Data Analytics Analysis

The assignment content discusses data analytics for five types of businesses: startup costs for pizza, baker/donuts, shoe stores, pet stores, and gift stores. The mean, median, mode, range, variance, and standard deviation are calculated for each type of business. The analysis also includes regression analysis to predict net annual sales based on variables such as number of square feet, inventory, amount spent on advertising, size of the sales district, and number of competing stores.

Running Head: DATA ANALYTICS
Data Analytics
Name of the Student
Name of the University
Author Note

1DATA ANALYTICS
Table of Contents
TASK 1............................................................................................................................................2
TASK 2............................................................................................................................................7
Bibliography..................................................................................................................................10

2DATA ANALYTICS
TASK 1
1. The mean, median, mode, range, variance and standard deviation separately for
each of the five types of businesses such as startup costs for pizza, baker/donuts, shoe
stores and pet stores are given in table 1.1.
Table 1.1: Descriptive measures for the five types of businesses
2. Frequency and relative frequency distribution for the starting costs of all the five
business types are given in the following tables from table 1.1 to table 1.6. The relative
frequency histograms of the starting costs of all the five business types are given in figure
1.1 to figure 1.5.

3DATA ANALYTICS
0-30 30-60 60-90 90-120 120-1500.000
0.308 0.308
0.154
0.231
Startup Cost for Pizza
Clas Boundaries (Costs)
Relative Frequency
Figure 1.1: Relative frequency histogram for startup cost for pizza
0-30 30-60 60-90 90-120 120-150 150-1800.000
0.182
0.364
0.182
0.091
0.182
Startup cost for Baker/Donuts
Class Boundaries (Cost)
Relative frequency
Figure 1.2: Relative frequency histogram for startup cost for Baker/Donuts

4DATA ANALYTICS
0-30 30-60 60-90 90-120 120-1500
0.4
0.3
0.2
0.1
Startup cost for Shoe Store
Class Boundary (Cost)
Relative Frequency
Figure 1.3: Relative frequency histogram for startup cost for Shoe Store

5DATA ANALYTICS
0-30 30-60 60-90 90-120 120-1500
0.3
0.1
0.4
0.2
Startup cost for Gift Store
Class Boundaries (Cost)
Relative Frequency
Figure 1.4: Relative frequency histogram for startup cost for Gift Store
0-30 30-60 60-90 90-120
0.25
0.375
0.3125
0.0625
Startup cost for Pet Store
Class Boundaries (Cost)
Relative Frequency
Figure 1.5: Relative frequency histogram for startup cost for Pet Store

6DATA ANALYTICS
The mean, median, mode, range, variance and standard deviation of the startup
costs of the variables have been calculated in part 1. From table 1.1, it can be observed
that the variance of the startup costs for each type of business is high. However, the
variance is least in case of a pet store compared to the other stores. Thus, it can be said
that the startup cost for building a pet store is close to the mean cost. The startup costs for
all the other types of business varies more than the pet store. Again, it can be seen that for
a gift store, the mode is greater than the median, which is again greater than the mean.
Thus, the data is negatively skewed. This means most of the costs are above the mean
cost. All the other business types show a negatively skewed startup cost. This means that
most of the startup costs are less than the mean cost.
To test if there is any significant difference between the starting costs of these
types of businesses, analysis of variance (ANOVA) test has to be conducted. The test
results (table 1.7) show that the p-value is found to be 0.0184 which is less than the level
of significance. Thus, it can be said that there is no significant difference in the starting
costs for these types of businesses.

7DATA ANALYTICS
TASK 2
1. The MS Excel output for the regression analysis is given in table 2.1. The
estimated regression equation that can be obtained from this regression analysis is given
by
X1 = -18.86 + (16.20 * X2) + (0.17 * X3) + (11.53 * X4) + (13.58 * X5) - (5.31 * X6)
Where, X1 is the net annual sales (per $ 1000), X2 is the number of square feet (per 1000),
X3 is inventory (per $ 1000), X4 is the amount spent on advertising (per $ 1000), X5 is the
size of the sales district (Per 1000 families) and X6 is the number of competing stores in
the district.
2. From the regression statistics, it can be seen that the value of R Square is found to
be 0.99. Thus, the independent variables X2, X3, X4, X5 and X6 can predict the
dependent variable net annual sales (X1) 99 percent correctly. Thus, it can be said that
the model is a very good fit to the data.
3. To test the relationship between the dependent variable and the independent
variables, Analysis of Variance (ANOVA) test has to be done. From the ANOVA table in
table 2.1, it can be seen that the p-value is found to be 0.000, which is less than the level
of significance (0.05). Thus, it can be said that there is significant difference between the
dependent variables and the independent variables.
4. From the coefficients table in table 2.1, it can be said that with one unit increase
in the number of square feet (X2), the net annual sales (X1) increases by 16.20 units.
With one unit increase in inventory (X3) the net annual sales (X1) increases by 0.17.
Again, with one unit increase in amount spent on advertising (X4) the net annual sales
(X1) increases by 11.53, with one unit increase in size of sales district (X5) the net annual

8DATA ANALYTICS
sales (X1) increases by 13.58 and with one unit increase in the number of competing
stores in the district (X6) the net annual sales (X1) decreases by 5.31.
5. The 95 percent confidence interval for the slope coefficients of the individual
variables are given as follows:
Variable Name Lower 95 % Upper 95 %
Number of Sq. ft. 8.83 23.57
Inventory 0.05 0.29
Amount spent on
advertising
6.26 16.79
Size of sales district 9.90 17.26
Number of competing
stores
-8.86 -1.76
6. It can be seen from the coefficients table 2.1 that all the p-values of the variables
are less than 0.05. Thus, all the variables are significant. All the variables are significant
and thus there is no need to re-estimate the model.
7. The annual sales for a franchisee with 1,000 sq ft floor area, $150,000 inventory,
$5,000 spent on advertising, 5,000 families in the area of operation and 2 competitors is
given by
X1 = -18.86 + (16.20 * 1) + (0.17 * 150) + (11.53 * 5) + (13.58 * 5) - (5.31 * 2)
= $ 137.77.

9DATA ANALYTICS

10DATA ANALYTICS
Bibliography
Draper, N.R. and Smith, H., 2014. Applied regression analysis. John Wiley & Sons.
Kleinbaum, D., Kupper, L., Nizam, A. and Rosenberg, E., 2013. Applied regression analysis and
other multivariable methods. Nelson Education.