Department of Economics

University of Dhaka

ASSIGNMENT
STATISTICS - II (ECON 106)

Submitted to
Submitted on

Dr Rushad Faridi November 08, 2022

Assistant Professor
Department of Economics
University of Dhaka
Submitted by

Aishe Sarkar
Roll # FM-135-015
Registration # 2020-912-491
Chapter # 8

Case Problem 3 | Metropolitan research Inc.

Metropolitan Research Inc., a consumer research organization, conducts surveys designed to evaluate a
wide variety of products and services available to consumers. In one particular study, Metropolitan looked
at consumer satisfaction with the performance of automobiles produced by a major Detroit manufacturer.
A questionnaire sent to owners of one of the manufacturer’s full-sized cars revealed several complaints
about early trans-mission problems. To learn more about the transmission failures, Metropolitan used a
sample of actual transmission repairs provided by a transmission repair firm in the Detroit area.

The following data show the actual number of kilometers driven for 50 vehicles at the time of transmission
failure:
136.913, 52.468, 95.679, 124.596, 52.347, 103.121, 52.235, 96.382, 63.271, 144.232, 151.598, 187.936,
149.407, 102.069, 105.558, 138.150, 103.526, 99.723, 109.409, 96.246, 163.746, 154.100, 195.255, 111.935,
119.510, 107.800, 64.362, 115.959, 40.331, 124.051, 112.504, 57.380, 119.750, 108.128, 190.576, 86.082,
127.584, 103.851, 139.682, 187.077, 60.870, 143.750, 118.006, 137.228, 222.225, 85.924, 137.708, 132.350,
124.760, 142.876

Managerial Report
1. Use appropriate descriptive statistics to summarize the transmission failure data.
2. Develop a 95% confidence interval for the mean number of kilometres driven until transmission
failure for the population of automobiles with transmission failure. Provide a managerial
interpretation of the interval estimate.
3. Discuss the implication of your statistical findings in terms of the belief that some owners of the
automobiles experienced early transmission failures.
4. How many repair records should be sampled if the research firm wants the population mean number
of kilometres driven until transmission failure to be estimated with a margin of error of 8000
kilometres? (Use 95% confidence.)
5. What other information would you like to gather to evaluate the transmission failure problem more
fully?

Answer

1. The descriptive stations for the number of miles driven for 50 vehicles at the name of transmission failure
is shown below.

[Continued]

[1]
The actual number of kilometers Descriptive Statistics Formula
85,092 Sum 3,667,015 Sum( x1,x2,... xN )
39,323 Average or Mean 73,340 Sum((x1,x2,... xN)/D4)
64,342 Count 50 Count(A2:A51)
74,276 Maximum 138,114 Max(A2:A51)
74,425
Minimum 25,066 Min(A2:A51)
37,831
Median 72,705 Average(A2:A51)
77,539
Variance 619946014.1 Var(A2:A51)
32,609
89,641 1st Quartile 60421 Quartile(A2:A51,1)
61,978 3rd Quartile 86575 Quartile(A2:A51,3)
66,998
67,202
89,341
88,798
59,465
94,219
67,998
40,001
118,444
73,341
77,437
116,803
59,817
72,069
53,500
85,288
32,534
92,857
101,769
25,066
79,294
138,114
64,090
63,436
95,774
77,098
64,544
53,402
32,464
65,605
121,352
69,922
86,813
85,586
59,902
85,861
69,568
35,662
116,269
82,256

[2]
From the descriptive statistics, we can observe that the date shows the variance is very large. So, the data
have more variability.

2. Here, our task is to construct a 95% Confidence Interval. We know that (1-α)% Confidence Interval for
the population SD is given by,
𝑠𝑠
�𝑥𝑥̅ ± 𝑡𝑡𝛼𝛼�2;𝑛𝑛−1 �
√𝑛𝑛

X� = Sample Mean1
s = Sample Standard Deviation
tα/2;n-1 = Critical Value
n = Sample Mean
α = Level of Significance
The table of calculations is provided below.

