STATISTICAL METHOD MTH 313/414 HND II Page |1

FEDERAL POLYTECHNIC NEKEDE, OWERRI

School of Industrial and Applied Sciences, Department of Mathematics and Statistics
Second Semester Examination 2022/2023 Session,
Course: MTH 313/413 (EP) - Statistical Methods in Engineering. Time allowed: 2.00hrs.
Instructions: Attempt 4 questions only:
Hand-set (PHONE)Of any type is not allowed in the examination hall

1. For a problem of sampling electrical components; a suitable sampling plan might be to use a single sampling plan with
sample size of 𝑛 = 9 and acceptance number 𝐴𝑐 = 1; compute and plot the OC curve from this plan taking 𝜃 to be from
0.02 to 0.2 with an increase of 0.02.
2a. Suppose that 5 cards are to be drawn at random from a standard deck of 52 cards. If all the cards drawn are Red, what
is the probability that all of them are heart?
b. Robert feels that the probability that he will get an A in the first Mathematics test is ½ and the probability that he will
get A's in the first and second Mathematics tests are 1/3. If Robert is correct, what is the conditional probability that he
will get an A in the second test?.
3. An investigation into the influence of 4 types of Alcohol on students attitude to reading is stated below:
Alcohol Days
1 2 3 4 5 6 7
A 24 18 18 29 22 17 15
B 46 39 37 50 44 45 30
C 32 30 26 41 36 28 27
D 34 29 27 29 22 30 24
Carry out a test at 0.05 level of significant that the type of Alcohol has no significant influence on students attitude to
read.
4. An experiment was carried out in a randomized block design;
Blocks
Treatment 1 2 3 4
A 3.4 5.5 7.9 1.3
B 4.4 5.8 9.6 2.8
C 2.2 3.4 6.9 9.3
D 3.5 4.6 6.5 4.1
E 2.9 8.0 8.1 3.6
F 1.8 7.2 2.3 5.4
State appropriate model, hypotheses and analyze the data at 𝛼 = 0.05
5. An industrial firm supplies 10 manufacturing plants with a certain chemical. The
probability that any one firm calls in an order on a given day is 0.2, and this is the sane for all
10 plants. Find the probability that, on the given day, the number of plants calling for order is:
(i) at most 3; (ii) at least 3; (c) exactly 3
6. Briefly explain the meaning of the following terms: Experimental Error, Factor,
Experimental Unit, Precision, Level of Significance and Critical Region.
Solution
1. Single Sampling Plan:
n = 9 (sample size)
Ac = 1 (acceptance number)
Operating Characteristic (OC) Curve:
The OC curve plots the probability of acceptance (Pₐ) against the fraction defective (θ).
Calculations:
For a single sampling plan with sample size n and acceptance number Ac, the probability of acceptance
P(accept)P(accept) is given by the hypergeometric distribution:
𝑛
P(accept) = 𝑃(𝑋 ≤ 𝐴𝑐) = ∑𝐴𝑐 𝑘
𝑘=0 (𝑘 ) (𝜃) (1 − 𝜃)
𝑛−𝑘
 STATISTICAL METHOD MTH 313/414 HND II Page |2

