STAT201A - Research Enquiry: Sublime Delight Case Analysis Report

This report presents a comprehensive analysis of the Sublime Delight coffee business, focusing on sales and profit distribution across its various outlets (external customers, internal carts, and mobile outlets). The analysis utilizes the BADIR methodology (Business question, Analysis plan, Data collection, deriving of insights and Recommendations) to assess sales data, profit margins, and the effectiveness of different sales channels. Statistical tests, including t-tests and ANOVA, are employed to compare service and coffee quality between internal cart outlets. Furthermore, the report examines the bean mix supplied to external outlets, comparing actual mix proportions to market predictions and forecasting future market mixes. Key findings highlight the importance of external customer and internal cart outlets for maximizing sales and profits, while also revealing deviations from predicted market mixes. The report concludes with recommendations for optimizing resource allocation, improving service and coffee quality, and adjusting the bean mix to align with market demands.

STAT201A – Research Enquiry for
Managers
A case analysis on Sublime Delight
A pitch perfect summary is required whenever one aims at selling an idea to a potential
investor. (Markowitz, 2010). It is read before a decision is made in whether the investor
will bother reading the rest of the document. (Markowitz, 2010)
Executive Summary
Sublime delight is a rapidly growing coffee roaster and coffee supplier and a supply outlet
owned by David Geoffs. Three main products were produced with time, Espresso Delight,
Mocha Delight, and Sublime Delight. The products have admirable qualities such as long
shelf lives, consistent in flavor and are easy to grind. The company has been able to
maintain an outstanding coffee product and has experienced a more manageable and cost
effective process of production. Eighteen months ago the management branched out into
coffee cart operations and three mobile units. The main use of the mobile units being
supply to building sites, commercial areas and office suits on a regular basis and event
catering.
The company has however faced challenges in the general management. Geoff discovered
that he was increasingly spending a lot of time on the general business management. He
therefore decided to recruit a general manager who later left for Australia leaving a big
mess at Sublime Delight
The distribution of sales reveals that the external customers have the highest sales record
from March to December. The Internal carts outlets records the highest sale in the month of
January and February. The mobile outlet has the lowest number of sales all through the
year. The company should therefore consider concentrating on the External outlet and the
Internal carts and close down the mobile outlet as a way of managing their resources.
Considering the distribution of profits across the three outlets, the internal carts contribute
the highest profits to the company in the month of January and February. However, as from
March to December, the external customers outlet contributes to the highest profits level
with a maximum of $20000 in the month of December. Throughout the year, the mobile
outlet has the lowest contribution to the company’s profits. Since the main purpose of every

business is to maximize on the profits (Saleemi, 2009), Sublime delight should therefore
concentrate more on the External customer outlet where they can make more profits and
also on the internal carts outlets. Resources should therefore not be wasted on the mobile
outlets whose profit margin is very low.
Introduction
Evidence for the solutions given will be provided by workings from Excel. The datasets
provided will be investigated using the BADIR methodology in order to find the most
appropriate and useful information required from the datasets. BADIR stands for the
Business question, Analysis plan, Data collection, deriving of insights and
Recommendations.
Task 1
(I) Sales distribution among the outlets
Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
0
100
200
300
400
500
600
700
800
900
1000
Distribution of sales across outlets
per month.
External Customers
Internal Carts
Mobiles
Results above show the distribution of sales across all the three outlets. The external
customer outlet is on average high across the months compared to the internal carts and the
mobiles. The maximum distribution of sales in the External customers is 905 kg and the
minimum is 626kg. Sales in the internal carts are highest in the months of January and

February. The maximum sales are 837kg and the minimum is 665kg. The mobile outlet has
the least sale distributions all along the year with an average sale distribution of 200kg. The
lowest sale distribution for this outlet is 186kg and the highest is 238kg. Highest sales are in
the month of December for all the outlets.
We recommend the company to invest more in the external customer outlet since it records
the highest sales in the month of March to December. They should also concentrate on the
internal carts since they record the highest sale in the month of January and February.
In conclusion, the external customer and internal cart outlets seem to record highest sales in
the month of December. The company should either find more building sites, commercial
areas and office suits to supply to or close down the mobile outlets in order to increase sales
in the other two outlets.
(ii)Distribution of profits among the different outlets
Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec
0.0
5000.0
10000.0
15000.0
20000.0
25000.0
Distribution of profits
Externmal Customers
Internal carts
Mobiles
Month
Profits
The figure above shows the profits distribution among the three outlets. In the months of
January and February, Internal carts bring in most profits compared to the other outlets. As
from march to December, the external Customers record the highest profits with a
maximum of $20362.5 and a minimum of 11581.0.Internal carts outlet contributes a
maximum of $ 18825.0 to the Company’s profits and a minimum of $ 13965.0. The
mobile outlet is seemingly a low source of profits at an average of $ 3415.1 for this