[3]
Number of Miles Driven (x) (x - x̄ ) (x - x̄ )2
85,092 11,752 138109504
39,323 -34,017 1157156289
64,342 -8,998 80964004
74,276 936 876096
74,425 1,085 1177225
37,831 -35,509 1260889081
77,539 4,199 17631601
32,609 -40,731 1659014361
89,641 16,301 265722601
61,978 -11,362 129095044
66,998 -6,342 40220964
67,202 -6,138 37675044
89,341 16,001 256032001
88,798 15,458 238949764
59,465 -13,875 192515625
94,219 20,879 435932641
67,998 -5,342 28536964
40,001 -33,339 1111488921
118,444 45,104 2034370816
73,341 1 1
77,437 4,097 16785409
116,803 43,463 1889032369
59,817 -13,523 182871529
72,069 -1,271 1615441
53,500 -19,840 393625600
85,288 11,948 142754704
32,534 -40,806 1665129636
92,857 19,517 380913289
101,769 28,429 808208041
25,066 -48,274 2330379076
79,294 5,954 35450116
138,114 64,774 4195671076
64,090 -9,250 85562500
63,436 -9,904 98089216
95,774 22,434 503284356
77,098 3,758 14122564
64,544 -8,796 77369616
53,402 -19,938 397523844
32,464 -40,876 1670847376
65,605 -7,735 59830225
121,352 48,012 2305152144
69,922 -3,418 11682724
86,813 13,473 181521729
85,586 12,246 149964516
59,902 -13,438 180579844
85,861 12,521 156775441
69,568 -3,772 1419631684

[4]
 35,662 -37,678 1419631684 x̄
116,269 42,929 1842899041 73,340
82,256 8,916 79495056
Sum = 3,667,015 Sum = 30377354689 n
50
(x-x̄ )2 / (n-1) = 619946014.1
Standard Deviation 24898.71511 n-1
49

⦿ The sample mean is,

3667015
𝑥𝑥̅ = = 73340.3
50

⦿ The sample SD is,

∑(𝑥𝑥− 𝑥𝑥̅ )2 30377354688.5000

s =� 𝑛𝑛−1
=� = 24898.7151
50 − 1

⦿ The level of significance is,

α = 1 - 0.95= 0.05

⦿ The critical value is,

(tα/2;n-1)
= t0.025;49
= 2.0096; [ using Excel function “=T.INV.2T.(0.05,49)” ]

⦿ Hence the 95% interval for the population mean is,

‣ Lower Limit
𝑠𝑠
�𝑥𝑥̅ − 𝑡𝑡𝛼𝛼�2;𝑛𝑛−1 �
√𝑛𝑛
24898.7151
= �73340.3 − (2.0096 × )�
√50

= 66264.0763

‣ Upper Limit
𝑠𝑠
�𝑥𝑥̅ + 𝑡𝑡𝛼𝛼�2;𝑛𝑛−1 �
√𝑛𝑛
24898.7151
= �73340.3 + (2.0096 × )�
√50

[5]
= 80416.5237
Hence, the 95% Confidence Interval is (66264.0763, 80416.5237).
Therefore, with 95% confidence, we can conclude that the mean number of miles driven until transmission
failure lies within (66264.0763 to 80416.5237) miles.

3. The following is the SPSS output.

Data of Actual Number of Miles Descriptive Statistics

85,092 Total Statistic 3667015
39,323 N Statistic 50
64,342 Range Statistic 113,048
74,276 Maximum Statistic 138,114
74,425 Minimum Statistic 25,066
37,831 Mean Statistic 73340
77,539 Standard Error 3521.210059
32,609 Standard Deviation 24898.71511
89,641 Variation 619946014.1
61,978 Square Root of N 7.071067812
66,998
67,202
89,341
88,798
59,465
94,219
67,998
40,001
118,444
73,341
77,437
116,803
59,817
72,069
53,500
85,288
32,534
92,857
101,769
25,066
79,294
138,114
64,090
63,436
95,774
77,098
64,544

[6]
 53,402
32,464
65,605
121,352
69,922
86,813
85,586
59,902
85,861
69,568
35,662
116,269
82,256

From the above output, mean is 73340 (approx.)

Which means that on an average the car driven transmission failure is 73340 miles.
Where the Standard Deviation is 24898.71511. shows that the variation between the car driven is much
high about 24898.71511 skewness – 0.260, which shows that the sample data of car is positively skewed,
but skewness is less about to symmetric also range is also the measure of variation, which is also high.

The histogram is also shows that sample of mile driven of car is normally distributed.