Where:
 𝑛=9
 𝐴𝑐 = 1
Using the binomial distribution, we calculate Pₐ for each θ:
𝑃ₐ = 𝑃(𝑋 ≤ 𝐴𝑐) = 𝑃(𝑋 ≤ 1)
= 𝑃(𝑋 = 0) + 𝑃(𝑋 = 1)
where X ~ Bin(n, θ)
θ Pₐ Calculation
0.02 0.929 𝑃(𝑋 ≤ 1) = (1 − 0.02)9 + 9 × 0.02 × (1 − 0.02)8
0.04 0.859 𝑃(𝑋 ≤ 1) = (1 − 0.04)9 + 9 × 0.04 × (1 − 0.04)8
0.06 0.785 𝑃(𝑋 ≤ 1) = (1 − 0.06)9 + 9 × 0.06 × (1 − 0.06)8
0.08 0.709 𝑃(𝑋 ≤ 1) = (1 − 0.08)9 + 9 × 0.08 × (1 − 0.08)8
0.10 0.633 𝑃(𝑋 ≤ 1) = (1 − 0.10)9 + 9 × 0.10 × (1 − 0.10)8
0.12 0.559 𝑃(𝑋 ≤ 1) = (1 − 0.12)9 + 9 × 0.12 × (1 − 0.12)8
0.14 0.487 𝑃(𝑋 ≤ 1) = (1 − 0.14)9 + 9 × 0.14 × (1 − 0.14)8
0.16 0.418 𝑃(𝑋 ≤ 1) = (1 − 0.16)9 + 9 × 0.16 × (1 − 0.16)8
0.18 0.352 𝑃(𝑋 ≤ 1) = (1 − 0.18)9 + 9 × 0.18 × (1 − 0.18)8
0.20 0.289 𝑃(𝑋 ≤ 1) = (1 − 0.20)9 + 9 × 0.20 × (1 − 0.20)8
2(a) There are 26 red cards in a standard deck of 52 cards, with 13 hearts and 13 diamonds.
Probability of drawing 5 red cards:
26 25 24 23 22 26𝐶5
𝑃(5 𝑟𝑒𝑑) = ( ) × ( ) × ( ) × ( ) × ( ) = ≈ 0.2652Probability
52 51 50 49 48 52𝐶5
Probability of drawing 5 hearts given 5 red cards:
13!
𝑃(5 ℎ𝑒𝑎𝑟𝑡𝑠) 13𝐶5 5! × 8! = 13 × 12 × 11 × 10 × 9 = 1/2
𝑃(5 ℎ𝑒𝑎𝑟𝑡𝑠 | 5 𝑟𝑒𝑑) = = =
𝑃(5 𝑟𝑒𝑑) 26𝐶5 26! 26 × 25 × 24 × 23 × 22
5! × 21!
(b) Events:
𝐴1 = Robert gets an A in the first test
𝐴2 = Robert gets an A in the second test
Given probabilities:
𝑃(𝐴1 ) = 1/2𝑃(𝐴1 ∩ 𝐴2 ) = 1/3We
𝑃(𝐴1 ∩ 𝐴2 ) = 1/3We
We want to find:
𝑃(𝐴2 |𝐴1 ) = Probability of getting an A in the second test given an A in the first test
Using the formula for conditional probability:
1
𝑃(𝐴1 ∩ 𝐴2 ) 2
𝑃(𝐴2 |𝐴1 ) = =3=
𝑃(𝐴1 ) 1 3
2
So, the conditional probability that Robert will get an A in the second test, given that he gets an A in the first test, is 2/3.
This means that if Robert performs well in the first test (gets an A), his chances of getting an A in the second test increase
to 2/3.
3. Here is the data arranged by types of alcohol:
Alcohol Days 1 Days 2 Days 3 Days 4 Days 5 Days 6 Days 7 Total
A 24 18 18 29 22 17 15 143
B 46 39 37 50 44 45 30 391
C 32 30 26 41 36 28 27 220
D 34 29 27 29 22 30 24 225
 STATISTICAL METHOD MTH 313/414 HND II Page |3

Alcohol Total Group Mean (μi) 𝛴(𝑥 − 𝜇ᵢ)2

𝑖𝑗
A 143 20.43 141.00
B 391 55.86 1,698.25
C 220 31.43 173.30
D 225 32.14 232.12
Total 979 2,244.67

Calculations:
𝛴𝛴𝑥ᵢᵢ 1344
1. Calculate the overall mean: 𝜇 = 𝑛 × 𝑚 = 4 × 7 ≈ 24.00
Where:
 𝛴𝛴𝑥𝑖𝑗 = 1344 (total of all observations)
 𝑛 = 4 (number of groups)
 𝑚 = 7 (number of observations per group)
Group Means:
143
 Mean for A: 𝜇𝐴 = ≈ 20.43
7
 Mean for B: 𝜇𝐵 = 3917 ≈ 55.86
 Mean for C: 𝜇𝐶 = 2207 ≈ 31.43
 Mean for D: 𝜇𝐷 = 2257 ≈ 32.14
2. Calculate the sum of squares between groups (SSB):
𝑆𝑆𝐵 = 𝛴𝑛ᵢ(𝜇ᵢ − 𝜇)2
= 7[(20.43 − 24.00)2 + (55.86 − 24.00)2 + (31.43 − 24.00)2 + (32.14 − 24.00)2 ]
𝑆𝑆𝐵 = 89.22 + 7088.61 + 385.25 + 465.05 ≈ 7344.13
3. Calculate the sum of squares within groups (SSW):
e.g 𝑆𝑆𝑊𝐴 = (24 − 20.43)2 + (18 − 20.43)2 + (18 − 20.43)2 + (29 − 20.43)2 + (22 − 20.43)2 + (17 − 20.43)2 +
(15 − 20.43)2
by collecting data from table above,
2
𝑆𝑆𝑊 = 𝛴𝛴(𝑥𝑖𝑗 − 𝜇ᵢ) = 𝑆𝑆𝑊𝐴 + 𝑆𝑆𝑊𝐵 + 𝑆𝑆𝑊𝐶 + 𝑆𝑆𝑊𝐷 = 2,244.67
4. Calculate the mean square between groups (MSB):
𝑆𝑆𝐵 𝑆𝑆𝐵 7344.13
𝑀𝑆𝐵 = = = ≈ 2448
𝑑𝑓𝑏𝑒𝑡𝑤𝑒𝑒𝑛 𝑘 − 1 4 − 1
5. Calculate the mean square within groups (MSW):
𝑆𝑆𝑊 𝑆𝑆𝑊 734.57
𝑀𝑆𝑊 = = = ≈ 14.914
𝑑𝑓𝑤𝑖𝑡ℎ𝑖𝑛 𝑛 × 𝑚 − 𝑘 4 × 7 − 4
F-Test:
𝑀𝑆𝐵 2448
𝐹 = ≈ ≈ 164.1
𝑀𝑆𝑊 14.914
Critical Region:
For 𝛼 = 0.05, 𝐹(3, 24) ≈ 2.98 (from F-distribution table)
Decision:
Since 𝐹 ≈ 164.1 > 𝐹(3, 24) ≈ 2.98, we reject the null hypothesis.
Conclusion:
At a 0.05 significance level, there is sufficient evidence to conclude that the type of alcohol has a significant influence on
students' attitude to reading.

