Applied Statistics

Dr. V. Raja
Assistant Professor
Vellore Institute of Technology

Andhra Pradesh

March 11, 2025

.

Module 4
Inference for Decision Making-I

Applied Statistics (MAT1011) Dr. V. Raja 2 / 45

Hypothesis

Definition
A statistical hypothesis is an assertion or conjecture concerning one or
more populations.

where population is the complete collection of all the elements to be

studied and sample is a sub collection of elements drawn from a
population.

Applied Statistics (MAT1011) Dr. V. Raja 3 / 45

Hypothesis

Procedure for testing the Hypothesis:

1) To set the hypothesis.
2) To set the suitable significant level.
3) To set the test criteria.
4) Computation.
5) Decision.

Applied Statistics (MAT1011) Dr. V. Raja 4 / 45

Hypothesis

1) To set the hypothesis.

a) Null Hypothesis
For example. µ = 5, p = 0.8, χ2 = 0.5
b) Alternative Hypothesis
Types:
(i) One-tail test (left) For eg. µ < 5,
(ii) One-tail test (right) For eg. p > 0.8,
(iii) Two tail test For eg. χ2 6= 0.5

Applied Statistics (MAT1011) Dr. V. Raja 5 / 45

Hypothesis

2) To set the suitable significant level (denoted by α).

Usually α = 1%, 5%, 10%.
The value of x lies in the region where P(X < x) = α is rejected
(For One-tail test[left])
3) To set the test criteria. (Varies problem to problem)
4) Computation. (Varies problem to problem)
5) Decision.
(i) Reject the Null Hypothesis in favor of Alternative Hypothesis, because
of sufficient evidence in the data.
(ii) Fail to reject the Null Hypothesis, because of insufficient evidence in
the data.

Applied Statistics (MAT1011) Dr. V. Raja 6 / 45

Test of Hypothesis for Single Proportion

Definition
The problem of testing the hypothesis that the proportion of successes in a
binomial experiment equals some specified value. That is, we are testing
the null hypothesis H0 that p = p0 , where p is the parameter of the
binomial distribution. The alternative hypothesis may be one of the usual
one-sided or two-sided alternatives:

p < p0 , p > p0 , or p 6= p0 .

Applied Statistics (MAT1011) Dr. V. Raja 7 / 45

Test of Hypothesis for Single Proportion

1) To set the hypothesis.

H0 : p = p0 ,
(i) H1 : p < p0
(ii) H1 : p > p0
(iii) H1 : p 6= p0
where p is the parameter of the binomial distribution (probability of
success).
2) To set the suitable significant level.
α = 1%, 5%, 10%.

Applied Statistics (MAT1011) Dr. V. Raja 8 / 45

Test of Hypothesis for Single Proportion

3) To set the test criteria and 5) Decision.

For p = p0 ,
(i) If P = P(X ≤ x) ≤ α, reject H0 ,
(ii) If P = P(X ≥ x) ≤ α, reject H0 ,
(iii)
(a) If x < n × p0 and P = 2P(X ≤ x) ≤ α, reject H0 ,
(b) If x > n × p0 and P = 2P(X ≥ x) ≤ α, reject H0 ,
4) Computation.
Use P(X = x) = nCx px q n−x or Table A.1, if n is small.
x −µ x − np0
Otherwise, Convert z = = √
σ np0 q0

Applied Statistics (MAT1011) Dr. V. Raja 9 / 45

Test of Hypothesis for Single Proportion

Example. A builder claims that heat pumps are installed in 70% of all
homes being constructed today in the city of Mysuru. Would you agree
with this claim if a random survey of new homes in this city showed that 8
out of 15 had heat pumps installed? Use a 10% level of significance.
Solution. H0 : p = 0.7,
H1 : p 6= 0.7
α = 10% = 0.10
n = 15, x = 8
Since n × p0 = 15 × 0.7 = 10.5, x = 8 < 10.5,
Compute 2P(X ≤ 8) = 2 × 0.1311 = 0.2611
And α = 0.10 < 0.2611 = P-value.
Since there is insufficient evidence in the data, we fail to reject the
builder’s claim.
Applied Statistics (MAT1011) Dr. V. Raja 10 / 45
Test of Hypothesis for Single Proportion

A commonly prescribed drug for relieving nervous tension is believed to be

only 60% effective. Experimental results with a new drug administered to
a random sample of 100 adults who were suffering from nervous tension
show that 70 received relief. Is this sufficient evidence to conclude that the
new drug is superior to the one commonly prescribed? Use a 0.05 level of
significance.
Solution. H0 : p = 0.6,
H1 : p > 0.6
α = 5% = 0.05
n = 100, x = 70
x − np0 70 − 100 × 0.6
Since n is too large, z = √ =√ = 2.04,
np0 q0 100 × 0.6 × 0.4
Compute P(Z > 2.04) = 1 − P(Z < 2.04) = 1 − 0.9793 = 0.0207
And α = 0.05 > 0.0207 = P-value.
Applied Statistics (MAT1011) Dr. V. Raja 11 / 45
Test of Hypothesis for Single Proportion

Since there is sufficient evidence in the data, we reject the claim that the
new drug is not superior to the one commonly prescribed. That is, the
new drug is superior to the one commonly prescribed.

