FACULTY OF BUSINESS AND MANAGEMENT

MARA University of Technology

Bachelor of Business Administration (Hons) Marketing

JBA2523A

GROUP ASSIGNMENT:
“Performance Lawn Equipment”

MGT 555 - Business Analytics

PREPARED BY:

NAME STUDENT ID

NURUL FARAHIN BINTI FAKHRUL ANWAR 2020813448

FATIN DIYANA SYAZWANI BINTI ISMAN 2020819628

MUGHNI NADIRAAISYAH BINTI NORLINA 2020872828

NURIN ZAWANAH BINTI BAHRAM 2020813534

PREPARED FOR:
DR. SUHAIDI ELIAS

DATE OF SUBMISSION: 20.01.2022

QUESTION 1

a. The total number of responses to each level of the survey across all regions for each
year.

The total number of responses to each level of survey scale across all regions for each year
were obtained using SUM functions [=SUM (data range)].

i) Dealer satisfaction

0 1 2 3 4 5 Total
2010 1 0 4 22 37 17 81
2011 0 0 5 23 39 20 87
2012 1 1 5 20 71 39 137
2013 1 3 8 19 72 87 190
2014 4 4 13 47 127 143 338
 Data Table 1.1

In 2010, the total number of responses at that time recorded 81 responses. Further, in 2011 the
number of responses for all scales was 87 responses. In 2012, the number of responses was 137
responses. The next in 2013 was 190. Finally, in 2014 recorded the highest number of 338.

ii) End-user Satisfaction

The total number of responses to each level of survey scale across all regions for each year
were obtained using SUM functions [=SUM (data range)].

Sample
North America 0 1 2 3 4 5 Size
2010 1 3 6 15 37 38 100
2011 1 2 4 18 35 40 100
2012 1 2 5 17 34 41 100
2013 0 2 4 15 33 46 100
2014 0 2 3 15 31 49 100

South America
2010 1 2 5 18 36 38 100
2011 1 3 6 17 36 37 100
2012 0 2 6 19 37 36 100
2013 0 2 5 20 37 36 100
2014 0 2 5 19 37 37 100

Europe
2010 1 2 4 21 36 36 100
2011 1 2 5 21 34 37 100
2012 1 1 4 26 37 31 100
2013 1 1 3 17 41 37 100
2014 0 1 2 19 45 33 100

Pacific Rim
2010 2 3 5 15 41 34 100
2011 1 2 7 15 41 34 100
2012 1 2 5 16 40 36 100
2013 0 2 4 17 40 37 100
2014 0 1 3 19 42 35 100

China
2012 0 3 3 6 28 10 50
2013 1 2 2 4 30 11 50
2014 0 1 1 3 31 14 50
 0 1 2 3 4 5 Total
2010 5 10 20 69 150 146 400
2011 4 9 22 71 146 148 400
2012 3 10 23 84 176 154 450
2013 2 9 18 73 181 167 450
2014 0 7 14 75 186 168 450

Data table 1.2

In 2010 and 2011 recorded the same number of responses, namely 400 responses.
Furthermore, in 2012, 2013 and 2014, a total of 450 responses were recorded.

b. Account of the number of failures in the worksheet Mower Test.

Sample
Observation 1 2 3 4 5 6 7 8 9 10
1 Pass Fail Pass Pass Pass Pass Pass Pass Pass Pass
2 Pass Fail Pass Pass Pass Pass Pass Pass Pass Pass
3 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
4 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
5 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
6 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
7 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
8 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
9 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
10 Pass Pass Pass Pass Pass Fail Pass Pass Pass Pass
11 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
12 Pass Fail Pass Pass Pass Pass Pass Pass Pass Pass
13 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
14 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
15 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
16 Pass Pass Pass Pass Pass Fail Pass Pass Pass Pass
17 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
18 Pass Pass Pass Pass Fail Pass Pass Pass Pass Pass
19 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
20 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
21 Pass Pass Pass Pass Pass Fail Pass Pass Pass Pass
22 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
23 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
24 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
25 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
26 Pass Fail Pass Pass Pass Pass Pass Pass Pass Pass
27 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
28 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
29 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
30 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass
31 Pass Pass Pass Pass Pass Pass Pass Pass Pass Pass

Number of failure in the worksheet mower test = 54

The calculation's formula is as follows:

=COUNT-IF (DATA RANGE, “Fail”)

According to the results of the calculation, the number of failures in the Mower Test
worksheet is 54.

c. The market share for each product and region based on the PLE and industry sales
data in the database.
d. Summarize the above findings in a report.