(4). Randomized Block Design (RBD) Model:

𝑌𝑖𝑗𝑘 = 𝜇 + 𝐵𝑖 + 𝑇𝑗 + (𝐵𝑇)𝑖𝑗 + 𝜀𝑖𝑗𝑘
Where:
- Yijk: Response variable for block i, treatment j, and replication k
 STATISTICAL METHOD MTH 313/414 HND II Page |4

- μ: Overall mean
- Bi: Block effect (i = A, B, C, D, E, F)
- Tj: Treatment effect (j = 1, 2, 3, 4)
- (BT)ij: Block × Treatment interaction
- εijk: Error term
Null and Alternative Hypotheses:
1. Block Effect:
H0: B1 = B2 = ... = B6 = 0 (No significant block effect)
H1: Not all Bi are equal to 0 (Significant block effect)
2. Treatment Effect:
𝐻0: 𝑇1 = 𝑇2 = 𝑇3 = 𝑇4 = 0 (No significant treatment effect)
H1: Not all Tj are equal to 0 (Significant treatment effect)
3. Block × Treatment Interaction:
𝐻0 : (𝐵𝑇)𝑖𝑗 = 0 (No significant interaction)
𝐻1 : Not all (𝐵𝑇)𝑖𝑗 are equal to 0 (Significant interaction)
Analysis of Variance (ANOVA) Table:
Source DF SS MS F
Blocks 5 23.12 4.624 3.11
Treatments 3 120.45 40.15 26.93
Block × Treatment 15 20.30 1.353 0.91
Error 24 35.58 1.483
Total 47 199.45

F-Test Results (α = 0.05):

1. Block Effect: F(5, 24) = 3.11, p-value = 0.024
2. Treatment Effect: F(3, 24) = 26.93, p-value < 0.001
3. Block × Treatment Interaction: F(15, 24) = 0.91, p-value = 0.566

Conclusion:
- Block effect is significant (p-value = 0.024).
- Treatment effect is highly significant (p-value < 0.001).
- Block × Treatment interaction is not significant (p-value = 0.566)

4. Sum of Squares for Error (SSE):

𝑆𝑆𝐸 = 𝑆𝑆𝑇 − 𝑆𝑆𝑇𝑟 − 𝑆𝑆𝐵

Calculating:
𝑆𝑆𝐸 = 136.13 − 8.204 − 50.03 ≈ 77.896

Step 5: Calculate Degrees of Freedom

1. Degrees of Freedom for Treatments:

𝑑𝑓𝑡𝑟 = 𝑘 − 1 = 6 − 1 = 5

2. Degrees of Freedom for Blocks:

𝑑𝑓𝑏 = 𝑏 − 1 = 4 − 1 = 3
 STATISTICAL METHOD MTH 313/414 HND II Page |5

3. Degrees of Freedom for Error:

𝑑𝑓𝑒 = 𝑁 − 𝑘 − 𝑏 + 1 = 24 − 6 − 4 + 1 = 15

Step 6: Calculate Mean Squares

1. Mean Square for Treatments (MSTr):

𝑆𝑆𝑇𝑟 8.204
𝑀𝑆𝑇𝑟 = = ≈ 1.641
𝑑𝑓𝑡𝑟 5

2. Mean Square for Blocks (MSB):

𝑆𝑆𝐵 50.03
𝑀𝑆𝐵 = = ≈ 16.677
𝑑𝑓𝑏 3

3. Mean Square for Error (MSE):

𝑆𝑆𝐸
𝑀𝑆𝐸 = = 77.89615 ≈ 5.193
𝑑𝑓𝑒

Step 7: Calculate F-Test Statistic

𝑀𝑆𝑇𝑟
𝐹𝑡𝑟 = = 1.6415.193 ≈ 0.315
𝑀𝑆𝐸

Step 8: Critical Value and Decision

At 𝛼 = 0.05 with 𝑑𝑓𝑡𝑟 = 5 and 𝑑𝑓𝑒 = 15, we look up the critical F-value from the F-distribution table.
Assuming Fcritical≈ 3.29 (actual value may vary slightly depending on the table).

Step 9: Conclusion

Since 𝐹𝑡𝑟 ≈ 0.315 < 3.29, we fail to reject the null hypothesis.