Applied Statistics (MAT1011) Dr. V. Raja 12 / 45

Test of Hypothesis for Two Proportions

1) To set the hypothesis.

H0 : p1 = p2 ,
(i) H1 : p1 < p2
(ii) H1 : p1 > p2
(iii) H1 : p1 6= p2
where p1 and p2 are proportion of two samples.
2) To set the suitable significant level.
α = 1%, 5%, 10%.

Applied Statistics (MAT1011) Dr. V. Raja 13 / 45

Test of Hypothesis for Two Proportions

4) Computation.
pˆ1 − pˆ2
Convert z = r   where
1 1
p̂q̂ +
n1 n2
x1 x2 x1 + x2
pˆ1 = , pˆ2 = , p̂ = , q̂ = 1 − p̂
n1 n2 n1 + n2
3) To set the test criteria and 5) Decision.
(i) For H1 : p1 < p2 , if P = P(Z ≤ z) ≤ α, reject H0 ,
(ii) For H1 : p1 > p2 , if P = P(Z ≥ z) ≤ α, reject H0 ,
(iii) For H1 : p1 6= p2 , if P = 2P(Z ≥ |z|) ≤ α, reject H0 ,

Applied Statistics (MAT1011) Dr. V. Raja 14 / 45

Test of Hypothesis for Two Proportions

Example. A vote is to be taken among the residents of a town and the

surrounding county to determine whether a proposed chemical plant
should be constructed. The construction site is within the town limits, and
for this reason many voters in the county believe that the proposal will
pass because of the large proportion of town voters who favor the
construction. To determine if there is a significant difference in the
proportions of town voters and county voters favoring the proposal, a poll
is taken. If 120 of 200 town voters favor the proposal and 240 of 500
county residents favor it, would you agree that the proportion of town
voters favoring the proposal is higher than the proportion of county
voters? Use an 0.05 level of significance.
Solution. x1 = 120, n1 = 200, x2 = 240, n2 = 500, α = 0.05.
Question: Is p1 > p2 ?
Applied Statistics (MAT1011) Dr. V. Raja 15 / 45
Test of Hypothesis for Two Proportions

H0 : p1 = p2 ,
H1 : p1 > p2
x1 120 x2 240
pˆ1 = = = 0.60, pˆ2 = = = 0.48,
n1 200 n2 500
x1 + x2 120 + 240
p̂ = = = 0.51, q̂ = 1 − p̂ = 1 − 0.51 = 0.49
n1 + n2 200 + 500
pˆ1 − pˆ2 0.6 − 0.48
z=r   = r   = 2.9
1 1 1 1
p̂q̂ n1 + n2 (0.51 × 0.49) 200 + 500
P(Z > 2.9) = 0.0019
Conclusion: Reject H0 in favor of H1 . That is, we agree that the
proportion of town voters favoring the proposal is higher than the
proportion of county voters.

Applied Statistics (MAT1011) Dr. V. Raja 16 / 45

Test of Hypothesis for Two Proportions

Example. In a study to estimate the proportion of residents in a certain

city and its suburbs who favor the construction of a nuclear power plant, it
is found that 63 of 100 urban residents favor the construction while only
59 of 125 suburban residents are in favor. Is there a significant difference
between the proportions of urban and suburban residents who favor
construction of the nuclear plant? Make use of a P-value.
Solution. H0 : p1 = p2 ,
H1 : p1 6= p2
x1 63 x2 59
pˆ1 = = = 0.63, pˆ2 = = = 0.472,
n1 100 n2 125
x1 + x2 63 + 59
p̂ = = = 0.54, q̂ = 1 − p̂ = 1 − 0.54 = 0.46
n1 + n2 100 + 125
pˆ1 − pˆ2 0.63 − 0.472
z=r   = r   = 2.37
p̂q̂ n11 + n12 (0.54 × 0.44) 100 1 1
+ 125
Applied Statistics (MAT1011) Dr. V. Raja 17 / 45
Test of Hypothesis for Two Proportions

2P(Z > |2.37|) = 0.0019 =⇒ P = 0.0178

Conclusion: At 1.79% level of significance, we would reject H0 in favor of
H1 . That is, at 1.79% level of significance, we can say that the proportion
of urban residents who favor construction of the nuclear plant is not equal
to the proportion of suburban residents. Therefore 1.79% is the significant
difference between the proportion of urban and suburban residents who
favor construction of the nuclear plant.

Applied Statistics (MAT1011) Dr. V. Raja 18 / 45

Test of Hypothesis for Two Proportions

Example. An urban community would like to show that the incidence of

breast cancer is higher in their area than in a nearby rural area. (PCB
levels were found to be higher in the soil of the urban community.) If it is
found that 20 of 200 adult women in the urban community have breast
cancer and 10 of 150 adult women in the rural community have breast
cancer, can we conclude at the 0.05 level of significance that breast cancer
is more prevalent in the urban community?

Applied Statistics (MAT1011) Dr. V. Raja 19 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)

1) To set the hypothesis.