4. We know that,
Margin of error = Critical value × Standard error
Margin of error = 5000 (given)

[7]
Critical value = zα/2= z0.05/2= z0.025= 1.96 (z-table)

Standard error = σ�
√𝑛𝑛
‣ We have all of the values needed to compute for n (number of repair records to be sampled) except for σ
(standard deviation). To get the value of the standard deviation,

[Continued]

[8]
Number of Miles Driven (x) (x - x̄ ) (x - x̄ )2
85,092 11,752 138109504
39,323 -34,017 1157156289
64,342 -8,998 80964004
74,276 936 876096
74,425 1,085 1177225
37,831 -35,509 1260889081
77,539 4,199 17631601
32,609 -40,731 1659014361
89,641 16,301 265722601
61,978 -11,362 129095044
66,998 -6,342 40220964
67,202 -6,138 37675044
89,341 16,001 256032001
88,798 15,458 238949764
59,465 -13,875 192515625
94,219 20,879 435932641
67,998 -5,342 28536964
40,001 -33,339 1111488921
118,444 45,104 2034370816
73,341 1 1
77,437 4,097 16785409
116,803 43,463 1889032369
59,817 -13,523 182871529
72,069 -1,271 1615441
53,500 -19,840 393625600
85,288 11,948 142754704
32,534 -40,806 1665129636
92,857 19,517 380913289
101,769 28,429 808208041
25,066 -48,274 2330379076
79,294 5,954 35450116
138,114 64,774 4195671076
64,090 -9,250 85562500
63,436 -9,904 98089216
95,774 22,434 503284356
77,098 3,758 14122564
64,544 -8,796 77369616
53,402 -19,938 397523844
32,464 -40,876 1670847376
65,605 -7,735 59830225
121,352 48,012 2305152144
69,922 -3,418 11682724
86,813 13,473 181521729
85,586 12,246 149964516
59,902 -13,438 180579844
85,861 12,521 156775441
69,568 -3,772 1419631684

[9]
 35,662 -37,678 1419631684 x̄
116,269 42,929 1842899041 73,340
82,256 8,916 79495056
Sum = 3,667,015 Sum = 30377354689 n
50

(x-x̄ )2 / (n-1) = 619946014.1 n-1

Standard Deviation 24898.71511 49

‣ To compute for the number of repair records to be sampled:

Margin of error = Critical value × Standard error
24.898.7151
⇒ 5000 = 1.96 ×
√𝑛𝑛
24.898.7151
5000 1.96×
√𝑛𝑛
⇒ 1.96
= 1.96
24898.7151
⇒ 2551.0204 =
√𝑛𝑛

24898.7151
⇒ 2551.0204 × √𝑛𝑛 = × √𝑛𝑛
√𝑛𝑛

⇒ 2551.0204 × √𝑛𝑛 = 24898.7151

2551.0204 × √𝑛𝑛 24898.7151
⇒ =
2551.0204 2551.0204

⇒ √𝑛𝑛 = 9.7603
2
⇒ �√𝑛𝑛� = 9.76032

⇒ n = 95.26 (number of repair records to be sampled)

5. Other additional information that would be included:

The nature of the roads the vehicles were using- Some roads would result to faster transmission failures
e.g. rough roads up the ragged mountains and valleys which are dusty and would cause clogging of the
transmission filter which would consequently cause transmission failure.
What was the identifier cause of the transmission as low transmission fluid can result in serious
transmission? The data on what level of fluid it was when the transmission failure occurred.
Another important information is on maintenance. How frequent was the vehicle maintained? Routine
maintenance is an easy and proven way to extend the transmission life. Hence, data on routine maintenance
will be very significant.

[10]
Chapter # 9

Case Problem 2 | Ethical Behavior of Business Students of Bayview University

During the global recession of 2008 and 2009, there were many accusations of unethical behavior by Wall
Street executives, financial managers, and other corporate officers. At that time, an article appeared that
suggested that part of the reason for such unethical business behavior may stem from the fact that cheating
has become more prevalent among business students (Chronicle of Higher Education, February 10, 2009). The
article reported that 56% of business students admitted to cheating at some time during their academic
career as compared to 47% of nonbusiness students.
Cheating has been a concern of the dean of the College of Business at Bayview University for several years.
Some faculty members in the college believe that cheating is more widespread at Bayview than at other
universities, while other faculty members think that cheating is not a major problem in the college. To
resolve some of these issues, the dean commissioned a study to assess the current ethical behavior of
business students at Bayview. As part of this study, an anonymous exit survey was administered to a sample
of 90 business students from this year’s graduating class. Responses to the following questions were used
to obtain data regarding three types of cheating.

• During your time at Bayview, did you ever present work copied off the Internet as your own?
Yes _________ No _________
• During your time at Bayview, did you ever copy answers off another student’s exam?
Yes _________ No _________
• During your time at Bayview, did you ever collaborate with other students on projects that were supposed
to be completed individually?
Yes _________ No _________

Any student who answered Yes to one or more of these questions was considered to have been involved
in some type of cheating. A portion of the data collected follows. The complete data set is in the file
Bayview.