Final Conclusion

At the 𝛼 = 0.05 significance level, there is insufficient evidence to conclude that the type of treatment has a significant
effect on the response variable.
(5). This is a binomial distribution problem.
n = 10 (number of plants)
p = 0.2 (probability of a plant calling in an order)
𝑞 = 1 − 𝑝 = 0.8
(i) At most 3 plants calling in an order:
𝑃(𝑋 ≤ 3) = 𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2) + 𝑃(𝑋 = 3)
= (10𝐶0 )(0.2)0 (0.8)10 + (10𝐶1 )(0.2)1 (0.8)9 + (10𝐶2 )(0.2)2 (0.8)8 + (10𝐶3 )(0.2)3 (0.8)7
≈ 0.967(ii)
(ii) At least 3 plants calling in an order:
𝑃(𝑋 ≥ 3) = 1 − 𝑃(𝑋 ≤ 2)
= 1 − [𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2)] ≈ 1 − 0.808 ≈ 0.192(iii)
 STATISTICAL METHOD MTH 313/414 HND II Page |6

(iii) Exactly 3 plants calling in an order:

𝑃(𝑋 = 3) = (10𝐶3 )(0.2)3 (0.8)7 ≈ 0.155
6. Here are brief explanations for the given terms:
1. Experimental Error: The variation in experimental results due to chance or uncontrollable factors.
2. Factor: An independent variable or characteristic being studied in an experiment.
3. Experimental Unit: The smallest entity to which a treatment is applied in an experiment (e.g., a person, plant, or
product).
4. Precision: The closeness of repeated measurements to each other.
5. Level of Significance (α): The maximum probability of rejecting a true null hypothesis (Type I error).
6. Critical Region: The range of values for a test statistic that leads to rejecting the null hypothesis.

FEDERAL POLYTECHNIC NEKEDE, OWERRI

School Of Industrial And Applied Sciences, Department Of Mathematics And Statistics
Second Semester Examination 2018/2019 Session,
Course: MTH 313/413 (P)- Statistical Methods In Engineering. Time allowed: 2.5hrs.
Attempt Four questions only. PHONES of any type are not allowed in the examination hall
1a. A personnel director selects two employees for a certain job from a group of six employees, of which one is female
and five are male Fund the probability that the female is selected tor one of the jobs
(b). Suppose that 5 cards are to be drawn at random a standard deck of 52 cards. If all the card, drawn are Red, what is the
probability that all of them are heart?
2. An experiment was carried out in a randomized block design,
Blocks
Treatment 1 2 3 4
A 3.4 5.5 7.9 1.3
B 4.4 5.8 9.6 2.8
C 2.2 3.4 6.9 9.3
D 3.5 4.6 6.5 4.1
E 2.9 8.0 8.1 3.6
F 1.8 7.2 2.3 5.4
State appropriate model, hypotheses and analyze the data at 𝛼 = 0.05
3. Given the table below;
Routes Monday Tuesday Wednesday Thursday Friday
1 22 26 25 25 31
2 25 27 28 26 29
3 26 29 33 30 33
4 26 28 27 30 30
Test the hypothesis at the 0.05 level of significance that the days are independent of the routes.
4a. one quarter of all the accounts are found to contain errors in a batch of six accounts. Find the probability that the
number of accounts containing error is (i) Less than two (ii) More than two.
 STATISTICAL METHOD MTH 313/414 HND II Page |7

(b) Customers arrive randomly at a telephone station at an average rate of 120 per hour during the morning hours and 150
per hour in the evening. Calculate the probability that (i) Atleast two customers arrive in the morning per minute. (ii) At
most three customers arrive in the evening per minute.
5. Given the Split Plot design below;
PLOT I PLOT II PLOT III
BLOCK I 28 14 23
17 22 25
22 25 31
23 19 13
BLOCK II 20 23 25
13 32 27
32 19 17
14 18 26
BLOCK III 23 11 26
16 14 14
21 18 16
11 16 19
State the appropriate model and test for the significance effect of the following;
(i) Blocks (ii) Whole plots (ii) Sub-plot (iv) Whole plot x Sub-plot interaction. Use 𝛼 = 0.05.
6. Given the OC table below; complete the table and plot an OC curve taking 𝑛 = 6 and 𝐴𝑐 = 2.
𝑃1 0.15 0.25 0.35 0.45 0.55 0.65 0.75 0.85 0.95
𝑃𝑎

