1. An important property of fiber is its ability to absorb water.

Thirty (30) randomly

selected pieces of cotton fiber were found to have an average percent absorbency of 20
with a standard deviation of 1.75. On the other hand, 30 pieces of acetate had an average
percent absorbency of 14 and a standard deviation of 1.50.
a) Assuming that the percent absorbency is normally distributed and that the population
variances for the two variances are the same, is there convincing evidence to conclude
that the mean percent absorbency for cotton fiber is significantly higher than for
acetate? Use a significance level of 0.10.
b) What is the p-value of the test statistic?
c) Determine the corresponding confidence interval for the mean difference between the
average percent absorbency of the two fibers.
Solution:
Cotton Fiber Acetate
Sample size 30 30
Sample Mean 20 14
Standard Deviation 1.75 1.50
Null and Alternative Hypothesis:
Ho: µ1-µ2 = 0
Ha: µ1-µ2 > 0
Significance Level:
α= 0.10
Degrees of Freedom = n1 + n2 – 2 = 30 + 30 – 2 = 58

n1−1 ) ∙ s 21+ ( n2−1 ) ∙ s 22 ( 30−1 ) ∙ ( 1.75 )2 + ( 30−1 ) ∙ ( 1.50 )2

Sp=
(
√ n1+ n2−2
=
√ 58
= 1.6298

Test statistic:
x 1−x 2 20−14
t= 1 1 = 1 1 = 14.2581
s p∙
√ +
n 1 n2
1.6298∙
√ +
30 30

P-value = P [ t58 > t14.26 ] = 0

Yes, there is a convincing evidence to conclude that the mean percent absorbency for cotton fiber
is significantly higher than for acetate.
Confidence Interval:

s 21 s22
E=t α
2 √ +
n1 n2
= 1.311
1.75 1.50
30√+
30
= 0.4315

5.5685 6.4315

2. A random sample of size n1 = 25, taken from a normal population with a standard
deviation σ 1 =5.0, has a mean of x́ 1=83. A second random sample of size n2 = 36, taken
from a different normal population with a standard deviation σ 2=3.6, has a mean x́ 2=88.
a) Test the hypothesis that μ1=μ2 using a 0.01 significance level.
b) What is the p-value of the test statistic?
c) Develop the appropriate confidence interval.
Solution:
P1 P2
Sample size 25 36
Sample Mean 83 88
Standard Deviation 5 3.6
Null and Alternative Hypothesis:
Ho: µ1-µ2 = 0
Ha: µ1-µ2 > 0
Significance Level:
α= 0.01
Degrees of Freedom = n1 + n2 – 2 = 25 + 36 – 2 = 59

( n1−1 ) ∙ s 21+ ( n2−1 ) ∙ s 22 ( 25−1 ) ∙ ( 5 )2 + ( 36−1 ) ∙ ( 3.6 )2

Sp=
√ n1+ n2−2
=
√ 59
= 4.2258

Test statistic:
x 1−x 2 83−88
t= 1 1 = 1 1 = -4.5448
s p∙
√ +
n 1 n2
4.2258 ∙
√ +
25 36

P-value = P [ t59 > t-4.5448 ] = 0.000014

Since the P-value < 0.01, we reject the null hypothesis.
Confidence Interval:
 s 21 s22
E=t α
2 √ +
n1 n2
= 2.492
5 3.6
√
25
+
36
= 1.3649

3. A taxi company manager is trying to decide whether the-3.6351

-6.3649 use of radial tires instead of regular
belted tires improves fuel economy. Twelve cars were equipped with radial tires and driven over
a prescribed test course. Without changing drivers, the same cars were then equipped with
regular belted tires and driven once again over the test course. The gasoline consumption, in
kilometers per liter, was recorded as follows:

