Planning future activity plays a crucial role in a company as it plans for the future demands of the market. The future planning of the company for the production, finance, marketing, etc., can be done through forecasting technique. The forecasting plan helps the organization to establish the sales performance goals, get real and accurate pictures of sales, estimates the number of raw materials, the workforce of the production. ABC Furniture Company is one such company that likes to predict the sales for their subsequent year based on the customer traffic data (Shim, 2000). However, before proceeding with the sales forecasting, it is necessary to determine whether a relationship exists between the sales and customer traffic. Linear Regression is the most widely used statistical techniques to think of relationship and the prediction. Linear Regression calculates the mathematical relationship between two variables (dependent and independent variables) and uses the historical relationship between two variables to predict the future value of the dependent variable.
Relationship between two variables
Linear Regression was performed on the ABC furniture company to demonstrate how the past customer traffic was related to sales so as to make a future prediction of sales. Table 1 provides the two variables (Customer Traffic) and (Sales) where; ‘Customer Traffic’ is the independent variable, whereas ‘Sales’ is the dependent variable. See Table 1.
Customer-Sale Table
The following information was construed and interpreted through the Linear Regression analysis;
The Linear regression model represents how the set of observation fits the line and the proportion of variance between the dependent variable (Sales) and the independent variable (customer traffic).
The R-square value calculated through the formula ‘Explained variation/ Total variation’ = 71.80% clearly indicates that the observed data point falls closer to the regression line.
An adjusted R2 value that corrects positive bias provided the value that could be expected in the population.
Scatter Diagram
Scatter plot diagram shown in figure 1 provides a visual relationship (Meisenheimer, 1997) between ‘Customer traffic’ and ‘Sales’ along with the regression line fitted to the observed data of the ABC Furniture Company. See Figure 1 below.
Customer traffic vs Sales Regression
Regression Analysis: Sales ($000) versus Customers
Analysis of Variance
Source DF Adj SS Adj MS F-Value P-Value
Regression 1 27791 27791 25.46 0.001
Customers 1 27791 27791 25.46 0.001
Error 10 10915 1092
Total 11 38707
Model Summary
S R-sq R-sq (adj) R-sq (pred)
33.0385 71.80% 68.98% 58.47%
Coefficients
Term Coef SE Coef T-Value P-Value VIF
Constant 111.6 39.2 2.85 0.017
Customers 0.648 0.128 5.05 0.001 1.00
Regression Equation
Sales ($000) = 111.6 + 0.648 Customers
Forecast Sales
Customer-Sale for Year 2
Customer-Sale for Year 2
A significant difference found between the actual and forecast sales hence variances was calculated by the formula that divides the difference between the actual and forecast by the actual sales. The difference value known as ‘Variance’ helped the company to estimate their performance by comparing the forecast vs. actual .
Conclusion
The ABC Furniture Company sets the predicted sales as a standard against which the company has to evaluate their performance. Sketched forecast predicts how the sales will be like if the company doesn’t undergo any significant changes in strategy and tactics. Any recent changes may unlikely cause the overall forecasting calculation to differ. To avoid the difference between the actual and forecast sales ABC Furniture Company fixes up the responsibility for each department. The department will understand why fluctuation occurs in their respective areas and plans to change the situation.
References
Drury, C. M. (2008). The investigation of Variances. In Management and Cost Accounting (p. 463).
Meisenheimer, C. G. (1997). Using SPC Tools in the Quality Process. In Improving Quality: A Guide to Effective Programs (p. 256).
Shim, J. K. (2000). Strategic business forecasting: The complete guide to forecasting real world company performance. CRC Press.
