Question 3: Oreo Sales

The file Oreos.xlsx gives daily sales of Oreos at a supermarket and whether Oreos were placed on different floors of the shelf.

There were three different floors of the shelf: 7th floor, 6th floor, or 5th floor.

1. Please run a regression analysis. What is the influence of shelf position on Oreo Sales?

2. Which floor level is the best to place Oreo in order to increase sales?

3. As an analyst, do you want to add additional variables to the model? Please explain.

Note: You do not need to analyze the new variables. The new variables should influence the sales of Oreo sold in the supermarket.

Instruction: 

You need to run regression analysis for question 3.

Oreo Sales

• You need to determine how the shelf position affect daily sales of Oreo.

• Before running a regression analysis, you need to know the independent variable and dependent variable. Considering regression analysis as a causal relationship between/among variables, the independent variable(s) are the "cause," and the dependent variable is the "effect." The cause happens before the effect, and the effect happens because of the cause.

o In this case, the independent variable is shelf position. The reason is, we assume that if we place the Oreo at different floor on the shelf, the daily sales will change.

• After running a regression analysis, you need to check the statistics in the proper order:

o 1st step: Checking the R-squared, which is a statistical measure of how close the data are to the fitted regression line. R-squared is the percentage of the variance in the dependent variable that the

independent variables explain.

 Range: 0 - 100%.

 For example, a R-squared of 25% means that 25% of the variations of the dependent variable is explained by the independent variables.

 Thus, the higher the R-squared, the more accurate the regression results.

o 2nd step: The p-value of the regression coefficients of independent variables.

 If the p-value for an independent variable is greater than 0.05, it means that the independent variable has no significant impact on the dependent variable. This variable should be excluded from the model.

 If the p-value for an independent variable is less than 0.05, it means that the independent variable has a significant impact on the dependent variable. The coefficient of this independent variable needs to be interpreted.

o 3rd step: Interpretation of the independent variable.

 Important: If the p-value for an independent variable is greater than 0.05, the independent variable has no impact on the dependent variable and it does not need to be interpreted.

 We should look at the coefficients.

 The meaning of coefficients: If the independent variable increase by one unit, the dependent variable will increase (when the coefficient is positive) or decrease (when the coefficient is negative) by (the value of coefficient) units.