H0 : µ = µ0 ,
(i) H1 : µ < µ0
(ii) H1 : µ > µ0
(iii) H1 : µ 6= µ0
where µ is the mean of the population.
2) To set the suitable significant level.
α = 1%, 5%, 10%.

Applied Statistics (MAT1011) Dr. V. Raja 20 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)

4) Computation.

Applied Statistics (MAT1011) Dr. V. Raja 21 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)

4) Computation.
x −µ
Find z = σ √
/ n
where x is the mean of the sample, n is the size of the sample and σ is the
variance of the population.

Applied Statistics (MAT1011) Dr. V. Raja 21 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)

4) Computation.
x −µ
Find z = σ √
/ n
where x is the mean of the sample, n is the size of the sample and σ is the
variance of the population.
3) To set the test criteria and 5) Decision.
For µ = µ0 ,
(i) For µ < µ0 , if P = P(Z ≤ z) ≤ α, reject H0 ,
(ii) For µ > µ0 , if P = P(Z ≥ z) ≤ α, reject H0 ,
(iii) For µ 6= µ0 , if P = 2P(Z ≥ |z|) ≤ α, reject H0 ,

Applied Statistics (MAT1011) Dr. V. Raja 21 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)

Example. A manufacturer of sports equipment has developed a new

synthetic fishing line that the company claims has a mean breaking
strength of 8 kilograms with a standard deviation of 0.5 kilogram. Test the
hypothesis that µ = 8 kilograms against the alternative that µ 6= 8
kilograms if a random sample of 50 lines is tested and found to have a
mean breaking strength of 7.8 kilograms. Use a 0.01 level of significance.

Applied Statistics (MAT1011) Dr. V. Raja 22 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)

Example. A manufacturer of sports equipment has developed a new

synthetic fishing line that the company claims has a mean breaking
strength of 8 kilograms with a standard deviation of 0.5 kilogram. Test the
hypothesis that µ = 8 kilograms against the alternative that µ 6= 8
kilograms if a random sample of 50 lines is tested and found to have a
mean breaking strength of 7.8 kilograms. Use a 0.01 level of significance.
Solution. x = 7.8, n = 50, σ = 0.5,

Applied Statistics (MAT1011) Dr. V. Raja 22 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)

Example. A manufacturer of sports equipment has developed a new

synthetic fishing line that the company claims has a mean breaking
strength of 8 kilograms with a standard deviation of 0.5 kilogram. Test the
hypothesis that µ = 8 kilograms against the alternative that µ 6= 8
kilograms if a random sample of 50 lines is tested and found to have a
mean breaking strength of 7.8 kilograms. Use a 0.01 level of significance.
Solution. x = 7.8, n = 50, σ = 0.5,
H0 : µ = 8,

Applied Statistics (MAT1011) Dr. V. Raja 22 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)

Example. A manufacturer of sports equipment has developed a new

synthetic fishing line that the company claims has a mean breaking
strength of 8 kilograms with a standard deviation of 0.5 kilogram. Test the
hypothesis that µ = 8 kilograms against the alternative that µ 6= 8
kilograms if a random sample of 50 lines is tested and found to have a
mean breaking strength of 7.8 kilograms. Use a 0.01 level of significance.
Solution. x = 7.8, n = 50, σ = 0.5,
H0 : µ = 8,
H1 : µ 6= 8
x −µ
z= σ√
/ n

Applied Statistics (MAT1011) Dr. V. Raja 22 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)

Example. A manufacturer of sports equipment has developed a new

synthetic fishing line that the company claims has a mean breaking
strength of 8 kilograms with a standard deviation of 0.5 kilogram. Test the
hypothesis that µ = 8 kilograms against the alternative that µ 6= 8
kilograms if a random sample of 50 lines is tested and found to have a
mean breaking strength of 7.8 kilograms. Use a 0.01 level of significance.
Solution. x = 7.8, n = 50, σ = 0.5,
H0 : µ = 8,
H1 : µ 6= 8
x −µ 7.8 − 8
z = σ √ = 0.5 √ = −2.83
/ n / 50
2P(Z ≥ | − 2.83|) = 2 × 0.0023 = 0.0046 ≤ 0.01 = α

Applied Statistics (MAT1011) Dr. V. Raja 22 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)

Conclusion: Reject H0 in favor of H1 . That is, the average breaking

strength is not equal to 8.

Applied Statistics (MAT1011) Dr. V. Raja 23 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Known; z-test)
Example. A random sample of 100 recorded deaths in the United States
during the past year showed an average life span of 71.8 years. Assuming a
population standard deviation of 8.9 years, does this seem to indicate that
the mean life span today is greater than 70 years? Use a 0.05 level of
significance.
Solution. x = 71.8, n = 100, σ = 8.9,
H0 : µ = 70,
H1 : µ > 70
x −µ 71.8 − 70
z = σ √ = 8.9 √ = 2.02
/ n / 100
P(Z ≥ 2.02) = 0.0217 ≤ 0.05 = α
Conclusion: Reject H0 in favor of H1 . That is, this seem to indicate that
the mean life span today is greater than 70 years.
Applied Statistics (MAT1011) Dr. V. Raja 24 / 45
Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

1) To set the hypothesis.

