Business ventures keeps changing overtime in various aspects including the finances, the customer base, the production capacity, and expansion in terms of reaching new markets. However, companies operations must be synchronized with the set standards to achieve the results. The production process must ensure that there are no defectives items reaching the markets to avoid defamation of the company reputation with its customers and even possible customers. Maintaining existing customers and even attracting more potential ones is sole aim why companies spend so much resources building the name through rigorous advertising campaigns and other marketing process. The management must also find strategies that will be unique with customers to boost its competitive advantage in the ever-evolving contemporary markets.
Managers need to realize the importance of data-driven decision-making process, that is, the days when managers made decision based on intuition longer gone and replaced by the data-driven age. Companies should stores information or rather collect data to evaluate the progress of performance along various lines of marketing, production, or even comparing incomes made during various quarters of the year. Data has proven important even in making future prediction on company and even the direction the entire economy will take and how that might affect the market demand and supply. With such predictive knowledge, managers can contingency measures that will tackle problematic futures. Statistical knowledge is needed to make sense of the collected data through exploration data analysis and inferential procedures. These statistical procedures include visualizations, predictive modeling, and market segmentation among many others. The current paper aims to evaluate a case study of the Toybox a national retailer of children toys through various statistical procedures to summarize and model data from the various departments of company that is suitable in managerial decision-making.
Overview of the Toybox
Toybox is a national retailer of children toys. The company have experience much growth over the years since it was established. The sells all kind of children toys but have a specific taste in design, therefore, deals only with manufacturers who have the best products. Due to seasonality through the year, the company has adopted a culture of retailing toys that suits the various conditions throughout the year. Under seasonal conditioned kind of market, the company has the ability to respond to various customer orders, which ensure that the company is always making sales throughout the seasons. The seasonality does not only affect sales but also the operating expenses and even strain the working capital. In the process, the accounts department experiences instances of imbalances between receivables and payables.
Toybox operates in an industry that extremely competitive and with large number of other retailers that brings all sorts forces into the market. Toybox has to ensure the suppliers remain within safety standards with evolving superior designs at affordable prices to withstand the intense competition. At a macroeconomic level, the Toybox faces the weakening signs of the economy including a decline of the real consumer expenditure and possible decline in consumption as has been observed in various industries over the years. Therefore, from an economic consultant perspective, the findings outlined in various sections of the current case study will help under the past, current, and some future aspects of the Toybox retail market.
Data collection and analysis
The data collected from the case study is quantitative data where some is retrospective and other provides information on the current situation at Toybox. First, there is sales data for products by My Little Pony (MLP) for year 2016. Under this piece of information, there are several variables including the store number, store region (nominal variable), size of the store (ordinal variable), and sales for each of three featured products (Rainbow Dash, Pinkie Pie, and Fluttershy). For the sales data, statistical analysis will help produce a breakdown by region and store size to visualize where the demand falls for each product. In other words, frequency distribution tables and charts will help achieve the visualization and additionally the mean value of each product will tell on their popularity among the customers.
The second piece of data collected on profits made in 2016. In this case, the data has two variables, that is, the region and the profits made in UK pounds. At this point, the company wants to reflect the percentage distribution of the total profits across the different regions in 2016. The third piece of information of the data collected is the averages spend from a random sample of customer in 20 stores. A histogram will be used to explore the distribution of the average spend in the 20 stores. The fourth piece of data is on total profits where the analysis provides the company a report of profit index between 2001 and 2016. From the same piece of information the reports provide explore the relationship between total profits and number of store using a scatterplot. The fifth piece of data is on the 2014 advertising campaign where a scatterplot is constructed to explore the relationship between the profits and the advertising expenditure. In addition, a regression analysis will help investigate quantitatively the impacts of the advertising expenditure on totals profits and determine how much the company needs to spend on advertisement to hit £1,000,000 in profits. The forecasting MLP revenue data is last part of collected data and it is broken down into four quarters per year. The analysis focuses on providing a moving average forecasts for revenues in the last 2 quarters of 2015 and first two quarters of 2016.
