ANSWERS FOR QUESTIONS

1. Population: 7, 7, 8, 8, 7
A. Population Mean:
7+7 +8+8+7 37
μ= = =7.4
5 5
B. Sampling Distribution of Sample Means (n = 2):
List all possible samples without replacement and compute their means:

Sampl
e Mean
(7,7) 7
(7,8) 7.5
(7,8) 7.5
(7,7) 7
(7,8) 7.5
(7,8) 7.5
(8,8) 8
(8,7) 7.5
(8,7) 7.5
(7,7) 7

Unique sample means and their frequencies:

 7 → 3 times
 7.5 → 6 times
 8 → 1 time
C. Mean of the Sampling Distribution:
ˉ
3 ×7 +6 ×7.5+1 × 8 22.5+ 45+8 74
x sampling = = = =7.4
10 10 10
✅ The mean of the sampling distribution = Population mean

2. Probability sample proportion > 0.75

Given:
 Population proportion p=0.65
 Sample size n=150
 We want P ( ^p >0.75 )
Step 1: Compute standard error (SE)

SE=
√ p ( 1 − p)
n √
=
0.65 ×0.35
150
≈ 0.0391

Step 2: Compute z-score

0.75 −0.65
z= ≈ 2.56
0.0391
Step 3: Use z-table
P ( ^p >0.75 )=P ( z >2.56 ) ≈ 0.0052

3. Confidence Interval for Population Proportion

Given:
168
 x = 168, n = 200 → ^p= =0.84
200
 Confidence level = 90% → z=1.645
Step 1: SE

SE=
√ 0.84 ( 1 −0.84 )
200
=
√
0.1344
200
≈ 0.0259

Step 2: Margin of Error (ME)

ME=1.645 ×0.0259 ≈ 0.0426
Step 3: CI
CI =0.84 ± 0.0426=( 0.797 , 0.883 )

4. Confidence Interval for Mean (Sample Mean = 14.3, SE = 2)

 Confidence level = 95% → z=1.96
ˉ
 CI = x ± z ⋅SE

CI =14.3 ±1.96 × 2=14.3 ± 3.92=( 10.38 , 18.22 )

5. Sample Size for Estimating Mean Chips

Given:
 E (margin of error) = 2
 σ =10.1
 Confidence level = 99% → z=2.576

( ) ( )
2 2
z⋅ σ 2.576 ⋅10.1 2
 n= = =( 13.013 ) ≈ 169
E 2
6. Confidence Interval for Proportion
Given:
 ^p=0.39, n = 87
 Confidence level = 95% → z=1.96
Step 1: SE

SE=
√ 0.39 ×0.61
87
≈ 0.052

Step 2: ME
ME=1.96 ×0.052 ≈ 0.102
Step 3: CI
CI =0.39 ± 0.102=( 0.288 , 0.492 )

7. Hypothesis Test for Two Proportions (α = 0.10)

Given:
87
 Girls: p1= =0.58
150
123
 Boys: p2= =0.615
200
 Significance level = 0.10 → z crit=±1.645
Step 1: Pooled Proportion
87+123 210
p= = =0.6
150+200 350
Step 2: SE

√
SE= p ( 1− p ) ( 1501 + 2001 )=√ 0.6 ⋅0.4 ( 1501 + 2001 ) ≈ 0.055
Step 3: z-score
0.58 −0.615
z= ≈ −0.64
0.055
Since − 0.64>− 1.645, we fail to reject H₀.
Conclusion: No significant difference in proportions at 0.10 level. Great! Let’s walk through
questions 8 to 15, step-by-step:
8. Eastern vs. Western Home Ownership (Two-sample t-test)
ˉ
 Eastern: n1=40 , x1 =7.6 , s 1=2.3
ˉ
 Western: n2 =55 , x 2=8.1 , s 2=2.9
 Claim: Eastern homes are owned for a shorter time
 H 0 : μ1 ≥ μ2, H 1 : μ 1< μ 2
 α = 0.05
Step 1: Compute standard error (SE):

SE=
√ 2.32 2.92
+
40 55
≈
√
5.29 8.41
40
+
55
≈ √ 0.1323+0.1529=√ 0.2852 ≈ 0.534

Step 2: t-statistic:
7.6 −8.1 −0.5
t= = ≈ −0.936
0.534 0.534
Step 3: Degrees of freedom (approx.) ≈ 85
Step 4: Critical value for one-tailed test at α = 0.05 → t 0.05 ,df =85 ≈ −1.664

Conclusion: Since − 0.936>−1.664 , we fail to reject H 0.

