Problem 6.1:The average breaking strength of the steel rods is specified to be 18.5 thousand pounds.
To test this sample of 14 rods were tested. The mean and standard deviations obtained were 17.85
and 1.955 respectively. Is the result of experiment significant ?

Solution: Given sample size 𝑛 = 14, 𝑥̅ = 17.85, 𝑠 = 1.955, 𝜇 = 18.5

And 𝑑𝑒𝑔𝑟𝑒𝑒 𝑜𝑓 𝑓𝑟𝑒𝑒𝑑𝑜𝑚, 𝜈 = 𝑛 − 1 = 13.

Null Hypothesis, 𝐻0 : 𝜇 = 18.5 Alternative Hypothesis, 𝐻1 : 𝜇 ≠ 18.5

Level of significance, 𝛼 = 0.05 (say) 𝑧𝛼 (𝜈) = 𝑧0.025 (13) = 2.16

2

𝑥̅ −𝜇 17.85−18.5 −0.65
Test Statistic: 𝑡 = 𝑆 = 1.955⁄ = 0.542
= −1.199
⁄
√𝑛−1 √13

Decision: Since |𝑡| = 1.199 < 2.16, we accept the null Hypothesis at 5% L.O.S.

Problem 6.2: A random sample of 10 boys had the following I.Q’s: 70, 120, 110, 101, 88, 83, 95, 98,
107 and 100. i) Do these data support the assumption mean I.Q. of 100 ? ii) Find a reasonable range
in which most of the mean I.Q values of samples of 10 boys lie.

Solution: Given 𝑛 = 10,

The sample is {70,120,110,101,88,83,95,98,107,100}

∑𝑥 972
⇒ 𝑥̅ =mean of sample= = = 97.2
𝑛 10

∑(𝑥 − 𝑥̅ )2 1 27.22 + 22.82 + 12.82 + 3.82 + 9.22 + 14.22 1833.6

⇒ 𝑆2 = = ( 2 2 2 2 )= = 203.73
𝑛−1 9 +2.2 + 0.8 + 9.8 + 2.8 9
⇒ 𝑆 = √203.73 = 14.27
Degree of freedom, 𝜈 = 𝑛 − 1 = 9

i) Null Hypothesis 𝐻0 : 𝜇 = 100

Alternative Hypothesis 𝐻1 : 𝜇 ≠ 100

Level of significance, 𝛼 = 0.05 (say) 𝑧𝛼 (𝜈) = 𝑧0.025 (13) = 2.16

2

www.Jntufastupdates.com 9
 𝑥̅ −𝜇 97.2−100 −2.8
Test Statistic: 𝑡 = 𝑆 = 14.27⁄ = = −0.588
⁄ 4.756
√𝑛−1 √9

Decision: Since |𝑡| = 0.588 < 2.16, we accept the null Hypothesis at 5% Level of Significance.

Problem 6.3: Eight students were given a test in Statistics and after one month coaching they were
given another test of the similar nature. The following table gives the increase in their marks in the
second test over the first. Do the marks indicate that the students have gained from the coaching?

Student No. 1 2 3 4 5 6 7 8

Increase in marks 4 -2 6 -8 12 5 -7 2

Solution: Given 𝑛 = 8,

The sample is {4, −2,110,101,88,83,95,98,107,100}

∑𝑥 972
⇒ 𝑥̅ =mean of sample= 𝑛
= 10
= 97.2

∑(𝑥 − 𝑥̅ )2 1 27.22 + 22.82 + 12.82 + 3.82 + 9.22 + 14.22 1833.6

⇒ 𝑆2 = = ( 2 2 2 2 )= = 203.73
𝑛−1 9 +2.2 + 0.8 + 9.8 + 2.8 9
⇒ 𝑆 = √203.73 = 14.27
Degree of freedom, 𝜈 = 𝑛 − 1 = 9

i) Null Hypothesis 𝐻0 : 𝜇 = 100

Alternative Hypothesis 𝐻1 : 𝜇 ≠ 100

Level of significance, 𝛼 = 0.05 (say) 𝑧𝛼 (𝜈) = 𝑧0.025 (9) = 2.262

2

𝑥̅ −𝜇 97.2−100 −2.8
Test Statistic: 𝑡 = 𝑆 = 14.27⁄ = 4.756 = −0.588
⁄
√𝑛−1 √9

Decision: Since |𝑡| = 0.588 < 2.262, we accept the null Hypothesis at 5% Level of Significance.