Applied Statistics (MAT1011) Dr. V. Raja 25 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

1) To set the hypothesis.

H0 : µ = µ0 ,

Applied Statistics (MAT1011) Dr. V. Raja 25 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

1) To set the hypothesis.

H0 : µ = µ0 ,
(i) H1 : µ < µ0

Applied Statistics (MAT1011) Dr. V. Raja 25 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

1) To set the hypothesis.

H0 : µ = µ0 ,
(i) H1 : µ < µ0
(ii) H1 : µ > µ0

Applied Statistics (MAT1011) Dr. V. Raja 25 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

1) To set the hypothesis.

H0 : µ = µ0 ,
(i) H1 : µ < µ0
(ii) H1 : µ > µ0
(iii) H1 : µ 6= µ0

Applied Statistics (MAT1011) Dr. V. Raja 25 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

1) To set the hypothesis.

H0 : µ = µ0 ,
(i) H1 : µ < µ0
(ii) H1 : µ > µ0
(iii) H1 : µ 6= µ0
where µ is the mean of the population.

Applied Statistics (MAT1011) Dr. V. Raja 25 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

1) To set the hypothesis.

H0 : µ = µ0 ,
(i) H1 : µ < µ0
(ii) H1 : µ > µ0
(iii) H1 : µ 6= µ0
where µ is the mean of the population.
2) To set the suitable significant level.

Applied Statistics (MAT1011) Dr. V. Raja 25 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

1) To set the hypothesis.

H0 : µ = µ0 ,
(i) H1 : µ < µ0
(ii) H1 : µ > µ0
(iii) H1 : µ 6= µ0
where µ is the mean of the population.
2) To set the suitable significant level.
α = 1%, 5%, 10%.

Applied Statistics (MAT1011) Dr. V. Raja 25 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

4) Computation.

Applied Statistics (MAT1011) Dr. V. Raja 26 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

4) Computation.
x −µ
Find t = s √
/ n

Applied Statistics (MAT1011) Dr. V. Raja 26 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

4) Computation.
x −µ
Find t = s √
/ n
where x is the mean of the sample, n is the size of the sample and s is the
variance of the sample.

Applied Statistics (MAT1011) Dr. V. Raja 26 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

4) Computation.
x −µ
Find t = s √
/ n
where x is the mean of the sample, n is the size of the sample and s is the
variance of the sample.
3) To set the test criteria and 5) Decision.

Applied Statistics (MAT1011) Dr. V. Raja 26 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

4) Computation.
x −µ
Find t = s √
/ n
where x is the mean of the sample, n is the size of the sample and s is the
variance of the sample.
3) To set the test criteria and 5) Decision.
For µ = µ0 ,

Applied Statistics (MAT1011) Dr. V. Raja 26 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

4) Computation.
x −µ
Find t = s √
/ n
where x is the mean of the sample, n is the size of the sample and s is the
variance of the sample.
3) To set the test criteria and 5) Decision.
For µ = µ0 ,
(i) For µ < µ0 , if P = P(T ≤ t) ≤ α, reject H0 ,

Applied Statistics (MAT1011) Dr. V. Raja 26 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

4) Computation.
x −µ
Find t = s √
/ n
where x is the mean of the sample, n is the size of the sample and s is the
variance of the sample.
3) To set the test criteria and 5) Decision.
For µ = µ0 ,
(i) For µ < µ0 , if P = P(T ≤ t) ≤ α, reject H0 ,
(ii) For µ > µ0 , if P = P(T ≥ t) ≤ α, reject H0 ,

Applied Statistics (MAT1011) Dr. V. Raja 26 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

4) Computation.
x −µ
Find t = s √
/ n
where x is the mean of the sample, n is the size of the sample and s is the
variance of the sample.
3) To set the test criteria and 5) Decision.
For µ = µ0 ,
(i) For µ < µ0 , if P = P(T ≤ t) ≤ α, reject H0 ,
(ii) For µ > µ0 , if P = P(T ≥ t) ≤ α, reject H0 ,
(iii) For µ 6= µ0 , if P = 2P(T ≥ |t|) ≤ α, reject H0 ,

Applied Statistics (MAT1011) Dr. V. Raja 26 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

If P(T ≥ t) = α for the sample size n, then t = tα,n−1 .

Applied Statistics (MAT1011) Dr. V. Raja 27 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

If P(T ≥ t) = α for the sample size n, then t = tα,n−1 .

So if t > tα,n−1 , reject H0 .

Applied Statistics (MAT1011) Dr. V. Raja 27 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

If P(T ≥ t) = α for the sample size n, then t = tα,n−1 .

So if t > tα,n−1 , reject H0 .
If P(T ≤ t) = α for the sample size n, then t = −tα,n−1 .

Applied Statistics (MAT1011) Dr. V. Raja 27 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

If P(T ≥ t) = α for the sample size n, then t = tα,n−1 .

So if t > tα,n−1 , reject H0 .
If P(T ≤ t) = α for the sample size n, then t = −tα,n−1 .
So if t < −tα,n−1 , reject H0 .