organization throughout the year. Highest profits for the company are made in the month of
December by the External customer outlet and the internal carts outlet.
We recommend the company to concentrate more on the external customer outlets and the
internal carts in order to maximize their profits on their sales. The mobile outlets should be
closed down since they have very little profits.
In conclusion, the External outlets contribute largely to the profits obtained by the
organization. In the month of December, many orders are made in both the internal cart
outlet and the external customer outlet.
Task 2
Here, our main aim is to find out whether there is a significant difference between the two
internal cart outlets in terms of service quality and the coffee quality. Using the BADIR
methodology on this dataset, we discover that we only need the three columns with the
outlet, service quality and the coffee quality to address this task.
(1)We first check whether the two outlets are significantly different in terms of service
quality. Setting our null hypothesis H0: The two outlets are the same in terms of service
quality and the alternative as H1: The two outlets are different in terms of service quality.
Using 5% as the level of significance, we proceed to do a one way analysis of variance in
excel for the two outlets. The results are equally the same as if we did an independent two
sample t-test (Henry, 2010).
The variable of interest is service quality measured on a scale and the factor being studied is
outlet. The outlets are classified into two categories.
t-Test: Two-Sample Assuming Unequal Variances
Outlet Service
Mean 1.506173 3.938272
Variance 0.253086 1.183642
Observations 81 81
Hypothesized Mean Difference 0

df 113
t Stat -18.2615
P(T<=t) one-tail 8.33E-36
t Critical one-tail 1.65845
P(T<=t) two-tail 1.67E-35
t Critical two-tail 1.98118
From the results above, the pvalue is 1.67E-35 which is less than 0.05. We therefore reject
the null hypothesis and conclude that the two internal cart outlets are significantly
different in terms of service quality at a 5% level of significance.
(2) We proceed to check whether the two internal carts are significantly different in terms
of coffee quality. We set our null hypothesis H0: The two outlets are the same in terms of
coffee quality and the alternative as H1: The two outlets are different in terms of coffee
quality. Using 5% as the level of significance, we do an independent two sample t-test
assuming unequal variances in excel.
The independent two sample t test is oftenly used to test whether population means are
significantly different from each other using the means from randomly drawn samples.
(Boneau, 1960). The assumptions for this test are that the population from which the
samples have been drawn should be normal (Boneau, 1960), and that the samples must
have been randomly drawn independent of each other.
In excel we click on data, data analysis then choose the T test: two samples assuming
unequal variance.
t-Test: Two-Sample Assuming Unequal Variances
Outlet Coffee
Mean 1.506173 4.024691
Variance 0.253086 0.824383
Observations 81 81
Hypothesized Mean Difference 0

df 125
t Stat -21.8366
P(T<=t) one-tail 8.72E-45
t Critical one-tail 1.657135
P(T<=t) two-tail 1.74E-44
t Critical two-tail 1.979124
The above results give a p value of 1.74E-44 which is less than 0.05. We therefore reject
the null hypothesis and rule in favor of the alternative hypothesis. We conclude that there
is a significant difference between the two internal coffee outlets in terms of coffee
quality at 5% level of significance. We obtain the same results if we used a one way
anova.
We recommend that the company makes use of both of the internal carts since they are
significantly different in terms of service quality and coffee quality at 5%. The company
should investigate the internal cart with the poor service quality and recruit new staff or
train them on how to improve their services. The staff working in the outlet with good
services should be rewarded as a source of motivation. The coffee quality should also be
checked to ensure that the mixtures are done correctly.
In conclusion, the two internal carts are significantly different in terms of service quality
and coffee quality.
Task 3
Dataset 3 shows the type of bean mix that is supplied to external outlets in January and
December 2015. A market analysis that was conducted in the year 2014 shows that the
mix would be 30% Espresso, 10% Mocha and 60 % Sublime. Our aims are to investigate
whether this prediction indeed holds for the month of January, December, whether the
taste mix has changed overall between January and December and to forecast the new
expected market mix based on the December data.
To address these aims, we proceed as follows.