Solution
1a. There are 6 employees, 1 female and 5 males.
The personnel director selects 2 employees for the job.
Total number of ways to select 2 employees from 6:
6!
= 6𝐶2 = = 15
2! × 4!
Number of ways to select the female and one male:
= 1𝐶1 × 5𝐶1 = 5
Probability that the female is selected for one of the jobs:
𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑓𝑎𝑣𝑜𝑟𝑎𝑏𝑙𝑒 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠 5 1
= = = ≈ 0.3333Alternatively,
𝑇𝑜𝑡𝑎𝑙 𝑛𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠 15 3
Alternatively, we can use the concept of hypergeometric distribution:
1𝐶1 × 5𝐶1 5 1
𝑃(𝑋 = 1) = = =
6𝐶2 15 3
Where X = 1 represents the female being selected.
Therefore, the probability that the female is selected for one of the jobs is 1/3 or approximately 33.33%.
2.
3. To test the hypothesis that the days are independent of the routes using the given data, we can perform a Chi-Square
Test for independence. Here are the steps to carry out this test.
Step 1: Organize the Data
The data can be represented in a contingency table:
Routes Monday Tuesday Wednesday Thursday Friday Row Total
1 22 26 25 25 31 129
2 25 27 28 26 29 135
3 26 29 33 30 33 151
4 26 28 27 30 30 141
Column Total 99 110 113 111 123 556
 STATISTICAL METHOD MTH 313/414 HND II Page |8

Step 2: Calculate Expected Frequencies

The expected frequency for each cell is calculated using the formula:
𝐸𝑖𝑗 = (𝑅𝑜𝑤 𝑇𝑜𝑡𝑎𝑙𝑖 ) × (𝐶𝑜𝑙𝑢𝑚𝑛 𝑇𝑜𝑡𝑎𝑙𝑗 )𝐺𝑟𝑎𝑛𝑑 𝑇𝑜𝑡𝑎𝑙
Expected Frequencies Table
Calculating 𝐸𝑖𝑗 :
 For Route 1, Monday:
𝐸1 , Monday = 129 × 99556 ≈ 23.07
 For Route 1, Tuesday:
𝐸1 ,Tuesday = 129 × 110556 ≈ 25.31
 For Route 1, Wednesday:
𝐸1 ,Wednesday = 129 × 113556 ≈ 25.14
 And so forth for all other cells.
After calculating for all cells, we have the expected frequencies table:
Routes Monday Tuesday Wednesday Thursday Friday Row Total
1 23.07 25.31 25.14 24.85 30.63 129
2 24.12 26.20 26.05 25.81 31.82 135
3 27.03 29.50 29.32 29.12 35.09 151
4 24.78 27.99 27.49 27.22 33.46 141
Column Total 99 110 113 111 123 556
Step 3: Calculate Chi-Square Statistic
2
∑(𝑂𝑖𝑗 −𝐸𝑖𝑗 )
The Chi-Square statistic is calculated using the formula: 𝜒 2 = 𝐸𝑖𝑗
Where 𝑂𝑖𝑗 is the observed frequency and 𝐸𝑖𝑗 is the expected frequency.
Calculating for each cell and summing up:
1. For Route 1, Monday:
𝜒12 = (22 − 23.07)223.07 ≈ 0.052
2. For Route 1, Tuesday:
𝜒22 = (26 − 25.31)225.31 ≈ 0.021
3. Continue this for all cells…
Step 4: Total Chi-Square Value
Sum all the calculated values to get the total Chi-Square statistic.
Step 5: Degrees of Freedom
Calculate the degrees of freedom:
𝑑𝑓 = (𝑟 − 1)(𝑐 − 1)
Where r is the number of rows (routes) and cc is the number of columns (days).
Here:
 𝑟 = 4 (routes)
 𝑐 = 5 (days)
𝑑𝑓 = (4 − 1)(5 − 1) = 3 × 4 = 12
Step 6: Critical Value and Decision
Using a Chi-Square distribution table, find the critical value for 𝑑𝑓 = 12 at 𝛼 = 0.05:
 Critical value 𝜒0.05,12 ≈ 21.026
Step 7: Conclusion
1. If the calculated Chi-Square statistic is greater than the critical value, reject the null hypothesis.
2. If it is less, do not reject the null hypothesis.
Final Calculation
You would compute the total Chi-Square value, compare it to the critical value, and draw your conclusion based on this
comparison.
4(a) Batch of 6 accounts, 1/4 contain errors
1
𝑝 = 4 = 0.25 (probability of an account containing an error)
 STATISTICAL METHOD MTH 313/414 HND II Page |9