The total number of failures in the Mower Test is 54. 96,594,120 in Mower Unit Sales, with
gross revenues by month and region as well as global totals. 9.54 percent in Industry Mower
Total Sales, with market share for each product and region of 9.54 percent. Tractor Unit Sales
generates gross revenues of 570,880,750 dollars every month and per area, with global totals
of 570,880,750 dollars. Overall, 14.25 percent of Industry Tractor Total Sales is accounted for
by each individual product and location.

QUESTION 2:

Illustrate using appropriate charts for the data in the worksheet of:
a. Complaints

Complaints chart 2.1

The graphs show Complaints in 2010, with the biggest number of complaints coming from
North America in June 2010. In 2011, the biggest number of complaints came from North
America in May of that year. In 2012, the biggest number of complaints came from North
America in June. In 2013, the biggest number of complaints came from North America in June.
From January to December 2014, the biggest number of complaints was received in June 2014,
likewise from North America.
b. On time delivery

On time delivery Chart 2.2

In 2010, for On-Time Delivery. The number of deliveries and the number of deliveries on time
were highest in December 2010 and lowest in January 2010. In 2011, the highest was in
December of that year, and the lowest was in January of that year. From January to December
2012, the number of deliveries and the number of deliveries on time are highest in September
2012. The lowest point was in January of 2012. Which month had the highest number of
deliveries and the highest number of deliveries on time from January 2013 to December 2013?
The lowest point was in May of 2013. From January 2014 to December 2014, the number of
deliveries and the number of deliveries on time are at their peak in December 2014. The lowest
point was in February of 2014.
c. Defects After Delivery

Defects after Delivery Chart 2.3

The month with the most defects after delivery in 2010 was June, with 848 items. The month
with the most defects after delivery in 2011 was August, with 857 items. The month with the
most defects after delivery in 2012 was February, with 836 items. The month with the most
defects after delivery in 2013 was July, with 696 items. The month with the most defects after
delivery in 2014 was February, with 575 items.
d. Response

Response Time Chart 2.4

Response times to customer support calls reached an all-time high of 8.02 in the first quarter
of 2013. The average response time for customer support calls was 8.21 seconds in the second
quarter of 2013. Response times to customer support calls reached a record high of 6.76
seconds in the third quarter of 2013. The average response time for customer support calls was
8.93 seconds in the fourth quarter of 2013. Response times to customer support inquiries
reached a record high of 6.46 seconds in the first quarter of 2014. The response time for
customer support calls was 5.67 seconds in the second quarter of 2014. For customer support
calls, the average response time was 7.42 seconds in the third quarter of 2014. Responding to
service requests took the longest on average 4.87 minutes in the fourth quarter of 2014.
QUESTION 3:

i. Average of Quality

Average of Quality Column Labels

Row Labels 1 2 3 4 5 Grand Total

China 2 3 4 5 3.8

Eur 2 3 4 5 4.1

NA 1 3 4 5 4.6

Pac 3 4 5 4.4

SA 1 3 4 5 4.28

Grand Total 1 2 3 4 5 4.40

Average Quality Chart 3.1

This Pivot Table and Pivot Chart is showing the Average of Quality response from customers
in each market region. The highest scale of quality is in North America with a total of 4.6 and
China has the lowest average of quality with a total of 3.8.

ii. Average of Ease of Use

Average of Ease of Use Column Labels

Row Labels 1 2 3 4 5 Grand Total

China 3 4 5 4.1

Eur 3 4 5 4.33

NA 1 2 3 4 5 4.27

Pac 2 3 4 5 3.9

SA 1 2 3 4 5 3.92

Grand Total 1 2 3 4 5 4.17

Average of Ease-of-Use Chart 3.2

This Pivot Table and Pivot Chart shows the Average of Ease of use response from the
customers in each market region. The highest scale of Ease of Use is in Europe with a total 4.3
and Pacific has the lowest average of Ease of Use with 3.9.

iii. Average of Price

Average of Price Column Labels

Row Labels 1 2 3 4 5 Grand Total

China 2 3 4 3

Eur 1 2 3 4 5 3.9

NA 1 2 3 4 5 3.71

Pac 3 4 5 4.1

SA 1 2 3 4 5 3.5

Grand Total 1 2 3 4 5 3.67

Average of Price Chart 3.3

The Pivot Table and Pivot Chart shows the Average of Price response from customers in each
market region. The highest total scale of Price is at Pacific with total 4.1 and China has the
lowest average of price with 3.

iv. Average of Service

Average of Service Column Labels

Row Labels 1 2 3 4 5 Grand Total

China 1 2 3 4 2.6

Eur 1 2 3 4 5 3.87

NA 2 3 4 5 4.31

Pac 3 4 5 4.3

SA 1 3 4 5 4.24

Grand Total 1 2 3 4 5 4.14

Average of Service Chart 3.4

The Pivot Table and Pivot Chart shows the Average of Service response from customers in
each market region. The highest scale of Service is in North America with total 4.31 and China
has the lowest average of price with 2.6.

