Relationship between Sales and Earnings

Relationship between Sales and Earnings

Table of Contents

Introduction2

Discussion2

Exploring Data2

Correlation5

Calculating Correlation Using Excel6

Linear Regression9

Conclusion10

Relationship between Sales and Earnings

Introduction

Small businesses usually operate on the bases of catering a niche market segment. A small fashion retailer would cater for a narrowed down segment of women, in a particular age group as it will not have the resources to cater a large market segment. According to the type industry one operates its business; the profit earning will vary according to sales. A luxury goods retailer would have higher sales and profits, while a company working low price segment, working in highly competitive environment could have high sales and low earnings. In order to identify a relationship between two variables, the statistical techniques vary according to type of data (Anderson, 2011). We will be exploring the data types of the provided data and will explore if a relationship exists between the variables using statistical techniques of correlation and regression.

Discussion

Exploring Data

The data provided are the figures of “sales” and “earnings” of small businesses. Table 1 shows the sales and earnings of 12 best small companies.

Table 1: Sales and Earnings of 12 Best Small Companies

Company

Sales

Earnings

Papa John's

89.2

4.9

Applied Innovation

18.6

4.4

Integracare

18.2

1.3

Wall Data

71.7

8

Davidson and Associates

58.6

6.6

Chico's FAS

46.8

4.1

Checkmate

17.5

2.6

Royal Grip

11.9

1.7

M-Wave

19.6

3.5

Serving

51.2

8.2

Daig

28.6

6

Cobra Golf

69.2

12.8

It can be observed that data is numeric, quantitative and continuous. For this kind of data we will first carry out exploratory and descriptive statistical analysis (Baltagi, 2009). Table 2 shows the descriptive analysis of Sales variable.

Table 2: Descriptive Statistics of Sales Variable

Sales

Mean

41.75833

Standard Error

7.554794

Median

37.7

Mode

#N/A

Standard Deviation

26.17058

Sample Variance

684.899

Kurtosis

-1.16681

Skewness

0.48985

Range

77.3

Minimum

11.9

Maximum

89.2

Sum

501.1

Count

12

In order to asses if the data is distributed normally, we will use construct a histogram (Box et al.,2011). Figure 1 shows the histogram below:

Figure 1: Histogram of Sales

We will evaluate the descriptive statistics of “earning” variable. Table 3 shows the descriptive analysis of the earning data.

Table 3: Descriptive Analysis of “Earning” variable

Earnings

Mean

5.341667

Standard Error

0.937474

Median

4.65

Mode

#N/A

Standard Deviation

3.247505

Sample Variance

10.54629

Kurtosis

1.247752

Skewness

1.004277

Range

11.5

Minimum

1.3

Maximum

12.8

Sum

64.1

Count

12

In order to assess if the data is normally distributed, we will construct a histogram of the “earning” variable. Figure 2 shows the histogram of data in earning variable.

Figure 2: Histogram of variable “earning”

Effective evaluation of data requires one to analyze the different variables which may effect on the variables (Friston et al.2011). It is essential as the variation in one variable cannot be explained by analyzing its dependence or relationship to a single variable.

We will explore the two methods of relationship analysis which evaluate if there is a relation among sales and earnings of these companies.

Correlation

The statistic of correlation is the measure which evaluates the relationships' direction and strength among two variables. It requires data from the same subject on two variables (Girden et al., 2010). Correlation is tested most commonly using the Pearson's coefficient of correlation. This measures the strength of correlation among the variables which is represented by “r” (linear association between variables). The range of values which the correlation coefficient can take is -1 to +1. If the value of “r” is zero, it indicates that there is no association between the variables. If the value of “r” is greater than zero, then ...