The gross profit of the business was analyzed for all the 150 stores in the different states and the following results were realized. All the stores in total generated a combined profit of 140 Million.
Figure 1: Histogram showing the distribution of profits
The histogram is skewed to the right indicating that most of the stores did not make as much profit. Around 42 of the stores made profits between 0.018 and 0.458. 68 other stores managed profits in the range of 0.458 to 1.338 million. 22 stores made between 1.338 to 1.778 million. Only 2 stores made profits above 2.658 million.
2. Gross Profit by Sundays
The profits were further analyzed on the stores that opened on Sundays and the following results materialized.
Figure 2: Pie Chart showing the gross profits of stores that remained opened on Sundays and the ones that closed
From the above pie chart, it is evident that the stores that operated on Sundays made more profit than those that did not. The ones that remained open on Sundays made 92.713 Million which is roughly 66% of the total profit while the ones that closed on Sunday made the remaining 34% being only 47.3 Million.
3. Online Channels by Location
With this age of the internet, online sales have proven to be a big deal with most of goods being vended through the web. The following chart shows the distribution of the stores that made online sales.
Figure 3: Pie chart showing online channels by location
Of all the 150 stores, only 105 stores had online channels. The mall stores had the most online channels at 41% which is 43 stores. The strip and country malls followed closely with 30% and 29% respectively.
4. Wastage.
The wastage within the states was analyzed and the following results were found.
Figure 4: Pie chart showing overall wastage in the stores
From the above pie chart, 54% of the wastage was medium, 31% was high wastage while the remaining 15% was low wastage. The wastage was further analyzed by state and the following bar graph represents the results.
Figure 5: Bar graph showing the wastage by state
Table 1: Table showing the summary of wastage by state
From the graph and summary table above, New South Wales recorded the highest wastage counts at 40 counts, followed by Victoria at 30. South Australia however was the only state that had most of its stores (11 out of 22) recording high wastage.
5. Variation in Sales with other variables.
The sales of the stores are definitely influenced by other factors. Some of the factors that we analyzed in our study were number of staff, advertising expenses, hours trading and number of car spaces. We shall make a regression equation for each of the 4 factors in the form
Y = B0 + B1X where; Y is Sales in millions, B0 and B1 are coefficients.
i) Sales with Number of staff
We shall model a regression equation with sales being the dependent variable and number of staff the independent variable.
Table 2: Regression output of sales against number of staff
From the above regression output, the linear equation becomes:
Y = 0.581 + 0.18X
With the p-value of number of staff being less than 0.05, this is a significant factor affecting the sales of the stores. Also with an R2 Statistic of 0.54, it means that number of staff explains 54% of the variation in the equation.
ii) Sales with Advertising expenses
The following regression output was realized:
Table 3: Regression output of sales against advertising expenses
The resultant regression equation would be
Y = 5.145 + 0.044X
With the p-value of the number of staff being less than 0.05, advertising is a very significant variable that influences the sales. Also with the R2 Statistic being 0.84, it shows that advertising expenses account for 84% of the variation in the sales.
iii) Sales with Trading hours
The following regression output was realized:
Table 4: Regression output of sales against hours trading
The p-value of the trading hours variable is way greater than 0.05 indicating that hours of trading is not a significant variable in explaining the total sales of the stores.
iv) Sales with number of car spaces
The following were the regression output results.
Table 5: Regression output of sales against number of car spaces
The resultant regression equation would be
Y = 7.591 + 0.09X
Looking at the p-value (2.24E-14<0.05), it would be right to say that Number of car spaces is a significant variable in explaining the total sales done by the stores. However, having an R2 Statistic of 0.32, number of car spaces explains only 32% of the total variation in the sales.
Conclusion:
From the above computations, it would be prudent to say that advertising is the most important factor in determining the total sales of the stores. This is because it has the least p-value of all the 4 variables. On the other hand, trading hours is the least significant factor influencing the total sales of the stores.
Part 2: Email
TO: Grace Wong
FROM: Stephen Hennigsson
SUBJECT: Analysis of the stores data
Dear Grace
As requested in your mail, I managed to do an analysis of the stores and the following were the findings:
1. The total profit for all the stores amounted to 140 Million. The stores on average made a profit of 0.933 Million each. Most of the stores’ profits were in the range of 0.018 to 1.338 Million. Only a few stores (about 10) made profits above 2 million.
2. Opening on Sundays seems to have an added advantage on the profit made. Of the 150 stores, 93 of them opened on Sundays. 66% of the total profit which is about 93 Million came from the stores that remained open on Sundays. The remaining 34% which is about 47 Million was generated by the stores that did not operate on Sunday. It is therefore wise to make it compulsory that all our stores remain open 7 days a week
3. Of the 150 stores, 105 of them have online stores with the ones located at the malls having the biggest share at 41%. The strip and country malls follow closely with 30% and 29% respectively. It is therefore evident that the stores located at the malls are leading in setting up online stores.
4. The wastage in general is of concern as majority of the stores (81) reported medium wastage. 46 stores reported high wastage showing a not so good picture. Only 23 of the stores reported low wastage and this should be carefully looked into as wastage is expensive to the business. Of the 46 high wastage reports, Queensland and South Australia had the highest counts at 11 stores. New South Wales despite having the highest counts of medium wastage also recorded the highest counts of low wastage reports at 8 out of all its 40 stores.
5. Advertising, number of staff in a store and number of car spaces seem to have a direct influence in the total sales a store records. Number of car space seem not to have any significant influence to the total sales. Advertising is the most influencing factor explaining about 84% of the total variation in sales. Number of staff explains 54% of the total variation while the trading hours explain only 32%. Of the total variation. Hence advertising is the most important factor.
Kindly find the dashboard on the excel file attached together with this file
Sincerely,
Stephen Hennigsson,
Research and Analysis Department.