Problem 6.4: 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 and 68. Discuss whether the mean price of the shares in the month
is 65.

Solution: Given 𝜇 = 65, 𝑛 = 11, sample = {66,65,69,70,69,71,70,63,63,64,68}

∑𝑥 738
⇒ 𝑥̅ =mean of sample= 𝑛
= 11
= 67.09

∑(𝑥 − 𝑥̅ )2 1 1.092 + 2.092 + 1.912 + 2.912 + 1.912 + 3.912 80.441

⇒ 𝑆2 = = ( 2 2 2 2 )= = 8.0441
𝑛−1 10 +4.09 + 4.09 + 3.09 + 0.91 10
⇒ 𝑆 = √8.0441 = 2.836
Degree of freedom, 𝜈 = 𝑛 − 1 =10

i) Null Hypothesis 𝐻0 : 𝜇 = 65

www.Jntufastupdates.com 10
Alternative Hypothesis 𝐻1 : 𝜇 ≠ 65

Level of significance, 𝛼 = 0.05 (say) 𝑧𝛼 (𝜈) = 𝑧0.025 (10) = 2.228

2

𝑥̅ −𝜇 67.09−65 2.09
Test Statistic: 𝑡 = 𝑆 = 2.836 = 0.897 = 2.33
⁄ ⁄
√𝑛−1 √10

Decision: Since |𝑡| = 2.33 > 2.228, we reject the null Hypothesis at 5% Level of Significance.

➢ Modal 7: Test Significance of difference of Means

Let 𝑥̅ , 𝑦̅ be the means of two independent samples of sizes 𝑛1 &𝑛2 drawn from two normal
populations having means 𝜇1 &𝜇2 . To test whether the two populations means are equal (i.e., to test
whether the difference 𝜇1 − 𝜇2 is significant).

𝑥̅ −𝑦̅ 𝑛 𝑠12 +𝑛2 𝑠22 1 1

The test statistic is 𝑡 = , where 𝑆 = √ 𝑛1 , 𝑥̅ = 𝑛 ∑ 𝑥𝑖 , 𝑦̅ = 𝑛 ∑ 𝑦𝑖
1
𝑆.√ +
1 1 +𝑛2 −2 1 2
𝑛1 𝑛2

[∑(𝑥𝑖 −𝑥̅ )2 +∑(𝑦𝑖 −𝑦̅)2 ]

OR 𝑆 = √ 𝑛1 +𝑛2 −2
follows t-distribution with (𝑛1 + 𝑛2 − 2) degree of freedom.

Problem 7.2: A group of 5 patients treated with medicine A weigh 42, 39, 48, 60 and 41 kgs. Second
group of 7 patients from the same hospital treated with medicine B weigh 38, 42, 56, 64, 68, 69 and
62 kgs. Do you agree with the claim that meadicine B increases the weight significantly.