Applied Statistics (MAT1011) Dr. V. Raja 27 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

If P(T ≥ t) = α for the sample size n, then t = tα,n−1 .

So if t > tα,n−1 , reject H0 .
If P(T ≤ t) = α for the sample size n, then t = −tα,n−1 .
So if t < −tα,n−1 , reject H0 .
If 2P(T ≥ |t|) = α for the sample size n, then t = tα/2,n−1 .

Applied Statistics (MAT1011) Dr. V. Raja 27 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

If P(T ≥ t) = α for the sample size n, then t = tα,n−1 .

So if t > tα,n−1 , reject H0 .
If P(T ≤ t) = α for the sample size n, then t = −tα,n−1 .
So if t < −tα,n−1 , reject H0 .
If 2P(T ≥ |t|) = α for the sample size n, then t = tα/2,n−1 .
So if |t| > tα/2,n−1 , reject H0 .

Applied Statistics (MAT1011) Dr. V. Raja 27 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

Example. The Edison Electric Institute has published figures on the

number of kilowatt hours used annually by various home appliances. It is
claimed that a vacuum cleaner uses an average of 46 kilowatt hours per
year. If a random sample of 12 homes included in a planned study
indicates that vacuum cleaners use an average of 42 kilowatt hours per
year with a standard deviation of 11.9 kilowatt hours, does this suggest at
the 0.05 level of significance that vacuum cleaners use, on average, less
than 46 kilowatt hours annually? Assume the population of kilowatt hours
to be normal.

Applied Statistics (MAT1011) Dr. V. Raja 28 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

Example. The Edison Electric Institute has published figures on the

number of kilowatt hours used annually by various home appliances. It is
claimed that a vacuum cleaner uses an average of 46 kilowatt hours per
year. If a random sample of 12 homes included in a planned study
indicates that vacuum cleaners use an average of 42 kilowatt hours per
year with a standard deviation of 11.9 kilowatt hours, does this suggest at
the 0.05 level of significance that vacuum cleaners use, on average, less
than 46 kilowatt hours annually? Assume the population of kilowatt hours
to be normal.
Solution. µ = 46, x = 42, s = 11.9, n = 12, α = 0.05

Applied Statistics (MAT1011) Dr. V. Raja 28 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

H0 : µ = 46,

Applied Statistics (MAT1011) Dr. V. Raja 29 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

H0 : µ = 46,
H1 : µ < 46

Applied Statistics (MAT1011) Dr. V. Raja 29 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

H0 : µ = 46,
H1 : µ < 46
t0.05,11 = 1.796

Applied Statistics (MAT1011) Dr. V. Raja 29 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

H0 : µ = 46,
H1 : µ < 46
t0.05,11 = 1.796
Critical region: t < −1.796

Applied Statistics (MAT1011) Dr. V. Raja 29 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

H0 : µ = 46,
H1 : µ < 46
t0.05,11 = 1.796
Critical region: t < −1.796
x −µ
t= s√
/ n

Applied Statistics (MAT1011) Dr. V. Raja 29 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

H0 : µ = 46,
H1 : µ < 46
t0.05,11 = 1.796
Critical region: t < −1.796
x −µ 42 − 46
t = s √ = 11.9 √
/ n / 12

Applied Statistics (MAT1011) Dr. V. Raja 29 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

H0 : µ = 46,
H1 : µ < 46
t0.05,11 = 1.796
Critical region: t < −1.796
x −µ 42 − 46
t = s √ = 11.9 √ = −1.16
/ n / 12

Applied Statistics (MAT1011) Dr. V. Raja 29 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

H0 : µ = 46,
H1 : µ < 46
t0.05,11 = 1.796
Critical region: t < −1.796
x −µ 42 − 46
t = s √ = 11.9 √ = −1.16
/ n / 12
Conclusion: Since −1.16 > −1.796, we failed to reject H0 in favor of H1 .

Applied Statistics (MAT1011) Dr. V. Raja 29 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

H0 : µ = 46,
H1 : µ < 46
t0.05,11 = 1.796
Critical region: t < −1.796
x −µ 42 − 46
t = s √ = 11.9 √ = −1.16
/ n / 12
Conclusion: Since −1.16 > −1.796, we failed to reject H0 in favor of H1 .
That is, due to insufficient evidence in the data, we cannot conclude that
the average number of kilowatt hours used annually by home vacuum
cleaners is less than 46 at 0.05 level of significance.

Applied Statistics (MAT1011) Dr. V. Raja 29 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

Example. A theatre owner claimed that a large bag will contain 120
grams of popcorn. A random sample of 24 large bags of popcorn weighed,
on average, 118 grams with a standard deviation of 20 grams. Based on
the samples, can we conclude the claim of the theatre owner at 0.015 level
of significance.