No significant evidence that eastern residents owned homes for shorter time.

9. Did the battery life increase? (One-sample t-test)

ˉ
 μ0=305, x =311, s=12, n=20, α = 0.05
 H 0 : μ ≤305 , H 1 : μ >305

311−305 6
t= = ≈ 2.236
12/ √ 20 2.683
df = 19 → t 0.05 ,df =19 ≈1.729

2.236 > 1.729 → Reject H 0

The battery life significantly increased.

10. Proportion of Men Driving Ride Cars (One-sample z-test)

170
 p0=0.52, ^p= =0.567 , n = 300
300
 α = 0.01
 H 0 : p ≤ 0.52, H 1 : p> 0.52

SE=
√ 0.52 (1 − 0.52 )
300
≈ 0.0288
 0.567 −0.52
z= ≈ 1.63
0.0288
Critical z at α = 0.01 → 2.33
Since 1.63 < 2.33, fail to reject H 0
Not enough evidence to conclude more men are driving Ride cars.

11. Idle Time Exceeds 75 Minutes? (One-sample t-test)

ˉ
 μ0=75, x =84 , s=20, n=25
 α = 0.05
 H 0 : μ ≤75, H 1 : μ >75

84 −75 9
t= = =2.25
20/ √ 25 4
df = 24 → t 0.05 ,df =24 ≈ 1.711

2.25 > 1.711 → Reject H 0

Evidence that idle time exceeds 75 minutes

12. Health Club Weight Loss (Z-test, known σ)

ˉ
 μ0=10, x =9.2 , σ =2.4 , n=36

9.2− 10 − 0.8
z= = =−2.0
2.4 / √ 36 0.4
p-value = P(z < -2.0) ≈ 0.0228
 At α = 0.01: Do not reject H 0
 At α = 0.05: Reject H 0
➡️Depends on α. At 5% level, weight loss is significantly less than claimed. At 1%, it is not.

13. Fitness Center Claim: Average Loss ≥ 15 (One-sample t-test)

ˉ
 μ0=15, x =13 , s=3, n=45 , α = 0.05
 H 0 : μ ≥15 , H 1 : μ <15

13− 15 −2
t= = ≈ − 4.475
3/ √ 45 0.447
df = 44 → Critical t ≈ -1.68
-4.475 < -1.68 → Reject H 0
Weight loss is significantly less than claimed
14. New Food Machine Learning Time (Z-test)
ˉ
 μ0=90, x =85 , σ =7, n=20

85 −90 −5
z= = ≈− 3.194
7/ √ 20 1.565

p-value = 2 × P(z < -3.194) ≈ 2 × 0.0007 = 0.0014

 At α = 0.01 → p < α, reject H 0
Significant difference in learning time. The machine reduces learning time.

15. Parking Fees – Is Mean ≠ 125? (Z-test)

ˉ
 μ0=125, x =124 , σ =5, n=400, α = 0.01
124 −125 −1
 z= = =− 4.0
5 / √ 400 0.25
Critical z for α = 0.01 (two-tailed) = ±2.576
-4.0 < -2.576 → Reject H 0
Monthly parking fee significantly differs from 125 Birr

16. Mayor’s Claim on Net Worth

 Claim: Mean net worth ≥ $300,000
ˉ
 Sample: x =288 , 000, n=25, σ =80 , 000
 Test: One-sample Z-test (σ known), α = 0.025 (one-tailed)
Step 1:
H 0 : μ ≥300 , 000 , H 1 : μ< 300 ,000

Step 2: Compute Z:
288 , 000 −300 , 000 −12 ,000
z= = =−0.75
80 , 000 / √ 25 16 , 000

Step 3: Critical z for α = 0.025 (one-tailed) = -1.96

Step 4: Decision:
 Since − 0.75>−1.96 , we fail to reject H 0
 Conclusion: There is not enough evidence to reject the mayor’s claim.
17. TIV Telephone – Call Length Comparison
ˉ
 μ0=12.44, x =13.71, σ =2.65, n=150, α = 0.02 (two-tailed)
Step 1:
H 0 : μ=12.44 , H 1 : μ ≠12.44
Step 2: Z-statistic:
13.71− 12.44 1.27
z= = ≈ 5.87
2.65/ √150 0.2164

Step 3: Critical z for α = 0.02 (two-tailed) = ±2.326

Since 5.87 > 2.326 → Reject H 0
Conclusion: The mean length of calls is significantly different from 12.44 minutes.

