MGSC5111-Assignment#1-Sumit Garg

Case Study: John Deer Equipment

DAY 7
In reviewing your previous reports, several questions came to your
manager’s mind. Use point and interval estimates to help answer these
questions.

1. What estimate, with reasonable assurance, can JD give customers

for response times to customer calls?

Answer

The point estimate is equal to the mean of all the quarter of response time
to customer calls
With this formula we can estimate the reasonable assurance.

John deer has given the data of two year (2019 and 2020) quarter wise and
which is based on how much time employee took the response to
customers. The estimate can be calculated with the average of all the
quarters and also with the estimate interval in which JD can give response
to customers.
Excel formula solution

The point estimate calculation is calculated with the mean of all quarter of 2019-2020

=AVERAGE(A4:A53) (Excel formula)

=
3.9 3.73 3.75 4.45 3.09 3.11 3.20 2.53
2

= 3.47 (ESTIMATE)

Standard Error = = 0.081885704

Upper limit = + Tvalue( s/sqrt(n) ) =0.16098134 + (1.9659273)*( 0.081783282)

= 3.630779987

Lower limit = + Tvalue( s/√ (n) ) =0.16098134 - (1.9659273)*( 0.081783282)

= 3.309220013
 CONCLUSION= As per above calculation J D can give the point estimate with
the customer is point estimate that 3.47 day the service or complaint will be
resolved by the employees and we have also calculated the interval estimate
as which the response can be given to customers between 3.30 and 3.63
days .As per interval estimate we can give response time to customers

2. For the data in worksheet Blade Weight, how many blade weights
must be measured to find a 95% confidence interval for the mean
blade weight with a sampling error of at most 0.05?

Answer-
JD has given the datasheet of 350 blade weights samples in which we can
measure the blade weights with the .95 confidence level and with the error
of .005.

If the sampling error is specified as 0.05

n=19
Conclusion -As per above calculation 19 blade weights to be measure at the level
of confidence 95 %.in which value of z is calculated as per 95 % confidence level
from z table and after this we used the above formula to get the appropriate
sample size which comes up with rounded of 18.35260 = 19 blade weights can be
measured by the company

Answer 2 b
With the sampling error of 0.05 the sample size comes up to 19 but now we
have to calculate the size with sampling error 0.02

If the sampling error is specified as 0.02

n=115
Conclusion -As per above calculation 115 blade weights to be measure at the
level of confidence 95 %.in which value of z is calculated as per 95 % confidence
level from z table and after this we used the above formula to get the appropriate
sample size which comes up with rounded of 114.703759 = 115 blade weights can
be measured by the company
 DAY 8
(Chap. 7): (30 marks) Your manager has identified some additional questions she would like to
answer using JD database.

1. Are there significant differences in ratings of specific product/service attributes in the

customer survey worksheet?

Answer

-As per attributes we have calculated the Anova test to determine the significant differences in ratings
of specific product/service attributes in the customer survey of JD Company

First we have to determine the H0 AND H1 for determine the difference between the
ratings.

H0=there are no significant difference between the rating of specific product/service attributes in
the customer survey

H1= There are significant difference between the rating of specific product/service attributes in
the customer survey

 F =23.6907
 F crit = 2.616088
 F > F crit
 P value =1.079
 Reject H0
 Conclusion- As per Anova table we can see the F value (23.6907) is greater
than F crit value(2.616089) .Then we reject the null hypothsis H0 because as
per anova result it clearly depict that there are significant difference between
the rating of specific product/service attributes in the customer survey.

2. Have the data in the worksheet Defects After Delivery changed significantly over the past
years? (5 mark)

Answer

JD want to reduce the defects after the delivery to improve the satisfaction among the customer
across all the regions .When we take the average defects per year it have been reduced up to
50 % if we compare between the defect of 2016 to 2020.

Note-
The average defects shows us reduction every year and improving the customer
satisfaction level

Further for determine the significant changes over the last 5 years with the anova test
where
 Hypothesis:

Ho= There are no significant changes in defect after delivery over

the past 5 year in company:

(µ1-µ2) =0

H1= there are significant changes in defect after delivery over the
past 5 years in the company:

(µ1- µ2) ≠0

 F =178.2154
 F crit = 2.5396
 Df = 59
 P value = 8.6782

Conclusion- F value is greater that F crit so it is evident that We reject the

null hypothesis. Yes, the data in the worksheet Defects after Delivery
changed significantly over the past five years. So we reject Null Hypothesis
 Chapter 7: day_8.3
3.Are there differences in employee retention due to gender, college
graduation status, or whether the employee is from the local area in the
data in the worksheet Employee Retention? (5 marks)

Jd want to analyze the differences in employee retention due to gender, college

graduation status, or whether the employee is from the local area for these .we
conduct = t-Test: Two-Sample Assuming Unequal Variances
 (H0): There is no difference in employee retention due of gender.
 (H1): There is a difference in employs retention due of gender.

Hypothesis determine on difference between population parameters to

equal, we conduct Two sample test (Two tailed t-test) unequal variance

Decision Rule: t> t(critic value), reject (H0)

 Here t critical is greater than t value (2.100 >- 0.0091).
 Decision is failing to reject null hypothesis.