Applied Statistics (MAT1011) Dr. V. Raja 30 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

Example. A theatre owner claimed that a large bag will contain 120
grams of popcorn. A random sample of 24 large bags of popcorn weighed,
on average, 118 grams with a standard deviation of 20 grams. Based on
the samples, can we conclude the claim of the theatre owner at 0.015 level
of significance.
Solution. µ = 120, x = 118, s = 20, n = 24, α = 0.015

Applied Statistics (MAT1011) Dr. V. Raja 30 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

Example. A theatre owner claimed that a large bag will contain 120
grams of popcorn. A random sample of 24 large bags of popcorn weighed,
on average, 118 grams with a standard deviation of 20 grams. Based on
the samples, can we conclude the claim of the theatre owner at 0.015 level
of significance.
Solution. µ = 120, x = 118, s = 20, n = 24, α = 0.015
H0 : µ = 120,

Applied Statistics (MAT1011) Dr. V. Raja 30 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

Example. A theatre owner claimed that a large bag will contain 120
grams of popcorn. A random sample of 24 large bags of popcorn weighed,
on average, 118 grams with a standard deviation of 20 grams. Based on
the samples, can we conclude the claim of the theatre owner at 0.015 level
of significance.
Solution. µ = 120, x = 118, s = 20, n = 24, α = 0.015
H0 : µ = 120,
H1 : µ 6= 120

Applied Statistics (MAT1011) Dr. V. Raja 30 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

Example. A theatre owner claimed that a large bag will contain 120
grams of popcorn. A random sample of 24 large bags of popcorn weighed,
on average, 118 grams with a standard deviation of 20 grams. Based on
the samples, can we conclude the claim of the theatre owner at 0.015 level
of significance.
Solution. µ = 120, x = 118, s = 20, n = 24, α = 0.015
H0 : µ = 120,
H1 : µ 6= 120
t0.0075,23 = 2.629

Applied Statistics (MAT1011) Dr. V. Raja 30 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

Example. A theatre owner claimed that a large bag will contain 120
grams of popcorn. A random sample of 24 large bags of popcorn weighed,
on average, 118 grams with a standard deviation of 20 grams. Based on
the samples, can we conclude the claim of the theatre owner at 0.015 level
of significance.
Solution. µ = 120, x = 118, s = 20, n = 24, α = 0.015
H0 : µ = 120,
H1 : µ 6= 120
t0.0075,23 = 2.629
Critical region: |t| > 2.629

Applied Statistics (MAT1011) Dr. V. Raja 30 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

x −µ
t= s/√n

Applied Statistics (MAT1011) Dr. V. Raja 31 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

x −µ 118 − 120
t= √
s/ n
= √
20/ 24

Applied Statistics (MAT1011) Dr. V. Raja 31 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

x −µ 118 − 120
t= √
s/ n
= √
20/ 24
= −0.4898

Applied Statistics (MAT1011) Dr. V. Raja 31 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

x −µ 118 − 120
t= √
s/ n
= √
20/ 24
= −0.4898
Conclusion: Since | − 0.4899| < 2.629, we failed to reject H0 in favor of
H1 .

Applied Statistics (MAT1011) Dr. V. Raja 31 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

x −µ 118 − 120
t= √
s/ n
= √
20/ 24
= −0.4898
Conclusion: Since | − 0.4899| < 2.629, we failed to reject H0 in favor of
H1 . That is, due to insufficient evidence in the data, we cannot conclude
that the large bag will not contain 120 grams of popcorn at 0.015 level of
significance.

Applied Statistics (MAT1011) Dr. V. Raja 31 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

Example. The average height of females in the freshman class of a

certain college has historically been 162.5 centimeters. Is there reason to
believe that there has been a change in the average height if a random
sample of 30 females in the present freshman class has an average height
of 165.2 centimeters with a standard deviation of 6.9 centimeters at 0.02?

Applied Statistics (MAT1011) Dr. V. Raja 32 / 45

Test of Hypothesis for a Mean from a Single Sample
(Variance Unknown; t-test)

Example. The average height of females in the freshman class of a

certain college has historically been 162.5 centimeters. Is there reason to
believe that there has been a change in the average height if a random
sample of 30 females in the present freshman class has an average height
of 165.2 centimeters with a standard deviation of 6.9 centimeters at 0.02?
Solution. µ = 162.5, x = 165.2, s = 6.9, n = 30, α = 0.02.

Applied Statistics (MAT1011) Dr. V. Raja 32 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2
(x1 − x2 ) − d0
Z=p 2
σ1/n1 + σ22/n2

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2
(x1 − x2 ) − d0
Z=p 2
σ1/n1 + σ22/n2
where x1 , x2 are the means of the two samples,

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2
(x1 − x2 ) − d0
Z=p 2
σ1/n1 + σ22/n2
where x1 , x2 are the means of the two samples, d0 is the difference of the
means of two populations,

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2
(x1 − x2 ) − d0
Z=p 2
σ1/n1 + σ22/n2
where x1 , x2 are the means of the two samples, d0 is the difference of the
means of two populations, n1 , n2 are the sizes of the two samples

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2
(x1 − x2 ) − d0
Z=p 2
σ1/n1 + σ22/n2
where x1 , x2 are the means of the two samples, d0 is the difference of the
means of two populations, n1 , n2 are the sizes of the two samples and
σ1 , σ2 are the standard deviations of the two populations.