18. Bottling Company – Underfilling Complaint

 Claimed mean: μ0=330ml
ˉ
 x =326 , s=20, n=81, α = 0.01 (one-tailed)
Step 1:
H 0 : μ ≥330 , H 1 : μ< 330

Step 2: Use t-test (since σ unknown):

326 −330 −4
t= = ≈ −1.80
20 / √ 81 2.222

df = 80 → Critical t for one-tailed test at α = 0.01 ≈ -2.38

Step 3: Decision:
 Since −1.80> −2.38, we fail to reject H 0
Conclusion: No strong evidence that the product is underfilled.
19. Investor & Household Income
ˉ
 μ0=12000, x =11800 , s=1000, n=100, α = 0.01 (one-tailed)
Step 1:
H 0 : μ ≥12000 , H 1 : μ< 12000

Step 2: t-statistic:
11800 −12000 −200
t= = =− 2.0
1000/ √ 100 100

df = 99 → Critical t at α = 0.01 ≈ -2.364

Step 3: Decision:
 Since −2.0> −2.364 , we fail to reject H 0
Conclusion: The investor should not reject the area based on this test. There is not
enough evidence to prove the income is below 12,000.
20. Hypothesis Test for Proportion (Two-Tailed Test)
 Claim: p=0.81
 Sample size (n): 1600
 **Sample proportion ( ^p) = 0.83
 **Significance level (α ) = 0.05
Step 1: Hypotheses
H 0 : p=0.81 H 1 : p ≠ 0.81

Step 2: Test Statistic

^p − p 0 0.83 −0.81
z= =

√ p0 ( 1 − p0 )
n √ 0.81 ( 0.19 )
1600

0.02 0.02
z= = ≈ 2.037
√ 0.000096375 0.009816
Step 3: P-Value
Using the z-table:
P ( Z >2.037 )=0.0208 , so
p-value = 2 × 0.0208 = 0.0416
Conclusion:
Since p-value = 0.0416 < 0.05, reject H 0.
There is evidence that the percentage of drivers who talk on their phones has changed from
81%.

21. Hypothesis Test for Proportion (One-Tailed Test)

 Claim: p ≤ 0.04
 Sample size (n): 200
12
 **Sample defective rate ^p= =0.06
200
 **Significance level (α =0.025 )
Step 1: Hypotheses
H 0 : p ≤ 0.04 H 1 : p>0.04

Step 2: Test Statistic

0.06 − 0.04 0.02 0.02
z= = = ≈ 1.443

√ 0.04 ( 0.96 )
200
√ 0.000192 0.013857
Step 3: P-Value
From z-tables:
P ( Z >1.443 )=0.0747
Conclusion:
Since p-value = 0.0747 > 0.025, do not reject H 0.
There is not enough evidence to conclude that the machine needs adjustment.

22. Confidence Interval for Difference of Means (Population σ Known)

ˉ
 Retailer A: n =50 , x =82 , σ =7
1 1 1
ˉ
 Retailer B: n =60 , x =78 , σ =6
2 2 2

 Confidence Level = 95%, Z 0.025=1.96

Formula:

( ) √
σ 21 σ 22
ˉ ˉ
CI = x 1 − x 2 ± Z ⋅ +
n1 n 2

¿ ( 82 −78 ) ± 1.96 ⋅
√ 49 36
+ =4 ±1.96 ⋅ √ 0.98+ 0.6=4 ± 1.96 ⋅ √ 1.58≈ 4 ± 1.96 ⋅1.257 ≈ 4 ± 2.464
50 60
Confidence Interval:
( 1.536 , 6.464 )
Interpretation: We are 95% confident that the true difference in average satisfaction (Retailer
A - Retailer B) is between 1.54 and 6.46. Retailer A likely has higher customer satisfaction.