Solution: Given sample sizes 𝑛1 = 5, 𝑛2 = 7

∑ 𝑥 230
𝑥̅ = = = 46
5 5
∑ 𝑦 399
𝑦̅ = = = 57
7 7

x ̅
𝒙−𝒙 ̅)𝟐
(𝒙 − 𝒙 y ̅
𝒚−𝒚 ̅)𝟐
(𝒚 − 𝒚

42 -4 16 38 -19 361

39 -7 49 42 -15 225

48 2 4 56 -1 1

60 14 196 64 7 49

41 -5 25 68 11 121

69 12 144

62 5 25

230 290 399 926

www.Jntufastupdates.com 11
 ∑(𝑥−𝑥̅ )2 +∑(𝑦−𝑦̅)2 290+926 1216
𝑆2 = 𝑛1 +𝑛2 −2
= 5+7−2
= 10
= 121.6 ⇒ 𝑆 = 11.03, 𝜈 = 5 + 7 − 2 = 10

Null Hypothesis, 𝐻0 : 𝜇1 = 𝜇2 Alternative Hypothesis, 𝐻1 : 𝜇1 > 𝜇2

Level of significance, 𝛼 = 0.05 (say) , 𝑧𝛼 (𝜈) = 𝑧0.05 (10) = 1.812

𝑥̅ −𝑦̅ 46−57 −11
Test Statistic: 𝑡 = 1 1
= 1 1
= 6.4585 = −1.703
𝑆.√ + 11.03√ +
𝑛1 𝑛2 5 7

Decision: since |𝑡| = 1.703 < 1.812, we accept the null hypothesis.

Problem 7.3: Two horses A and B were tested according to the time (in seconds) to run a particular
track with the following results. Test whether the two horses have the same running capacity.

Horse A 28 30 32 33 33 29 34

Horse B 29 30 30 24 27 29

Solution: Calculation of sample means and S.D.s

∑ 𝑥 219
𝑥̅ = = = 31.286
7 7
∑ 𝑦 169
𝑦̅ = = = 28.16
6 6

x ̅
x-𝒙 ̅)𝟐
(𝒙 − 𝒙 y ̅
𝒚−𝒚 ̅)𝟐
(𝒚 − 𝒚

28 -3.286 10.8 29 0.84 0.7056

30 -1.286 1.6538 30 1.84 3.3856

32 0.714 0.51 30 1.84 3.3856

33 1.714 2.94 24 -4.16 17.3056

33 1.714 2.94 27 -1.16 1.3456

29 -2.286 5.226 29 0.84 0.7056

34 2.714 7.366

219 31.4358 169 26.8336

∑(𝑥−𝑥̅ )2 +∑(𝑦−𝑦̅)2 31.4358+26.8336 58.2694

𝑆2 = 𝑛1 +𝑛2 −2
= 7+6−2
= 11
= 5.23 ⇒ 𝑆 = 2.3, 𝜈 = 7 + 6 − 2 = 11

www.Jntufastupdates.com 12
Null Hypothesis 𝐻0 : 𝜇1 = 𝜇2

Alternative Hypothesis 𝐻1 : 𝜇1 ≠ 𝜇2

Level of significance, 𝛼 = 0.05 (say) 𝑧𝛼 (𝜈) = 𝑧0.025 (11) = 2.201

2

𝑥̅ −𝑦̅ 31.286−28.16
Test Statistic: 𝑡 = 1 1
= 1 1
= 2.443
𝑆.√ + 2.3√ +
𝑛1 𝑛2 7 6

Decision: Since |𝑡| = 2.443 > 2.201, we reject the null Hypothesis at 5% Level of Significance.

➢ Modal 9: Test Significance for variances

If 𝑠12 and 𝑠22 are the variances of two samples of sizes 𝑛1 and 𝑛2 respectively, then the population
variances are given by 𝑛1 𝑠12 = (𝑛1 − 1)𝑆12 and 𝑛2 𝑠22 = (𝑛2 − 1)𝑆22 .

The quantities 𝜈1 = 𝑛1 − 1 and 𝜈2 = 𝑛2 − 1 are called degrees of freedom of these estimates.

𝑆2 𝑆22
The test statistic is 𝐹 = 𝑆12 𝑂𝑅 𝑆12
according as 𝑆12 > 𝑆22 or 𝑆22 > 𝑆12 follows F-distribution with
2
degree of freedom (𝑛1 − 1, 𝑛2 − 1).