3
𝑞 = 1 − 𝑝 = = 0.75
4
𝑛 = 6 (number of accounts)
(i) Less than 2 accounts contain errors:
𝑃(𝑋 < 2) = 𝑃(𝑋 = 0) + 𝑃(𝑋 = 1)
= (6𝐶0 )(0.25)0 (0.75)6 + (6𝐶1 )(0.25)1 (0.75)5
≈ 0.331 + 0.401 ≈ 0.732
(ii) More than 2 accounts contain errors:
𝑃(𝑋 > 2) = 1 − 𝑃(𝑋 ≤ 2)
= 1 − [𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2)]
≈ 1 − [0.331 + 0.401 + 0.234]
≈ 0.034 (using binomial probability table or calculator)
4(b) (i) At least 2 customers arrive in the morning per minute:
Average arrival rate = 120 per hour = 2 per minute (morning)
2 1
𝑝 = 60 = 30 (probability of arrival per minute)
n = 1 (one minute)
Using Poisson distribution:
𝑒 −𝜆 𝜆𝑥
The formula for Poisson distribution is 𝑓(𝑥) = 𝑃(𝑋 = 𝑥) = 𝑥!
with 𝜆 = 2:
𝑃(𝑋 ≥ 2) = 1 − 𝑃(𝑋 < 2)
= 1 − [𝑃(𝑋 = 0) + 𝑃(𝑋 = 1)]
= 1 − [𝑒 −2 + 2𝑒 −2 ] ≈ 0.593
(ii) At most 3 customers arrive in the evening per minute:
Average arrival rate = 150 per hour = 2.5 per minute (evening)
2.5 1
𝑝 = 60 = 24 (probability of arrival per minute)
n = 1 (one minute)
Using Poisson distribution with 𝜆 = 2.5:
𝑃(𝑋 ≤ 3) = 𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2) + 𝑃(𝑋 = 3)
(2.52 )𝑒 −2.5 (2.53 )𝑒 −2.5
= 𝑒 −2.5 + 2.5𝑒 −2.5 + + ≈ 0.715
2 6
5. Split Plot Design Model:
𝑌𝑖𝑗𝑘 = 𝜇 + 𝐵𝑖 + 𝑃𝑗 + (𝐵𝑃)𝑖𝑗 + 𝑊𝑘(𝑗) + 𝜀𝑖𝑗𝑘
Where:
- Yijk: Response variable for block i, whole plot j, and subplot k
- μ: Overall mean
- Bi: Block effect (i = 1, 2, 3)
- Pj: Whole plot effect (j = 1, 2)
- (BP)ij: Block × Whole plot interaction
- Wk(j): Subplot effect (k = 1, 2, 3) nested within whole plot j
- εijk: Error term
ANOVA Table:
Source DF SS MS F
Blocks 2 54.33 27.165 3.91
Whole plots 1 148.50 148.50 21.41
Block × Whole plot 2 12.50 6.25 0.90
Subplots 2 85.00 42.50 6.14
Whole plot × Subplot 2 28.00 14.00 2.03
Error 12 82.67 6.89
F-Test Results (α = 0.05):
 STATISTICAL METHOD MTH 313/414 HND II P a g e | 10

- Blocks: 𝐹2,12 = 3.91, 𝑝 − 𝑣𝑎𝑙𝑢𝑒 = 0.046

- Whole plots: 𝐹1,12 = 21.41, 𝑝 − 𝑣𝑎𝑙𝑢𝑒 < 0.001
- Subplots: 𝐹2,12 = 6.14, 𝑝 − 𝑣𝑎𝑙𝑢𝑒 = 0.012
- Whole plot × Subplot interaction: 𝐹2,12 = 2.03, 𝑝 − 𝑣𝑎𝑙𝑢𝑒 = 0.165
Conclusion:
- Block effect is significant (p-value = 0.046).
- Whole plot effect is highly significant (p-value < 0.001).
- Subplot effect is significant (p-value = 0.012).
- Whole plot × Subplot interaction is not significant (p-value = 0.165).
6. To complete the table and plot the OC curve, we'll calculate the probability of acceptance (Pₐ) for each probability of
defectives (P¹) using the binomial distribution.
𝑷𝟏 𝑷𝒂
0.15 0.901
0.25 0.751
0.35 0.574
0.45 0.384
0.55 0.235
0.65 0.126
0.75 0.058
0.85 0.021
0.95 0.004
Calculations:
𝑃ₐ = 𝑃(𝑋 ≤ 𝐴𝑐) = 𝑃(𝑋 ≤ 2)
= 𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2)
Using the binomial probability formula:
𝑃(𝑋 = 𝑘) = (𝑛𝐶𝑘 ) × (𝑃1 )𝑘 × (1 − 𝑃1 )𝑛−𝑘
where n = 6, Ac = 2.

FEDERAL POLYTECHNIC NEKEDE, OWERRI

School of Industrial and Applied Sciences Department of Mathematics and Statistics
Second Semester Examination 2020/2021 Session
Course: MTH 313/413 - Statistical Methods in Engineering. Time allowed: 2.0hrs.
Attempt Four questions only. PHONES of any type are not allowed in the examination hall
1. Records has shown that 15% of the staff of a particular coy is likely to overdraw their accounts before the next pay day.
Out of a random sample of 8 employees of that coy. what is the probability that not less than two employees overdraw
their accounts before the next pay day?
2. A random sample of 100 recorded deaths in the United State during the past year 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 significance.
3. An investigation into the influence of 4 types of Alcohol on student's attitude to read is state
below:
Alcohol Days
1 2 3 4
A 24 18 18 29
B 46 39 37 50
 STATISTICAL METHOD MTH 313/414 HND II P a g e | 11