(1). Investigating whether the mix proportions prediction holds for January.
On average, the mix proportion for the month of January is:
26.164
6
:17.3591
4
:56.4762598
6
For Espresso, Mocha and Sublime respectively.
Basing on the orders, order 1,4,13 and 14 are close to the predicted ratio. The rest of the
orders experience a significant deviation resulting to an average mix of 26.1646%
Espresso, 17.35914% Mocha and 56.47625986% Sublime. This implies that the mix
proportion fails to hold for the month of January.
(2) Investigating whether the mix proportions prediction holds for December.
None of the orders in December holds the predicted mix proportions of 30% Espresso,
10% Mocha and 60% Sublime. The average mix proportion for this month is
37.34819
18
:27.7373
7
:34.9144
4
For Espresso, Mocha and Sublime respectively. A very significant deviation from the
predicted mixture leads to the conclusion that the mix proportion predictions fails to hold
for the month of December.
(3) Investigating whether the taste mix has changed between January and December.
January December Difference
Rate of
increas
e
Espress
o
26.1646041
8
37.3481917
7
11.1835875
9
42.7431
9
Mocha
17.3591359
5
27.7373689
3
10.3782329
8
59.7854
2
Sublim
e
56.4762598
6
34.9144392
9
-
21.5618205
7
-
38.1786
From the above data, we see that the taste mix has gradually changed from January to
December. Both espresso and Mocha have increased in the mix ratio as from January to

December. Espresso has increased with an average rate of 42.74319% from January to
December whereas Mocha has increased with an average rate of 59.78542% as from
January to December. Sublime has however decreased in proportion at an average rate of
38.1786% as from January to December. The results imply that the taste mix has
significantly changed since January to December.
(4) Prediction of the new expected market mix based on the December data.
Basing on the mix in the December data, the new expected market mix becomes 40.254:
28.325: 31.421. This is obtained from the forecast function on excel.
We recommend that the company checks on the proportion of espresso, mocha and
sublime in order to produce an appropriate mixture. The proportions have been deviating
from the predicted mixture proportions. This might be the reason as to why sales would
reduce and hence affect the margin of profit.
In conclusion, the proportions of espresso, mocha and sublime tend to deteriorate with
time. The mixture proportion in January is very different from the mixture proportions in
December. A serious action needs to be taken on the operations in this company lest the
sales reduce significantly.

References
Boneau, C., 1960. The effects of violations of assumptions underlying the T test, s.l.:
Psychological bulletin.
Henry, 2010. Independent two sample t-test. [Online]
Available at: explorable.com/independent-two-sample-t-test
[Accessed 17th August 2017].
Markowitz, E., 2010. How to write an executive summary, s.l.: Inc publishers.
Saleemi, N. A. (2009). Statistics Simplified. Nairobi: Saleemi Pubications LTD.
Bigalow, S. W. and Elliot, D. (2004). Day Trading With Candlesticks And Moving
Averages. Futures: News, Analysis & Strategies for Futures. Options & Derivatives Trade
rs 33 (14): 40‐42. [2]
Bowersox, D. J., Closs, D. J., and Bixby Cooper, M. (2002) Supply Chain Logistics
Management. New York: McGraw‐Hill Irwin. [3]
D’Attilio, D. F. (1989) Practical Applications of Trend Analysis in Business Forecasting.
Journal of the Academy of Marketing Science 25 (3): 9‐11. [4]
Taylor, J. W. (2004) Volatility Forecasting With Smooth Transition Exponential
Smoothing. International Journal of Forecasting, 20 (2): 273‐284. [5]
Vasilopoulos, A. (2005) Regression Analysis Revisited. Review of Business, 26 (3): 3646
ZhaoHui Tang & Jamie MacLennan, Data Mining with Excel 2005, page 153 [9]