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2
(x1 − x2 ) − d0
Z=p 2
σ1/n1 + σ22/n2
where x1 , x2 are the means of the two samples, d0 is the difference of the
means of two populations, n1 , n2 are the sizes of the two samples and
σ1 , σ2 are the standard deviations of the two populations.
H1 : d0 > 0 or H1 : µ1 > µ2 Critical region: z > zα

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2
(x1 − x2 ) − d0
Z=p 2
σ1/n1 + σ22/n2
where x1 , x2 are the means of the two samples, d0 is the difference of the
means of two populations, n1 , n2 are the sizes of the two samples and
σ1 , σ2 are the standard deviations of the two populations.
H1 : d0 > 0 or H1 : µ1 > µ2 Critical region: z > zα
H1 : d0 < 0 or H1 : µ1 < µ2

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2
(x1 − x2 ) − d0
Z=p 2
σ1/n1 + σ22/n2
where x1 , x2 are the means of the two samples, d0 is the difference of the
means of two populations, n1 , n2 are the sizes of the two samples and
σ1 , σ2 are the standard deviations of the two populations.
H1 : d0 > 0 or H1 : µ1 > µ2 Critical region: z > zα
H1 : d0 < 0 or H1 : µ1 < µ2 Critical region: z < −zα

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2
(x1 − x2 ) − d0
Z=p 2
σ1/n1 + σ22/n2
where x1 , x2 are the means of the two samples, d0 is the difference of the
means of two populations, n1 , n2 are the sizes of the two samples and
σ1 , σ2 are the standard deviations of the two populations.
H1 : d0 > 0 or H1 : µ1 > µ2 Critical region: z > zα
H1 : d0 < 0 or H1 : µ1 < µ2 Critical region: z < −zα
H1 : d0 6= 0 or H1 : µ1 6= µ2 Critical region: |z| > zα/2

Applied Statistics (MAT1011) Dr. V. Raja 33 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

Example. An experiment was performed to compare the abrasive wear of

two different laminated materials. Twelve pieces of material 1 were tested
by exposing each piece to a machine measuring wear. Ten pieces of
material 2 were similarly tested. In each case, the depth of wear was
observed. The samples of material 1 gave an average (coded) wear of 85
units, while the samples of material 2 gave an average of 81. Can we
conclude at the 0.05 level of significance that the average abrasive wear of
material 1 more than that of material 2? Assume the populations to be
approximately normal with a standard deviation of material 1 and material
2 are 4 and 5, respectively.

Applied Statistics (MAT1011) Dr. V. Raja 34 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

H0 : µ1 = µ2 i.e. H0 : d0 = 0
H: µ1 > µ2
α = 0.05
Critical region: z > z0.05 = 1.645
x1 = 85, x2 = 81, d0 = 0, σ1 = 4, σ2 = 5, n1 = 12, n2 = 10.
(85 − 81) − 0
z=p = 2.0430
16/12 + 25/10
Since 2.0430 > z0.05 = 1.645, we reject H0 in favor of H1 . That is, we can
conclude that the average abrasive wear of material 1 is more than that of
material 2 at 0.05 level of significance.

Applied Statistics (MAT1011) Dr. V. Raja 35 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

Example. An experiment was performed to compare the abrasive wear of

two different laminated materials. Twelve pieces of material 1 were tested
by exposing each piece to a machine measuring wear. Ten pieces of
material 2 were similarly tested. In each case, the depth of wear was
observed. The samples of material 1 gave an average (coded) wear of 85
units, while the samples of material 2 gave an average of 81. Can we
conclude at the 0.05 level of significance that the average abrasive wear of
material 1 exceeds that of material 2 by more than 2 units? Assume the
populations to be approximately normal with a standard deviation of
material 1 and material 2 are 4 and 5, respectively.
H0 : µ1 = µ2 + 2 i.e. H0 : d0 = 2
H: µ1 > µ2 + 2
Applied Statistics (MAT1011) Dr. V. Raja 36 / 45
Test of Hypothesis for a Two Means from Two set of
Samples (Variances Known)

α = 0.05
Critical region: z > z0.05 = 1.645
x1 = 85, x2 = 81, d0 = 2, σ1 = 4, σ2 = 5, n1 = 12, n2 = 10.
(85 − 81) − 2
z=p = 1.0215
16/12 + 25/10
Since 1.0215 < z0.05 = 1.645, we failed to reject H0 due to insufficient
evidence in the data. That is, we cannot conclude that the average
abrasive wear of material 1 exceeds that of material 2 by more than 2 units
at 0.05 level of significance.