QUESTION 4:

Are there significant differences in ratings of specific service attributes in the 2014 Customer
Survey data? (Use Anova: Single Factor)

SUMMARY
Groups Count Sum Average Variance
Quality 200 879 4.395 0.581884422
Ease of Use 200 833 4.165 0.610829146
Price 200 734 3.67 1.13678392
Service 200 828 4.14 0.794371859

ANOVA
Source of Variation SS df MS F P-value F crit
Between Groups 55.505 3 18.50166667 23.69070484 1.079E-14 2.61608896
Within Groups 621.65 796 0.780967337

Total 677.155 799

i) p-value Approach
The F-statistic is 23.69, and the p-value is 0.000000000000011, which is less than the
threshold of 0.05. Consequently, we rule out the null hypothesis and conclude that there are
statistically significant variations in ratings of certain products or services.

ii) Critical -Value Approach

Specifically, the F-statistic value is 23.69, and the critical F-value is 2.616, indicating that the
F-statistic value is bigger than the critical F-value in this case. As a result, the null hypothesis
is rejected.
b. Have the data in the worksheet Defects After Delivery changed significantly over the
past 5 years? (Use Anova: Single Factor)

SUMMARY
Groups Count Sum Average Variance
2010 12 9916 826.33 135.33
2011 12 10049 837.42 121.54
2012 12 9431 785.92 2749.72
2013 12 8029 669.08 959.36
2014 12 5955 496.25 2940.02

ANOVA
Source of Variation SS df MS F P-value F crit
Between Groups 984600.33 4 246150.08 178.22 8.67824E-31 2.54
Within Groups 75965.67 55 1381.19

Total 1060566 59

i) p-value Approach
There is a significant difference between the F-statistic value and the p-value. The p-value is
0.0000000000000000000000000087, which is less than 0.05. So, the null hypothesis is
rejected, and we infer that the mean Defects After Delivery are not the same as the mean
Defects Before Delivery.

ii) Critical-Value Approach

It is calculated that the F-statistic value is 178.22 and the critical F-value is 2.54, indicating
that the F-statistic value is more than the critical F-value. As a result, the null hypothesis is
rejected.
C. Use regression analysis to evaluate the data of Employee Retention. Develop a
multiple regression model for predicting employee retention as a function of the other
variables.
Regression model

Regression Statistics
Multiple R 0.387559901
R Square 0.150202677
Adjusted R Square 0.079386234
Standard Error 2.725526994
Observations 40

ANOVA
df SS MS F Significance F
Regression 3 47.26784375 15.75594792 2.121014127 0.114635312
Residual 36 267.4259062 7.428497396
Total 39 314.69375

Coefficients Standard Error t Stat P-value Lower 95% Upper 95%

Intercept -2.73710846 4.504149393 -0.60768598 0.547210322 -11.87194682 6.397729904
YrsEducation -0.06705429 0.355164691 -0.18879775 0.851311676 -0.787361672 0.653253085
College GPA 0.679981319 1.183551377 0.574526237 0.569184814 -1.720372129 3.080334767
Age 0.291535813 0.135043927 2.158822092 0.037605843 0.017654035 0.56541759

We delete Gender, College Graduation, and Local variables from consideration before
conducting regression analysis because they are not in numerical form.

Regression Statistics
Multiple R 0.387559901 F-test
R Square 0.150202677 Hypothesis:
Adjusted R Square 0.079386234 H₀ : B₁ = B₂ = B₃ = 0
Standard Error 2.725526994 H₁ : at least one B is not 0
Observations 40

R-Squared (R2) is a mathematical function.

Employee Retention = -2.737 - 0.067 (years of education) + 0.680 (college GPA) + 0.292
(Age)

The Significance F is 0.115 which is greater than the significance level (0.05). Therefore, we
fail to reject the null hypothesis. This means that the Years of Education, College GPA and
Age are equal to zero. Therefore, none of the independent variables going to exert any effect
on the dependent variable.

ANOVA
df SS MS F Significance F
Regression 3 47.26784375 15.75594792 2.121014127 0.114635312
Residual 36 267.4259062 7.428497396
Total 39 314.69375

t-test
Hypothesis:
H₀ : B₁ = 0
H₁ : B₁ ≠ 0

The p-values of each independent variable are used to test the hypothesis of that variable.