Can we conclude that cars equipped with radial tires give better fuel economy than those
equipped with belted tires? Assume the populations to be normally distributed. Use both p-value
and critical value approach. Use α=0.10.
Solution:
Null and Alternative Hypothesis:
Ho: µ1- µ2=0
H1+: µ1- µ2>0
Significance level:
α=0.10
Test statistic:
We use the t-distribution since we’re dealing with two dependent means
d́−do
T=
Sd
√n
Car radial tires Belted tires d
Critical Value Approach
1 4.2 4.1 0.1
2 4.7 4.9 -0.2
Using
3 Excel, 6.6 6.2 0.4
4 7.0 6.9 0.1
5 6.7 6.8 -0.1
6 4.5 4.4 0.1
7 5.7 5.7 0
8 6.0 5.8 0.2
9 7.4 6.9 0.5
10 4.9 4.7 0.2
11 6.1 6.0 0.1
12 5.2 4.9 0.3
 d́=0.141667
Sd =0.197523

d́−do
T=
Sd
√n
0.141667−0
T=
0.197523 = 2.48
√ 12
df= 12-1=11
For a right-tailed test with α=0.10, with df=11:
𝑐𝑟𝑖𝑡𝑖𝑐𝑎𝑙 𝑡−𝑣𝑎𝑙𝑢𝑒= 1.363
Decision:
Since the test statistic is greater than 1.363, we reject the null hypothesis.

P-value Method
Computing the test-statistic:
d́−do
T=
Sd
√n
0.141667−0
T=
0.197523 = 2.48
√ 12
df= 12-1=11
For a right-tailed test with test statistic= 2.48 and df=11:
P-value= 0.0153
Decision:
Since the p-value is lesser than the significance level= 0.10, we reject the null hypothesis.
Therefore, we concluded that the cars equipped with radial tires give better fuel economy than
those equipped with belted tires.
4. A study is conducted to compare the lengths of time required by men and women to assemble
a certain product. Past experience indicates that the distribution of times for both men and
women is approximately normal but the variance of the times for women is less than that for
men. A random sample of times for 11 men and 14 women produced the following data:

Test the hypothesis that the variance for men is greater than for women. Use both p-value
method and critical value approach. Use α=0.05.
Solution:
Claim: The variance for men is greater than for women
Null and Alternative Hypothesis:
Ho: σ12 = σ22
H1: σ12 > σ22

Significance level:
α=0.05

Test statistic:
We use the f-distribution since we’re dealing with two populations and two variances.

s2
F= 12 .
s2

smen =6.1>s women =5.3

Let population 1=men, population 2=women

6.12
F= =1.32467
5.32
d f 1 =11−1=10
d f 2 =14−1=13
Critical Value Approach
Critical region is f > Fα, n, df2, where Fα, df1, df2 is the upper α point of the F-distribution with
df1 and df2.
Using F-table, for α = 0.05, df1=10, df2=13
Critical value = 2.6710
Decision:
Since the test statistic is equal to 1.3247 and is not greater than 2.6710, we fail to reject
the null hypothesis.
P-value Method
For tailed test: P-value= P (f >1.3247)
Using EXCEL, P-value=0.3095
Decision:
Since p-value=0.3095 is greater than 0.05, we fail to reject the null hypothesis.
Thus, we can conclude that there is not enough evidence to claim the variance of the times for
men is less than that for women under the level of significance α = 0.05.
5. After each government project is completed, the concerned department inspects the project
and given a “pass” or “fail” rating. A pass rating is necessary before the appropriate contractor is,
given the final payment. A failed project must be reinspected until it passes the inspect. The
reinspection is both costly and time-consuming. In order to deter failure, the government decided
to publicize the inspection records of all contracts. A year after the web access was made public,
two samples of records were randomly selected. One sample was selected from the pool of
records before the web publication and one after. The proportion of projects that passed on the
first inspection was noted for each sample.