Applied Statistics (MAT1011) Dr. V. Raja 37 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Unknown, but both are equal; pooled
t-test)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2 s
(x1 − x2 ) − d0 (n1 − 1)s12 + (n2 − 1)s22
t= p ; sp = where x1 , x2 are
sp 1/n1 + 1/n2 n1 + n2 − 2
the means of the two samples, d0 is the difference of the means of two
populations, n1 , n2 are the sizes of the two samples and s1 , s2 are the
standard deviations of the two samples.
H1 : d0 > 0 or H1 : µ1 > µ2 Critical region: t > tα,n1 +n2 −2
H1 : d0 < 0 or H1 : µ1 < µ2 Critical region: t < −tα,n1 +n2 −2
H1 : d0 6= 0 or H1 : µ1 6= µ2 Critical region: |t| > tα/2,n1 +n2 −2

Applied Statistics (MAT1011) Dr. V. Raja 38 / 45

Test of Hypothesis for a Two Means (σ1 = σ2 )

Example. To compare customer satisfaction levels of two competing

cable television companies, 17 customers of Company 1 and 25 customers
of Company 2 were randomly selected and were asked to rate their cable
companies on a five-point scale, with 1 being least satisfied and 5 most
satisfied. The survey results indicated that the Company 1 received the
average score of 3.51 with a standard deviation 0.51, while Company 2
received the average score of 3.24 with a standard deviation 0.52. Test at
the 1% level of significance whether the data provided sufficient evidence
to conclude that Company 1 has a higher mean satisfaction rating than
does Company 2. Use the critical value approach. Assume that the
samples of both populations have equal variances.
Solution. H0 : µ1 = µ2
H1 : µ1 > µ2 or d0 > 0 where d0 = µ1 − µ2 .
Applied Statistics (MAT1011) Dr. V. Raja 39 / 45
Test of Hypothesis for a Two Means (σ1 = σ2 )

x 1 = 3.51, x 2 = 3.24, s1 = 0.51, s2 = 0.52, n1 = 17, n2 = 25

Critical
s
region: t > t0.01,40 = 2.423s
(n1 − 1)s12 + (n2 − 1)s22 16 × 0.512 + 24 × 0.522
sp = = = 0.516
n1 + n2 − 2 17 + 25 − 2
(x1 − x2 ) − d0 (3.51 − 3.24) − 0
t= p = p = 1.6644
1
sp /n1 + /n21 0.516 1/17 + 1/25
Since t < 2.423, we failed to reject H0 . That is, the data provided is
insufficient to conclude that Company 1 has a higher mean satisfaction
rating than does Company 2.

Applied Statistics (MAT1011) Dr. V. Raja 40 / 45

Test of Hypothesis for a Two Means from Two set of
Samples (Variances Unknown and both are unequal)

d 0 = µ1 − µ 2
H0 : d0 = 0, or H0 : µ1 = µ2
(x1 − x2 ) − d0
t= p2
s1/n1 + s22/n2
where x1 , x2 are the means of the two samples, d0 is the difference of the
means of two populations, n1 , n2 are the sizes of the two samples and
s1 , s2 are the standard deviations of the two samples.
H1 : d0 > 0 or H1 : µ1 > µ2 Critical region: t > tα,ν
H1 : d0 < 0 or H1 : µ1 < µ2 Critical region: t < −tα,ν
H1 : d0 6= 0 or H1 : µ1 6= µ2 Critical region: |t| > tα/2,ν
(s12/n1 + s22/n2 )2
where ν = (s /n )2 (s /n )2
2 2

n1 −1 + n2 −1
1 1 2 2

Applied Statistics (MAT1011) Dr. V. Raja 41 / 45

Test of Hypothesis for a Two Means (σ1 6= σ2 )

Example. The following data represent the running times of films

produced by two motion-picture companies:

Test the hypothesis that the average running time of films produced by
company 2 exceeds the average running time of films produced by
company 1 by 10 minutes against the one-sided alternative that the
difference is less than 10 minutes. Use a 0.1 level of significance and
assume the distributions of times to be approximately normal with unequal
variances.
Solution. H0 : µ1 = µ2
H1 : µ1 + 10 < µ2 or d0 < −10 where d0 = µ1 − µ2 .
Applied Statistics (MAT1011) Dr. V. Raja 42 / 45
Test of Hypothesis for a Two Means (σ1 6= σ2 )

n1 = 5, n2 = 7
x 1 = 51 (102 + 86 + 98 + 109 + 92) = 97.4,
x 2 = 71 (81 + 165 + 97 + 134 + 92 + 87 + 114) = 110,
s12 = 15 (102 − 97.4)2 + (86 − 97.4)2 + (98 − 97.4)2 + (109 − 97.4)2 +
(92 − 97.4)2 = 78.8,

s22 = 17 (81 − 110)2 + (165 − 110)2 + (97 − 110)2 + (134 − 110)2 + (92 −
110)2 + (87 − 110)2 + (114 − 110)2 = 913.3

(x1 − x2 ) − d0 (97.4 − 110) − (−10)

t= p2 2
= p = −0.21
s1/n1 + s2/n2 78.8/5 + 913.3/7

(s12/n1 + s22/n2 )2
ν = (s /n )2 (s /n )2
2 2

n1 −1 + n2 −1
1 1 2 2

Since t < 2.423, we failed to reject H0 . That is, the data provided is
insufficient to conclude that Company 1 has a higher mean satisfaction
rating than does Company 2.
Applied Statistics (MAT1011) Dr. V. Raja 43 / 45
Applied Statistics (MAT1011) Dr. V. Raja 44 / 45
Applied Statistics (MAT1011) Dr. V. Raja 45 / 45