[11]
Managerial Report
Prepare a report for the dean of the college that summarizes your assessment of the nature of cheating by
business students at Bayview University. Be sure to include the following items in your report.
1. Use descriptive statistics to summarize the data and comment on your findings.
2. Develop 95% confidence intervals for the proportion of all students, the proportion of male
students, and the proportion of female students who were involved in some type of cheating.
3. Conduct a hypothesis test to determine if the proportion of business students at Bayview
University who were involved in some type of cheating is less than that of business students at
other institutions as reported by the Chronicle of Higher Education.
4. Conduct a hypothesis test to determine if the proportion of business students at Bayview
University who were involved in some form of cheating is less than that of non-business students
at other institutions as reported by the Chronicle of Higher Education.
5. What advice would you give to the dean based upon your analysis of the data?

Answer

1. Cheating is considered as if the students are cheating in any one form of cheating is involved.

Frequency Cheating
Gender No Yes Grand Total
Female 26 16 42
Male 27 21 48

Grand Total 53 37 90

Percentage of cheating:
No Yes Total
Female 61.9 38.1 100
Male 56.25 43.75 100
58.89 41.11 100

There are 90 students surveyed.

Out of 90 induvial, 37 (41.1%) are reported in any one form of cheatings involved.
Out of 48 males, 21 (43.75%) are reported in any one form of cheatings is involved.
Out of 42 females, 16 (38.1%) are reported in any one form of cheatings is involved.

2. Excel is used for the analysis. Using descriptive statistic to summarize the data and comment on the
findings. Cheating is considered as if the students are cheating in any one form of cheating is involved.
There are 90 students surveyed. Out of 90, 37 (41.1%) are reported in any one form of cheatings involved.
Out of 48 males, 21 (43.75%) are reported in any one form of cheatings is involved. Out of 42 females, 16
(38.1%) are reported in any one form of cheatings is involved.

[12]
 Frequency Cheating
Gender No Yes Grand Total
Female 26 16 42
Male 27 21 48

Grand Total 53 37 90

Percentage of cheating:
No Yes Total
Female 61.9 38.1 100
Male 56.25 43.75 100
58.89 41.11 100

Now, developing 95% Confidence Intervals (CI) for the proportion of all students, the proportion of male
students and the proportion of female students who were involved in some type of cheating.

95% Confidence for all students:

Sample × N sample of Population 95% CI
1 37900.411111 (0.3094.57, 0.512765)
95% Confidence Interval for all students (0.3095, 0.5128)

95% Confidence Interval for male students:

Sample × N sample of Population 95% CI
1 21480.437500 (0.297161, 0.577839)
95% Confidence Interval for male students (0 2972, 0.5778)

95% Confidence Interval for female students:

Sample × N sample of Population 95% CI
1 16420.380953 (0.234087, 0.527818)
95% Confidence Interval for female students (0.2341, 0.5278).

3. There are 90 pupils surveyed.

Out of 90, 37 (41.1%) are reported in any one form of cheatings involved. Out of 48 males, 21 (43.75%)
are reported in any one form of cheatings is involved. Out of 42 females, 16 (38.1%) are reported in any
one form of cheatings is involved.
Developing 95% confidence intervals for the proportion of all students, the proportion of male students
and the proportion of female students who were involved in some type of cheating.

[13]
95% Confidence for all students:
Sample × N sample of Population 95% CI
1 37900.411111 (0.3094.57, 0.512765)
95% Confidence Interval for all students (0.3095, 0.5128)

95% Confidence Interval for male students:

Sample × N sample of Population 95% CI
1 21480.437500 (0.297161, 0.577839)
95% Confidence Interval for male students (0 2972, 0.5778)

95% Confidence Interval for female students:

Sample × N sample of Population 95% CI
1 16420.380953 (0.234087, 0.527818)
95% Confidence Interval for female students (0.2341, 0.5278)

Using a hypothesis test to see if the percentage of Bayview University business students who engaged in
some form of cheating is lower than the percentage of business students who engaged in some form of
cheating is lower than the percentage of business students at other institutions, as reported by the chronicle
of Higher Education.
The null and alternative hypothesis are:
Ho: p= 0.56
Hα: p < 0.56

Test and Confidence Interval for One Portion:

Test of p = 0.56 vs p < 0.56
Sample × N Sample P 95% Upper Bound
Z-Value
1 37900.411111 0.496422 -2.85
P-Value
0.002

Using the normal approximation, Calculated z = -2.85, P = 0.002, which is significant at the 0.05 level.
The null hypothesis is rejected at the 0.05 level of significance. According to the Chronicle of Higher
Education, the proportion of Bayview University business students who were involved in some type of
cheating is lower than that of business students at other colleges.

