Statistics 355 Homework 15

Problem 8.13
The calibration of a scale is to be checked by weighing a 10-kg test specimen 25 times.
Suppose that the results of different weighings are independent of one another and that
the weight on each trial is normally distributed with σ = 0.200 kg. Let µ denote the true
average weight reading on the scale.

a. What hypotheses should be tested?

H0 : µ = 10 Ha : µ 6= 10

b. With the sample mean itself as the test statistic, what is the P-value when
x̄ = 9.85, and what would you conclude at significance level 0.01?

m
P-value ≡ = P (X̄ ≥ 10.15) + P (X̄ ≤ 9.85) = 1 − P (9.85 ≤ X̄ ≤ 10.15)

er as
 
9.85 − 10 10.15 − 10

co
= 1−P ≤Z≤ = 1 − P (−3.75 ≤ Z ≤ 3.75)

eH w
0.2/5 0.2/5
= 1 − [Φ(3.75) − Φ(−3.75)] = 1 − (≈ 1− ≈ 0)

o.
≈ 0
rs e
ou urc
At 0.01 level of significance, we reject the H0 and conclude that the average weight
reading on the scale is different from 10 kgs.
o

c. For a test with α = 0.01, what is the probability that recalibration is judged unneces-
aC s

sary when in fact µ = 9.8?

vi y re

α = P (Reject H0 when H0 is true)

 
−c − 10 c − 10
0.01 = 1 − P ≤Z≤
ed d

0.2/5 0.2/5
ar stu

       
−c − 10 c − 10 c − 10 −c − 10 c − 10
0.99 = P ≤Z≤ =Φ −Φ = 2Φ −1
0.2/5 0.2/5 0.2/5 0.2/5 0.2/5
   
c − 10 c − 10
1.99 = 2Φ ⇒ 0.995 = Φ
is

0.2/5 0.2/5
c − 10
Th

2.575 = ⇒ c = 10.103
0.2/5
sh

This study source was downloaded by 100000827996918 from CourseHero.com on 07-16-2021 12:07:53 GMT -05:00
1
https://www.coursehero.com/file/23028205/HOMEWORK-15-SOLUTIONS/
 β(9.8) = P (Fail to Reject H0 when H0 is false)
= P (−c ≤ X̄ ≤ c when µ = µ0 = 9.8) = P (9.897 ≤ X̄ ≤ 10.103 when µ0 = 9.8)
X̄ − µ0
 
= P 9.897 ≤ √ ≤ 10.103
σ/ n
 
9.897 − 9.8 10.103 − 9.8
= P ≤Z≤
0.2/5 0.2/5
= P (2.425 ≤ Z ≤ 7.575) = Φ(7.575) − Φ(2.425) =≈ 1 − 0.9922
= 0.0078
 
9.897 − 10.1 10.103 − 10.1
β(10.1) = P ≤Z≤
0.2/5 0.2/5
= P (−5.075 ≤ Z ≤ 0.075) = Φ(0.08) − Φ(−5.08) = 0.5319− ≈ 0
= 0.5319

m
er as
co
eH w
o.
Problem 8.17
rs e
ou urc
Answer the following questions for the tire problem in Example 8.7.

H0 : µ = 30, 000 Ha : µ > 30, 000

o
aC s

a. If x̄ = 30, 960 and a level α = 0.01 test is used, what is the decision?
vi y re

X̄ − µ0 30, 960 − 30, 000

z = √ = √ = 2.56
σ/ n 1500/ 16
P-value ≡ 1 − Φ(z) = 1 − Φ(2.56) = 1 − 0.9948 = 0.0052
ed d
ar stu

Since P-value is less than 0.01, then we reject the null hypothesis.

b. If a level 0.01 test is used, what is β(30, 500)?

is

 
30, 000 − 30, 500
β(30, 500) = Φ 2.33 + √ = Φ(0.9967) = Φ(1) = 0.8413
Th

1, 500/ 16

c. If a level 0.01 test is used and it is also required that β(30, 500) = 0.05, what sample
size n is necessary?
sh

 2  2
σ(zα + zβ ) 1500(2.33 + 1.645)
n = = = 142.2056 ⇒ n = 143
µ0 − µ0 30, 000 − 30, 500

This study source was downloaded by 100000827996918 from CourseHero.com on 07-16-2021 12:07:53 GMT -05:00
2
https://www.coursehero.com/file/23028205/HOMEWORK-15-SOLUTIONS/
 d. If x̄ = 30, 960, what is the smallest α at which H0 can be rejected (based on n = 16)?

α = P (Reject H0 when H0 is true)

 
30, 960 − 30, 000
= P Z> √ = 1 − Φ(2.56) = 1 − 0.9948 = 0.0052
1500/ 16

Problem 8.19
The melting point of each of the 16 samples of a certain brand of hydrogenated vegetable
oil was determined, resulting in x̄ = 94.32. Assume that the distribution of the melting
point is normal with σ = 1.20.

a. Test H0 : µ = 95 versus Ha : µ 6= 95 using a two-tailed level 0.01 test.

m
er as
i. H0 : µ = 95 Ha : µ 6= 95

co
ii. α = 0.01

eH w
iii. Compute for the test statistic:

o.
We are given the following information: n = 16, x̄ = 94.32, µ0 = 95, σ = 1.20.
rs e
ou urc
x̄ − µ0 94.32 − 95
z= √ = √ = −2.27
σ/ n 1.20/ 16
iv. Decision Rule: Reject H0 if P-value ≤ α.
o
aC s

P-value = 2Φ(−2.27) = 2(0.0116) = 0.0232 > 0.01

vi y re

v. Conclusion: We fail to reject the null hypothesis. There is no sufficient evidence

that the melting point of a certain brand of hydrogenated vegetable oil is not 95,
ed d

at 0.01 level of significance.

ar stu

b. If a level 0.01 test is used, what is β(94), the probability of a Type II error when
µ = 94.
is

   
95 − 94 95 − 94
β(94) = Φ z0.005 + √ − Φ −z0.005 + √
1.20/ 16 1.20/ 16
Th

= Φ (2.58 + 3.33) − Φ (−2.58 + 3.33) = Φ(5.91) − Φ(0.75)

= 1 − 0.7734 = 0.2266
sh

c. What value of n is necessary to ensure that β(94) = 0.10 when α = 0.01?

 2  2
σ(z0.005 + z0.10 ) 1.2(2.58 + 1.28)
n = = = 21.4554
95 − 94 95 − 94
= 22

This study source was downloaded by 100000827996918 from CourseHero.com on 07-16-2021 12:07:53 GMT -05:00
3
https://www.coursehero.com/file/23028205/HOMEWORK-15-SOLUTIONS/
Powered by TCPDF (www.tcpdf.org)