CONCLUSION: We can easily determine with this the mean of

two variable is approx. 5.54 and 5.53 and as per the hypothesis
test we did the result comes up also we are failing to reject the
null hypothesis so we there is not difference in the employee
retention due to gender in the company.
 Null Hypothesis (H0) = There is no difference in
employee retention due to employee are graduate (µ1-µ2
=0)

 Alternate Hypothesis (H1) = There is difference in employee

retention due to employee are no graduate (µ1-µ2 ≠0)

Hypothesis determine on difference between population parameters

to equal, we conduct Two sample test (Two tailed t-test) unequal
variance

.
 Decision rule : t > t(critic value), reject null (H0)
 Here t critical is more than t value (2.0452 > -1.0788).
 Fail to reject null hypothesis.

CONCLUSION: we have conducted the hypothesis test to determine

whether the there is any significance difference in employee
retention due to college graduate or not .So we find that there is no
difference in employee retention due to college graduate.

 Null Hypothesis (H0) = there are no difference in employee due to

Employee is local .( µ1-µ2 =0)

 Alternate Hypothesis H1 = there are difference in employee

retention due to employee is not local (µ1- µ2) ≠0

Hypothesis determine on difference between population parameters

to equal, we conduct Two sample test (Two tailed t-test) unequal
variance
Decision Rule: t> t(critic value), reject
 Here we can see that critical value is more than t value (2.03224 > -
4.418).
 Therefore, we fail to reject (H0)

CONCLUSION: we have conducted the hypothesis test to determine

whether the there is any significance difference in employee
retention due to employee is local or not .So we find that there is
no difference in employee retention due to employee is local.
 Day 9 (Chap. 8)
a) Your manager provided you with prices for mover product in Europe for the past 5 years:
Year Mower price
($)
2016 105
2017 155
2018 170
2019 180
2020 180

Create a new worksheet in the database to compute gross revenues by month for Europe, for
mover product using the data in Mower Unit Sales.
Hint: the new worksheet must have three columns (month, mover unit sales, gross revenues for mover
sales).

b) Cost functions are often nonlinear with volume because production facilities are often able to
produce larger quantities at lower rates than smaller quantities. Using the data produced by the above
task, apply simple linear regression, and examine the residual plot. What do you conclude?

Answer A & B- we have calculated the gross revenue by month and

total revenue for Europe region which come up to $ 10720200. as per
excel sheet attached .after that we have applied the simple linear
regression on the Gross revenue by data analysis function of excel as
mention below

Europe Residual Plot

60000
40000
20000
Residuals

0
-20000200 400 600 800 1000 1200 1400 1600 1800
-40000
-60000
-80000
Europe
 300000

250000
R² = 0.764983876251491
200000
Revenue
150000
Revenue
100000 Power (Revenue)

50000

0
200 400 600 800 1000 1200 1400 1600 1800
Unit sale

Conclusion- We applied simple linear regression because there is only

one independent variable and as per residual plot no pattern with in
the data.

I have constructed the scatter chart with unit sale and the revenue with
this Revenue is increasing with the unit sales for maximizing the R2 I
used Power trend line to maximize the R square level =0.765
 Day 10 (Chap. 9):
An important part of planning manufacturing capacity is having a good forecast of sales
Your manager is interested in:

• Forecasting industry sales of tractors in each marketing region to assess future changes in
market share (Worksheet: Tractor Unit Sales).

Asnwers- In the work sheet tractor unit sales all the five region sales have
given and I have used the double exponential smoothing for the region
NA,SA and china region. Because there is trend in all three region we can
easily determine the forecasting.

In double exponential smoothing the below mention formula is used to

forecast

Lt = α Yt + (1 – α) [Lt –1 + Tt –1]

Tt = γ [Lt – Lt –1] + (1 – γ) Tt –1

FORECAST NA
3000

2500

2000

1500

1000

500

0
1 4 7 10 13 16 19 22 25 28 31 34 37 40 43 46 49 52 55 58
NA forcast
 SA FORECAST
1200

1000

800

600

400

200

0
1 5 9 13 17 21 25 29 33 37 41 45 49 53 57

SA forcast

China
forcast

160
140
120
100
80
60
40
20
0

CHINA FORECAST

In double exponential smoothing the below mention formula is used to

forecast

Formula
Lt = α Yt + (1 – α) [Lt –1 + Tt –1]

Tt = γ [Lt – Lt –1] + (1 – γ) Tt –1

alpha 0.6
beta 0.4
FOR Eur and pecific we used moving average method to forecast the sale of tractor

Moving Average EUR

1000
900
800
700
600
500 Actual
Value

400 Forecast
300
200
100
0
1 4 7 10 13 16 19 22 25 28 31 34 37 40 43 46 49 52 55 58

Data Point

Moving Average Pecific

400
300
200 Actual
Value

100 Forecast
0
1 4 7 10 13 16 19 22 25 28 31 34 37 40 43 46 49 52 55 58
Data Point
• Forecasting
future increases in production costs (Worksheet: Unit
Production Costs).

Answers-In this solution I have used the double exponential method to

forecast the production cost for the both tractor and mower products

With this forecasting method we come to know the cost of tractor and
mower will be in jan 21 is $2141 and $ 64.We can easily determine the
production cost for both the product has increased over a period of time.

We took alpha and beta level for use the double exponential smoothing .
alpha 0.6
beta 0.4

Tractor sale
$2,500
$2,000
$1,500
$1,000
$500
$0
1 4 7 10 13 16 19 22 25 28 31 34 37 40 43 46 49 52 55 58

Tractor forcast

Mower sale
$70

$60

$50

$40

$30

$20

$10

$0
1 4 7 10 13 16 19 22 25 28 31 34 37 40 43 46 49 52 55 58

Mower forcast