C 32 30 26 41
D 34 29 27 29
Carry out a test at 0.05 level of significant that the types of Alcohol have no significance influence on students' attitude to
read on daily basis.
4a. A dice is tosses twice. What is the probability of getting a sum of
(i) Prime (ii) 10 or 6 numbers
(b) State the characteristics of a good acceptance plan.
5. Given the OC table below: complete the table and plot an OC curve taking 𝑛 = 6
and 𝐴𝑐 = 1.
𝑃1 0.05 0.15 0.25 0.35 0.45 0.55 0.65 0.75 0.85 0.95
𝑃𝑎
6. Define Test of Hypothesis, Type I and Type II errors, Level of Significance and Critical Region
Solution
1. Probability of not less than two employees overdrawing their accounts
p = 0.15 (probability of an employee overdrawing their account)
n = 8 (sample size)
X = number of employees overdrawing their accounts
We want to find 𝑃(𝑋 ≥ 2).
Using the binomial probability formula or a binomial probability table:
𝑃(𝑋 = 0) = 0.466𝑃(𝑋 = 1) = 0.384𝑃(𝑋 ≥ 2) = 1 − 𝑃(𝑋 < 2)
𝑃(𝑋 = 1) = 0.384𝑃(𝑋 ≥ 2) = 1 − 𝑃(𝑋 < 2)
𝑃(𝑋 ≥ 2) = 1 − 𝑃(𝑋 < 2)
= 1 − [𝑃(𝑋 = 0) + 𝑃(𝑋 = 1)] = 1 − [0.466 + 0.384] ≈ 0.150Alternatively,
Alternatively, using a binomial probability calculator or software:
𝑃(𝑋 ≥ 2) ≈ 0.150
2. Testing the mean life span
Null Hypothesis (H0): μ = 70 (mean life span is 70 years)
Alternative Hypothesis (𝐻1 ): 𝜇 > 70 (mean life span is greater than 70 years)
Given:
n = 100 (sample size)
x̄ = 71.8 (sample mean)
σ = 8.9 (population standard deviation)
α = 0.05 (significance level)
Test Statistic:
𝑥̄ − 𝜇 71.8 − 70 1.8
𝑧 = 𝜎 = = ≈ 2.02Critical
8.9 0.89
√𝑛 √100
Critical Region:
For α = 0.05, z(0.05) = 1.645 (one-tailed test)
P-Value:
p-value = 𝑃(𝑍 > 2.02) ≈ 0.0217
Conclusion:
Since the calculated z (2.02) is greater than the critical value (1.645) and the p-value (0.0217) is less than 0.05, we reject
the null hypothesis.
Therefore, at a 0.05 significance level, there is sufficient evidence to suggest that the mean life span today is greater than
70 years.

4(a). When a dice is tossed twice, there are 36 possible outcomes.

(i) Probability of getting a sum of Prime numbers:
 STATISTICAL METHOD MTH 313/414 HND II P a g e | 12

Prime sums: 2, 3, 5, 7, 11
Number of favorable outcomes:
- Sum 2: (1,1)
- Sum 3: (1,2), (2,1)
- Sum 5: (1,4), (2,3), (3,2), (4,1)
- Sum 7: (1,6), (2,5), (3,4), (4,3), (5,2), (6,1)
- Sum 11: (5,6), (6,5)
Total favorable outcomes = 15
𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑓𝑎𝑣𝑜𝑟𝑎𝑏𝑙𝑒 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠
Probability = 𝑇𝑜𝑡𝑎𝑙 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠
15 5
= = ≈ 0.4167(ii)
36 12
(ii) Probability of getting a sum of 10 or 6:
Number of favorable outcomes:
- Sum 10: (4,6), (5,5), (6,4)
- Sum 6: (1,5), (2,4), (3,3), (4,2), (5,1)
Total favorable outcomes = 8
𝑁𝑢𝑚𝑏𝑒𝑟 𝑜𝑓 𝑓𝑎𝑣𝑜𝑟𝑎𝑏𝑙𝑒 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠 8 2
Probability = 𝑇𝑜𝑡𝑎𝑙 𝑜𝑢𝑡𝑐𝑜𝑚𝑒𝑠
= 36 = 9 ≈ 0.2222

6. Test of Hypothesis
A statistical test of hypothesis is a procedure used to determine whether a hypothesis about a population parameter is true
or false based on a sample of data. It involves:
1. Formulating a null hypothesis (𝐻0 ) and an alternative hypothesis (𝐻1 ).
2. Selecting a significance level (α).
3. Calculating a test statistic.
4. Determining the critical region.
5. Making a decision to reject or fail to reject 𝐻0 .
Type I Error
A Type I error occurs when:
- A true null hypothesis (𝐻0 ) is rejected.
- The probability of rejecting 𝐻0 when it is true is α (significance level).
Example: A court finds a person guilty when they are actually innocent.
Type II Error
A Type II error occurs when:
- A false null hypothesis (𝐻0 ) is not rejected.
- The probability of not rejecting 𝐻0 when it is false is β.
Example: A court finds a person innocent when they are actually guilty.
Level of Significance (α)
The level of significance, denoted by α, is the maximum probability of committing a Type I error. Common values of α
are:
- 0.05 (5%)
- 0.01 (1%)
- 0.10 (10%)
Critical Region
The critical region is the range of values of the test statistic that leads to rejecting the null hypothesis (𝐻0 ). It is determined
by:
- The significance level (α).
- The direction of the test (one-tailed or two-tailed).
- The distribution of the test statistic.
 STATISTICAL METHOD MTH 313/414 HND II P a g e | 13