Results
The following section reports on the various findings resulting from the different statistical analyses on the collected data for sales, revenues, and profits as observed at Toybox. Note all the analyses were performed using the Excel.
i. Breaking down the MLP sales for the year 2016 by region and store size for each product
Table 1: MLP total sales by region for each product
Region
Rainbow Dash
Pinkie Pie
Fluttershy
England
87520
84480
129910
Scotland
15450
15130
24340
Wales
12000
10970
17770
Grand Total
114970
110580
172020
Figure 1: Bar chart for MLP total sales by region
Table 1 and Figure 1 indicate and visualize the total sales for Rainbow Dash, Pinkie Pie, and Fluttershy in the three regions of operation. From the chart, it is clear that the England has the highest volume of sales while Wales has the least volume of sales for each product. In addition, the sales volume of the three products differs with a given region. For each region, Fluttershy has largest proportion of total sales while the sales volume for Rainbow Dash and Pinkie Pie are relatively the same.
Table 2: Total sales of each product by store size
Store size
Rainbow Dash
Pinkie Pie
Fluttershy
L
28310
26130
41230
M
42930
41760
66220
S
43730
42690
64570
Grand Total
114970
110580
172020
Figure 2: Bar chart for MLP products sales by store size
Table 2 and Figure 2 above summarize the sales of Rainbow Dash, Pinkie Pies, and Fluttershy by the store size across all the markets. The bar chart indicates there large-sized has the least volume of total sales while small-sized has the highest volume of sales. Individually, the Fluttershy has highest sales in all stores with the medium-sized stores recording the highest volume. The Rainbow Dash falls in second with a just slightly higher sales volume than the Pinkie pie makes in all the store sizes. However, it is important to note that the small stores makes the highest sales while large store makes the least sales for both Rainbow Dash and Pinkie Pie.
ii. The frequency distribution of total profits by region in 2016
Below is the percentage frequency distribution for total profits and a corresponding pie chart to visualize the situation at Toybox. Table 3 and Figure 3 below provide the percentage frequency distribution for total profits in three regions where Toybox operates. Of the total profits made by Toybox Scotland contributes 27.1 percent, Wales contributes 22.9%, and England contribute 50.0 percent of the profits. In other words, in 2016 financial year, England had highest contribution and Wales contributed the least to the total profits accrued by Toybox.
Table 3: The percentage distribution of total profits by region in 2016
Region
Profits
Percentage
Scotland
£2,284,639
27.1%
Wales
£1,928,737
22.9%
England
£4,214,817
50.0%
Total
£8,428,193
100%
Figure 3: Pie chart for percentage frequency distribution of total profits by region in 2016
iii. Average random sample of customers at 20 stores has been collected
Table 4: Frequency distribution table for average spending of customers
Class interval
Frequency
Relative frequency
(13-19)
586
0.18
(20-25)
123
0.04
(26-31)
633
0.20
(32-37)
0
0.00
(38-43)
333
0.11
(44-49)
823
0.26
(50-55)
142
0.04
(56-61)
177
0.06
(62-67)
351
0.11
Figure 4: Histogram for average spending of customers in various stores
Table 4 and Figure 4 indicate that frequency distribution of average spending customers. The histogram in the Figure 4 indicates that the frequency distribution is uni-modal with modal class interval falling between the £44 and £49. However, the mean value fall approximately in the same class the median value but it is relatively less than the modal value. This implies that the distribution of the spending of customers in the 20 stores is relatively symmetrical.
iv. Index of total profits since the company began in 2001.
Using 2001 as the base year, the index for each year by dividing the profit of that particular year by base year profits and then multiply by 100 percent.
,
Table 5 below indicates the indices for profits made from 2001 to 2016. The indices for 2016 indicates that the profits Toybox has increased by approximately 5546% from 2001 to 2016.