23. Confidence Interval for Difference in Proportions

 Campaign A: n1=200 , x 1=60 ⇒ ^p1=0.30
 Campaign B: n2=250 , x 2=85 ⇒ ^p2 =0.34
 Confidence Level = 95%, Z=1.96
Formula:

CI =( ^p1 − ^p2 ) ± Z ⋅
√ ^p 1 ( 1 − ^p1 ) p^ 2 ( 1 − ^p2 )
n1
+
n2

¿ ( 0.30 − 0.34 ) ±1.96 ⋅

√ 0.30 ( 0.70 ) 0.34 ( 0.66 )
200
+
250
=− 0.04 ± 1.96⋅ √0.00105+ 0.0008976=−0.04 ± 1.96 ⋅ √ 0.0019476

¿ − 0.04 ±1.96 ⋅ 0.0441≈ − 0.04 ± 0.0865

Confidence Interval:
( − 0.1265 ,0.0465 )
 Interpretation: We are 95% confident the true difference in awareness (A - B) is between -
12.65% and 4.65%.
Since the interval includes 0, we cannot conclude a significant difference in awareness
between the two campaigns.
We're looking to test whether family income and house type are statistically independent
using a Chi-Square Test of Independence at the 1% significance level. Let's solve it step by
step.

24. Step 1: Data (Contingency Table)

10 , 000 – 15,00
House Type < $10,000 0 > $15,000 Row Total
A 28 45 75 148
B 47 55 35 137
C 63 27 27 117
Col Total 138 127 137 402

Step 2: Hypotheses
 Null Hypothesis H 0: Family income and house type are independent.
 Alternative Hypothesis H 1: Family income and house type are not independent.

Step 3: Expected Frequencies

Use the formula:

( Row Total i )( Column Total j )

Eij =
Grand Total
For A:
148× 138
 A, <10k: ≈ 50.78
402
148× 127
 A, 10k–15k: ≈ 46.77
402
148× 137
 A, >15k: ≈ 50.45
402
For B:
137 ×138
 B, <10k: ≈ 47.08
402
137 ×127
 B, 10k–15k: ≈ 43.31
402
137 ×137
 B, >15k: ≈ 46.61
402
For C:
117 ×138
 C, <10k: ≈ 40.14
402
117 ×127
 C, 10k–15k: ≈ 37.92
402
117×137
 C, >15k: ≈ 39.94
402
Step 4: Chi-Square Test Statistic
( O − E )2
χ 2=∑
E
Compute for all cells:

Cell O E (O−E)²/E
A,<10k 2 50.78 10.29
8
A,10-15k 4 46.77 0.07
5
A,>15k 7 50.45 11.89
5
B,<10k 4 47.08 0.00
7
B,10-15k 5 43.31 3.16
5
B,>15k 3 46.61 2.89
5
C,<10k 6 40.14 13.03
3
C,10-15k 2 37.92 3.15
7
C,>15k 2 39.94 4.20
7

Total χ² ≈ 48.68

Step 5: Degrees of Freedom

df =( r −1 ) ( c − 1 )=( 3 −1 ) ( 3 −1 )=4

Step 6: Critical Value at 1% level, df = 4

From Chi-Square table:
**Critical value $ \chi^2_{0.01,4} = 13.277 **
Step 7: Conclusion
 Since χ² = 48.68 > 13.277, we reject the null hypothesis.
Conclusion: There is sufficient evidence at the 1% level to conclude that family income and
house type are not independent — there is a statistically significant relationship between
income and house type.

25.To test this, we perform an F-test for equality of variances.

Step 1: Hypotheses
We want to test if Employee A has more variation than Employee B.
Let ( \sigma_A^2 betℎevarianceofEmployeeAand \sigma_B^2 $ for Employee B.

 Null Hypothesis H 0: σ 2A ≤ σ 2B
 Alternative Hypothesis H 1: σ 2A >σ 2B (this is a one-tailed test)

Step 2: Sample Data

Employee Sample Size n Standard Deviation s Variance s2
2
A 10 2 2 =4
2
B 10 1.5 1.5 =2.25

Step 3: Test Statistic

2
sA 4
F= 2
= =1.78
sB
2.25

Step 4: Degrees of Freedom

 d f 1 =n A −1=9
 d f 2=nB −1=9

Step 5: Critical Value (Right-tailed test, α = 0.05)

From the F-distribution table:
At α =0.05 , d f 1 =9, d f 2=9
Critical F-value ≈ 3.18

Step 6: Decision
Since F=1.78<3.18 , we fail to reject the null hypothesis.
Conclusion:
At the 0.05 significance level, there is not enough evidence to conclude that Employee A has
more variation in the number of rejects per day than Employee B.