[14]
4. As reported by the Chronicle of Higher Education, conduct a hypothesis test to see if the proportion of
Bayview University business students who were involved in some sorts of cheating is lower than that of
non-business students at other institutions.
The null and alternative hypothesis are:
Ho: p= 0.47
Hα: p‹ 0.47
Test and Confidence Interval for One Portion:
Test of p = 0.47 vs p < 0.47
Sample × N Sample p 95% Upper Bound
Z-Value
1 37900.411111 0.496422 -1.12
P-Value
0.131
Using the normal approximation,
Calculated z= -1.12, P= 0.131, which is significant at the 0.05 level. The null hypothesis is rejected at the
0.05 level if significance. According to Chronicle of Higher Education, the proportion of Bayview
University business students who were engaged in some sort of cheating is comparable to that of
nonbusiness students at other institutions.
Excel is used for the analysis. Using descriptive statistic to summarize the data and comment on the
findings. Cheating is considered as if the students are cheating in any one form of cheating is involved.

Frequency Cheating
Gender No Yes Grand Total
Female 26 16 42
Male 27 21 48

Grand Total 53 37 90

Percentage of cheating:
No Yes Total
Female 61.9 38.1 100
Male 56.25 43.75 100
58.89 41.11 100

For the proportion of all students:

p = 42/90 = 0.4666667
So, the lower bound is,

[15]
 𝑝𝑝 (1−𝑝𝑝) 0.4666667(1−0.4666667)
𝑝𝑝 − �𝑍𝑍 × � � = 0.4666667 − 1.96 × � = 0.3635954
𝑛𝑛 90

So, the upper bound is,

𝑝𝑝 (1−𝑝𝑝) 0.4666667(1−0.4666667)
𝑝𝑝 + �𝑍𝑍 × � � = 0.4666667 + 1.96 × � = 0.569738
𝑛𝑛 90

For the proportion of all male students:

p = 24/90 = 0.2666667
So, the lower bound is,

𝑝𝑝 (1−𝑝𝑝) 0.2666667(1−0.2666667)
𝑝𝑝 − �𝑍𝑍 × � � = 0.2666667 − 1.96 × � = 0.1753038
𝑛𝑛 90

So, the upper bound is,

𝑝𝑝 (1−𝑝𝑝) 0.2666667(1−0.2666667)
𝑝𝑝 + �𝑍𝑍 × � � = 0.2666667 + 1.96 × � = 0.3580296
𝑛𝑛 90

For the proportion of all female students:

p = 18/90 = 0.2
So, the lower bound is,

𝑝𝑝 (1−𝑝𝑝) 0.2(1−0.2)
𝑝𝑝 − �𝑍𝑍 × � � = 0.2 − 1.96 × � = 0.1173592
𝑛𝑛 90

So, the upper bound is,

𝑝𝑝 (1−𝑝𝑝) 0.2(1−0.2)
𝑝𝑝 + �𝑍𝑍 × � � = 0.2 + 1.96 × � = 0.2826409
𝑛𝑛 90

5. For analysis, Excel is utilized.

To summarize the data and remark on the results, using descriptive statistics.

Frequency Cheating
Gender No Yes Grand Total
Female 26 16 42
Male 27 21 48

Grand Total 53 37 90

Percentage of cheating:
No Yes Total
Female 61.9 38.1 100

[16]
 Male 56.25 43.75 100
58.89 41.11 100

There are 90 pupils surveyed. Out of 90, 37 (41.1%) are reported in any one form of cheatings involved.
Out of 48 males, 21 (43.75%) are reported in any one form of cheatings is involved. Out of 42 females, 16
(38.1%) are reported in any one form of cheatings is involved.
Creating 95% percent confidence intervals for the proportion of all students, the proportion of male
students and the proportion of female students.
The proportion of male students who were involved in some way and the proportion of female students
who were involved in some type of cheating. For all students, the confidence interval is 95%.
Sample × N Sample p 95 percent Confidence Interval
+1(3790) 0.411111 = (0.309457, 0.512765)
95% Confidence Interval for all student is (0.3095, 0.5128)
For male students, the 95% Confidence Interval,
Sample × N Sample p 95% Confidence Interval
1 21480.437500= (0.297161, 0.577839)
95% Confidence Interval for male students is (0.2972, 0.5778)
For female students, the 95% Confidence Interval is,
Sample × N Sample p 95% Confidence Interval
1 16420.380952 (0.234087, 0.527818)
95% Confidence Interval for female students is (0.2341, 0.5278)

THE END

[17]