Table 5: Profits and profits indices for Toybox from 2001 to 2016
Year
Profits
Stores
Index
2001
£149,283
1
100%
2002
£210,546
3
141%
2003
£310,321
6
208%
2004
£415,014
10
278%
2005
£1,010,991
19
677%
2006
£1,784,615
34
1195%
2007
£3,266,769
60
2188%
2008
£4,631,124
87
3102%
2009
£5,260,627
100
3524%
2010
£6,204,369
134
4156%
2011
£7,183,314
187
4812%
2012
£7,672,186
211
5139%
2013
£7,703,112
234
5160%
2014
£8,008,524
266
5365%
2015
£8,257,879
283
5532%
2016
£8,428,193
300
5646%
v. Relationships between profits and number of stores
Figure 5: scatterplots for profits and stores
Figure 5 above indicates the relationship between the stores and profits. The scatterplot depicts a very strong positive relationship between the stores and profits. In other words, an increase in the number of stores is associated with a very strong increase in total profits.
vi. Relationships between profits and advertisement spending
Figure 6: scatterplot of total profits and advertisement spending
The scatterplot indicates a very positive linear relationship between total profits and advertisement spending at Toybox.
vii. Linear regression for relationship between profits and expenditure on advertisement
Note in this case the dependent variable is the profits and the explanatory variable is the advertisement expenditure. The aim is to test the following hypotheses at the 0.05 level of significance.
Null hypothesis: The advertisement expenditure does not predict total profits at Toybox
Alternative hypothesis: The advertisement expenditure is a significant predictor of total profits at Toybox.
Table 6 below indicates a summary of the linear regression analysis. The correlation coefficient = 0.983 and R-square =0.967 indicates a very strong positive association and ‘goodness of fit’ of the model respectively. The ANOVA statistic F(1,10) =293.51 , p-value < 0.05 implies that the model is statistically significant hence the null hypothesis is rejected. The slope coefficient indicates that the profits increase by £62.12 for every £1 increment in advertisement expenditure.
Table 6: Regression Analysis Summary
ANOVA
F(1,10)=293.51
p-value <0.000
Multiple R
0.983388
R Square
0.967052
Coefficients
Standard Error
t Stat
P-value
Lower 95%
Upper 95%
Intercept
-11368.6
40918.95
-0.278
0.787
-102541.66
79804.55
Ad Spend
62.12
3.626
17.132
0.000
54.04
70.20
viii. Determining advertisement expenditure from the model
Model:
Therefore, to make a profit of £1, 000, 000, the advertisement expenditure needed is calculated as:
Toybox will spend approximately £16,280.97 on advertisement to make a profit of £1,000,000.
ix. Moving average forecast to predict revenues for the last two quarters of 2015 and the first two quarters of 2016 for each MLP products.
Table 7 below provides the forecast of last two quarters of 2015 and the first two quarters of 2016 for MLP revenues at Toybox. Note a 3-period moving average was used to calculate the forecasts. The forecast of the next quarter is obtained by taking the average of the last three quarters. From the quarter 3 in 2015, the forecast values are used as actual value in order to predict the next period. For instance, to forecast the revenues for 2015 Q4 the average 2015 Q1, Q2, and Q3 is calculated where the forecast of Q3 is used as the actual value.
Table 7: 3-period moving averages forecast of MLP revenues (£000’s).
Rainbow Dash
Pinkie Pie
Flutterfly
Period
Actual
Forecast
Actual
Forecast
Actual
Forecast
2014 Q4
94
46
83
2015 Q1
99
47
85
2015 Q2
95
43
78
2015 Q3
96
96
45.33
45.33
82
82.00
2015 Q4
96.67
96.67
45.11
45.11
81.67
81.67
2016 Q1
95.89
95.89
44.48
44.48
80.56
80.56
2016 Q2
96.19
44.97
81.41