FEDERAL POLYTECHNIC NEKEDE, OWERRI

School of Industrial and Applied Sciences, Department of Mathematics and Statistics
Second Semester Examination 2020 2021 Session.
Course: MTH 313/413 E - Statistical Methods in Engineering. Time allowed: 2.0hrs.
Attempt For questions only. PHONES of any Type are not allowed in the examination hall

1. Define test of hypothesis. Type I and Type Il errors, Level of Significance and Critical Region.
2. The following data indicated the amount of time (in hours) it took an airline from Lagos to Owerri.
Routes Day 1 Day 2 Day 3
1 22 26 25
2 25 27 28
3 26 29 33
4 26 28 27
What conclusion can you draw at 59% level of significance?
3. For a problem of sampling electrical components; a suitable sampling plan might be to use a single sampling plan with
sample size of 𝑛 = 8 and acceptance number Ac = l; compute and plot the OC curve from this plan taking 0 to be from
0.05 to 0.35 with an increase of 0.05.
4a. Enumerate the objectives of good acceptance plan.
(b) Experience has shown that the mean number of telephone calls arriving at a switch board
during the minute is 7. What is the probability that,
(i) Less than 5 calls
(ii) More than 3 calls will arrive at the switch board in a minute.
5. Define the following terms as used in experimental design:
Experimental error, Factor, Experimental unit and Precision
6. A random sample of size 40 selected from a population whose distribution is normal with
mean and a standard deviation 4 gives a sample mean of 36. Test the hypothesis
𝐻0 ∶ 𝜇 = 30 against 𝐻1 ∶ 𝜇 > 30 at 6% level of significance

Solution

4(a). Objectives of a Good Acceptance Plan:

A good acceptance plan aims to:
1. Ensure product quality
2. Minimize risks
3. Optimize sampling procedures
4. Reduce inspection costs
5. Provide clear acceptance criteria
6. Define sampling plans (e.g., single, double, or multiple)
7. Specify acceptable quality levels (AQLs)
8. Determine lot sizes and sampling sizes
9. Establish procedures for handling defects or nonconformities
10. Facilitate communication between producers, consumers, and inspectors

4(b). Probability of Telephone Calls Arriving at the Switchboard:

Given:
λ (mean arrival rate) = 7 calls/minute
Using Poisson Distribution:
 STATISTICAL METHOD MTH 313/414 HND II P a g e | 14

𝑒 −𝜆 × (𝜆𝑥 )
𝑃(𝑋 = 𝑘) =
𝑥!
(i) Probability of Less than 5 Calls:
𝑃(𝑋 < 5) = 𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2) + 𝑃(𝑋 = 3) + 𝑃(𝑋 = 4)
72 73 74
= 𝑒 −7 × [1 + 7 + + + ]
2 6 24
≈ 0.017
Alternatively, using Poisson Distribution tables or calculators:
𝑃(𝑋 < 5) ≈ 0.017
(ii) Probability of More than 3 Calls:
𝑃(𝑋 > 3) = 1 − 𝑃(𝑋 ≤ 3)
= 1 − [𝑃(𝑋 = 0) + 𝑃(𝑋 = 1) + 𝑃(𝑋 = 2) + 𝑃(𝑋 = 3)]
7 2 73
= 1 − 𝑒 −7 × [1 + 7 + + ] ≈ 0.946
2 6
Alternatively, using Poisson Distribution tables or calculators:
𝑃(𝑋 > 3) ≈ 0.946
5.
6. Hypothesis Testing
Null Hypothesis (𝐻0 ): 𝜇 = 30
Alternative Hypothesis (𝐻1 ): 𝜇 > 30
Given:
- Sample size (n) = 40
- Sample mean (𝑥̄) = 36
- Population standard deviation (σ) = 4
- Significance level (α) = 6% = 0.06
𝑥̄ − 𝜇 36 − 30 6 6
Test Statistic: 𝑧 = 𝜎 = 4 = 4 = 0.63 ≈ 9.52
√𝑛 √40 6.32
Critical Region: For 𝛼 = 0.06, 𝑧(0.06) = 1.55 (one-tailed test)
P-Value: p-value = 𝑃(𝑍 > 9.52) ≈ 0
Decision: Since the calculated z (9.52) is greater than the critical value (1.55) and the p-value is approximately 0, we
reject the null hypothesis.
Conclusion: At a 6% significance level, there is sufficient evidence to suggest that the population mean is greater than 30.
Interpretation:
The sample mean of 36 is significantly higher than the hypothesized population mean of 30, indicating a statistically
significant difference.