We take the greater of the two variances in the numerator and the other in denominator. When F is
close to one then the two variances are nearly same.

Conclusion: If the test statistic value F > critical value from F table then we reject the null Hypothesis.

Problem 9.1: It is known that the mean diameters of rivets produced by two firms A and B are
practically the same, but the standard deviations may differ. For 22 rivets produced by firm A, the
S.D. is 2.9 mm, while for 16 rivets manufactured by firm B, the S.D. is 3.8 mm. Compute the statistic
you would use to test whether the products of firm A have the same variability as those of firm B
and test its significance.

Solution: Given 𝑛1 = 22, 𝑛2 = 16, 𝑠1 = 2.9 and 𝑠2 = 3.8

𝑛 𝑠2 185.02 𝑛 𝑠2 231.04
⇒ 𝑆12 = 𝑛 1−1
1
= 21
= 8.81 and 𝑆22 = 𝑛 2−1
2
= 15
= 15.40
1 2

Null Hypothesis 𝐻0 : 𝜎12 = 𝜎22

Alternative Hypothesis 𝐻1 : 𝜎12 ≠ 𝜎22

Level of significance 𝛼 = 0.05 (say) then 𝐹𝛼 (𝜈2 , 𝜈1 ) = 𝐹0.05 (15,21) = 2.33

𝑆22
Test statistic : 𝐹 = since 𝑆22 > 𝑆12
𝑆12

15.40
= 8.81
= 1.74

Decision: Since Test statistic value 𝐹 = 1.74 < 𝐹𝛼 = 2.33 we accept the null Hypothesis.

Problem 9.2: The time taken by workers in performing a job by method I and method II is given
below. Do the data show that the variances of time distribution from population from which these
sample are drawn do not differ significantly ?

www.Jntufastupdates.com 13
 Method I 20 16 26 27 23 22 -

Method 27 33 42 35 32 34 38
II

Solution: Given 𝑛1 = 6, 𝑛2 = 7
∑ 𝑥 134 ∑ 𝑦 241
𝑥̅ = = = 22.3 𝑦̅ = = = 34.4
𝑛1 6 𝑛2 7

x ̅
𝒙−𝒙 ̅)𝟐
(𝒙 − 𝒙 y ̅
𝒚−𝒚 ̅)𝟐
(𝒚 − 𝒚

20 -2.3 5.29 27 -7.4 54.76

16 -6.3 39.69 33 -1.4 1.96

26 3.7 13.69 42 7.6 57.76

27 4.7 22.09 35 0.6 0.36

23 0.7 0.49 32 -2.4 5.76

22 -0.3 0.09 34 -0.4 0.16

38 3.6 12.96

134 81.34 241 133.72

∑(𝑥 − 𝑥̅ )2 81.34 ∑(𝑦 − 𝑦̅)2 133.72

𝑆12 = = = 16.26 𝑆22 = = = 22.29
𝑛1 − 1 5 𝑛2 − 1 6

Null Hypothesis 𝐻0 : 𝜎12 = 𝜎22

Alternative Hypothesis 𝐻1 : 𝜎12 ≠ 𝜎22

Level of significance 𝛼 = 0.05 (say) then 𝐹𝛼 (𝜈2 , 𝜈1 ) = 𝐹0.05 (6,5) = 4.39

𝑆2
Test statistic : 𝐹 = 𝑆22 since 𝑆22 > 𝑆12
1

22.29
= 16.26
= 1.37

Decision: Since Test statistic value 𝐹 = 1.37 < 𝐹𝛼 = 4.39 we accept the null Hypothesis.

Modal 10: Test of Significance for Goodness of fit

www.Jntufastupdates.com 14
This test is used to decide whether the discrepancy between theory and experiment is significant or
not.