With the exception of Age, all of the p-values are greater than 0.05. Consequently, the null
hypothesis for the coefficients of YearsEducation and College GPA fails to be rejected, and
we can conclude that they are not statistically significant. We reject the null hypothesis in the
case of Age and conclude that it is statistically significant.

Coefficients Standard Error t Stat P-value

Intercept -2.73710846 4.504149393 -0.60768598 0.547210322
YrsEducation -0.06705429 0.355164691 -0.18879775 0.851311676
College GPA 0.679981319 1.183551377 0.574526237 0.569184814
Age 0.291535813 0.135043927 2.158822092 0.037605843

Confidence Interval
Hypothesis:
H₀ : B₁ = 0
H₁ : B₁ ≠ 0

As you can see in the figure below, the confidence interval for each variable does not contain
a zero, which leads us to conclude that the coefficients are statistically significant.

Coefficients Standard Error Lower 95% Upper 95%

Intercept -2.73710846 4.504149393 -11.8719468 6.397729904
YrsEducation -0.06705429 0.355164691 -0.78736167 0.653253085
College GPA 0.679981319 1.183551377 -1.72037213 3.080334767
Age 0.291535813 0.135043927 0.017654035 0.56541759

d. Summarize the above findings in a report

 Following the ANOVA: Single Factor analysis, we use the results of the worksheet
2014 Customer Survey to interpret the information in the worksheet. In order to accomplish
this, we employ the p-value technique and the crucial value strategy. The F-statistic value for
the p-value approach is 23.69, and the p-value is 0.000000000000011, which is less than the
threshold of 0.05. For the p-value technique, the F-statistic value is 23.69, and the p-value is
0.000000000000011. (i.e., less than 0.05). We therefore reject the null hypothesis and come to
the conclusion that there are statistically significant differences in ratings of certain products
or services. Based on this assumption, the F-statistic value is 23.69, and the crucial F-value is
2.616, with the F-statistic value being more than the F-value in this example. As a result, the
null hypothesis is ruled out of the running.

We use the p-value approach and the critical value strategy to explain the findings from
the ANOVA: Single Factor analysis in the worksheet Defects After Delivery, which were
acquired from the data analysis. If we take the p-value approach, the F-statistic value is 178.22,
and the p-value is 0.00000000000000000000000000087, which is less than the threshold value
of 0.05. If we take the F-statistic value approach, the F-statistic value is 178.22, and the p-value
is 0.00000000000000000000000000087, which is less than the threshold value of 0.05. (0.05).
Because of this, we reject the null hypothesis and discover that the mean number of Defects
After Delivery has increased significantly over the past five years. It turns out that the F-
statistic value is 178.22, and the essential F-value is 2.54, which means that the F-statistic value
is greater than the F-value obtained using the critical-value method. As a result, the null
hypothesis is ruled out of the running.

The data from the Employee Retention worksheet, which was based on the data from
the Multiple Linear Regression Model, was analysed using regression analysis to better
comprehend the situation. The regression model YearsPLE(Y) = -2.7371 - 0.0671
YrsEducation + 0.6800 College GPA + 0.2915 Age may be computed based on the coefficients
obtained. The Years Education variable has a bigger impact on the YearsPLE than the other
factors, as can be observed from the model, when compared to the other variables. Because the
R2 value is 0.15, it is reasonable to assume that Years of Education, College GPA, and Age
account for approximately 15 percent of the variation in Years of PLE (Personal Learning
Experience). The fact that there are more variables influencing Years PLE in addition to Years
Education is demonstrated in this instance (including College GPA and Age). We can see,
however, that it is greater than the level of significance (0.05) when we look at the significance-
F (F-test), indicating that the null hypothesis is not rejected. Furthermore, the p-values for each
of the independent variables are calculated in order to evaluate each of the independent
variables' hypotheses individually.

There is a statistically significant difference between the independent variables Years

of Education and College GPA for all three variables (p-values larger than 0.05). The null
hypothesis cannot be ruled out as a result of our findings. The effect of age, on the other hand,
has a p-value that is less than 0.05. PLE employee retention has been found to be influenced
by only one variable, age, which is statistically significant when it comes to employee retention.
As a result, we reject the null hypothesis regarding age as a predictor of retention at the
organisation. The fact that the confidence interval does not contain a zero allows us to conclude
that the coefficients are statistically significant in this particular instance. It appears that the
criteria for linearity has not been met in this case.