Test whether there is sufficient evidence to conclude that public web access to the inspection
records has increased the proportion of projects that passed on the first inspection by more than 5
percentage points. Use α=0.10.
a) Perform hypothesis test.
b) Construct the corresponding confidence interval.
Solution:
Claim: There is a significant difference between having public access and without
public access to inspection records on the proportion of project passed on the first
inspection.
Null and Alternative Hypothesis:
P1= with public access, p2=w/o public access
H A : p 1− p 2˃ 0 Right tailed

H 0 :P 1−P 2 ≤ 0

Significance level:
α=0.10
Test statistic:
p1−^
(^ p2 ) −( p1− p2 )
z=
1 1
√ ṕ ( 1− ṕ )
( +
n 1 n2 )
 x 1+ x2
ṕ=
n1+ n2
0.68+ 0.81
ṕ= =2.48333 x 10¯ ³
400+200

z=
( 0.68 −
0.81
400 200 )
−(0)
=−0.55
1 1
√ 2.48333 x 10¯ ³ ( 1−( 2.48333 x 10¯ ³) )( +
400 200 )
P ( 1−z )=P ( 1−(−0.55 ) )=1.55

P= 0.93943

Decision:
Since p-value (0.93943) is greater than 0.10, we fail to reject the null hypothesis.
Thus, we can conclude that there is no significant difference between having public
access and without public access to inspection records on the proportion of project passed on
the first inspection.

Confidence Interval:
α =0.10
CL=80 %

p 1(1−^p1) ^
p (1−^p 2)
E=z α /2 ×
√ ^
n1
+ 2
n2

0.68 0.68 0.81 0.81

E=1.28×
400
(1−
√
400
400
)
+
200
(1−
200
200

Point estimate:
)
=6.3241 x 10 ¯ ³

0.68 0.81
p1 − ^
^ p2 = −
400 200
80% CL:
 ( 0.68 −
0.81
400 200 )
−6.3241 x 10 ¯ ³< p − p <(
1
0.68 0.81
400 200 )
2 − +6.3241 x 10 ¯ ³

−08.6741 x 10 ¯ ³< p1 −p 2<3.9741 x 10 ¯ ³

Since the confidence interval is−08.6741 x 10 ¯ ³< p1 −p 2<3.9741 x 10 ¯ ³ , and the p-

value (1.55) is greater than the computed confidence interval, we fail to reject the null
hypothesis.
Thus, we can conclude that there is no significant difference between having public
access and without public access to inspection records on the proportion of project passed on
the first inspection.

Bonus: 10 points
A study at the University of Colorado at Boulder shows that running increases the percent resting
metabolic rate (RMR) in older women. The average RMR of 30 elderly women runners was
34.0% higher than the average RMR of 30 sedentary elderly women, and the standard deviations
were reported to be 10.5 and 10.2%, respectively. Was there a significant increase in RMR of the
women runners over the sedentary women? Use α=0.01.
Older women Elder women
Sample mean 34 0
Sample standard deviation 10.5 10.2
Sample size 30 30

Claim: there is a significant difference of the average RMR of elderly women

runners and the average RMR of sedentary elderly women.
Null and Alternative Hypothesis:
Let μ₁ be elderly women runners and μ₂ sedentary elderly women.
H 0: μ₁- μ₂ =0

H A : μ₁ - μ₂˃0

Significance level:
α=0.01, the alternative is right tailed.
Test statistic:
We use the t-distribution since we’re given that the population to be approximately
normally distributed with equal variances.
 ( x́ 1− x́ 2) −(μ 1−μ2)
t=
1 1
s❑p
√ +
n1 n 2

Df= n₁+n₂-2 = 30+30-2= 58

Pooled standard deviation;

2 ( n1−1 ) s 21+ ( n2−1 ) s22

s=
p
( n1−1 ) +(n2−1)

2 ( 30−1 ) (10.5)2❑ + ( 30−1 ) (10.2) ²

s=
p
( 30−1 ) +(30−1)

s❑p =10.3511

( x́ 1− x́ 2) −(μ 1−μ2)
t=
1 1
s❑p
√ +
n1 n 2

( 34−0 )−( 0)
t=
1 1
10.3511
√ +
30 30
t=12.72149
Using Excel,
P-value = P (t>12.72) = 2.3924
Decision:
Since the p-value is greater than the significance level, we fail reject the null hypothesis.
Therefore, there is no significant difference of the average RMR of elderly women runners and
the average RMR of sedentary elderly women.