Let 𝑂1 , 𝑂2 , … 𝑂𝑛 be a set of observed frequencies and 𝐸1 , 𝐸2 , … 𝐸𝑛 are the corresponding set of

expected frequencies.
(𝑂𝑖 −𝐸𝑖 )2
The test statistic is 𝜒 2 = ∑ [ 𝐸𝑖
]

If the calculated value of 𝜒 2 > tabulated value of 𝜒 2 [at 𝛼 level in 𝜒 2 distribution with (𝑛 − 1)
degree of freedom] then 𝐻0 is rejected [otherwise we accept].

Problem 10.1 : Four coins were tossed 160 times and the 0, 1, 2, 3 and 4 results were obtained 17,
52, 54, 31 and 6 times. Under the assumption that coins are balanced, find the expected frequencies
of 0, 1, 2, 3 or 4 heads, and test the goodness of fit at level of significance 0.05.

Solution: Given N = 160, n = 4

p = P(getting head in one trial) = 0.5 , q = 1 – p = 0.5

No. of Heads 0 1 2 3 4

Observed frq.( O 17 52 54 31 6
)

Expected frq. (E) 𝟏𝟔𝟎 × 𝟒𝑪𝟎 𝟏𝟔𝟎 𝟏𝟔𝟎 𝟏𝟔𝟎 × 𝟒𝑪𝟑 𝟏𝟔𝟎 × 𝟒𝑪𝟒
= 𝟏𝟎 × 𝟒𝑪𝟏 × 𝟒𝑪𝟐 = 𝟒𝟎 = 𝟏𝟎
= 𝟒𝟎 = 𝟔𝟎

𝑶−𝑬 7 12 -6 -9 -4

(𝑶 − 𝑬)𝟐 4.9 3.6 0.6 2.025 1.6

𝑬

(𝑶 − 𝑬)𝟐
𝜒2 = ∑ [ ] = 12.725
𝑬

Null Hypothesis 𝐻0 : Coins are biased

Alternative Hypothesis 𝐻1 : Coins are unbiased

2 (4)
Level of significance: 𝛼 = 0.05, 𝜒𝛼2 (𝜈) = 𝜒0.05 = 9.488
(𝑂𝑖 −𝐸𝑖 )2
Test statistic: 𝜒 2 = ∑ [ 𝐸𝑖
] = 12.725

2 (4),
Decision: Since 𝜒 2 > 𝜒0.05 Null hypothesis is rejected.

Problem 10.2: A sample analysis of examination results of 500 students was made. It was found that
220 students had failed, 170 had secured a third class, 90 were placed in second class and 20 got a
first class. Do these figures commensurate with the general examination result which is in the ratio
of 4 : 3 : 2 : 1 for the various categories respectively.

www.Jntufastupdates.com 15
Solution: Given observed results of 500 students, who secured fail, third class, second class and first
class result are 220, 170, 90, 20.

Given expected result are in the ration 4 : 3 : 2 : 1.

4 3 2 1
Hence 10 ∗ 500, 10 ∗ 500, 10 ∗ 500 and 10 ∗ 500 i.e., 200, 150, 100 and 50 are expected result
secured by 500 students.

Result fail third second First

Observed ( O ) 220 170 90 20

Expected (E) 200 150 100 50

(𝑶 − 𝑬) 20 20 - 10 - 30

(𝑶 − 𝑬)𝟐 2 2.67 1 18
𝑬

Null Hypothesis 𝐻0 : The observed result commensurate with the general exam result.

Alternative Hypothesis 𝐻1 : The observed result commensurate with the general exam result.
2 (3)
Level of significance: 𝛼 = 0.05 (𝑠𝑎𝑦), 𝜒𝛼2 (𝜈) = 𝜒0.05 = 7.815
(𝑂𝑖 −𝐸𝑖 )2
Test statistic: 𝜒 2 = ∑ [ ] = 23.67
𝐸𝑖

2 (4),
Decision: Since 𝜒 2 > 𝜒0.05 Null hypothesis is rejected.

www.Jntufastupdates.com 16