I want to replay to this essay ***In Part 2 of this assignment, you can read you

I want to replay to this essay
***In Part 2 of this assignment, you can read your classmate’s posts and the articles they found, select one, and do some critical analysis on that same article (not your classmate’s original post).
**
(Introduction:
Determining the relationship between explanatory variables can allow management to determine an outcome given a certain level of the variables being tested. In the article “Linear Regression Model for business Strategy”, authors Keyi Chen, Liyao Dong, and Linxinyi Wang utilize regression analysis to determine how the marketing mix for a product launch will impact sales numbers within a food distribution company.
Regression Model:
The aim of the regression analysis conducted within this article is to determine which variable within a given marketing mix have a correlation with the total number of sales of the new product being launched. To determine the optimal marketing mix, the independent variables have been labeled as: the month of sale, price, advertising expenses, display area, store volume, and city index. These are the initial variables included in the marketing mix, which will be used in the optimization of sale tactic strategies.
Goodness of Fit:
To determine the most effective marketing mix, the variables that are determined to have no significant relationship to the sales numbers are extracted from the formula, until only those with significant relationships remain. The articles utilize the p-value to determine if the independent variable can be ruled as significant. The significance level is set to 0.1 for this regression analysis. The first variable that is determined to be insignificant is the city. The p-value for the city was determined to be 0.8492, which is over the allowed 0.1. The next variable to be removed is the display area. Since this was a categorical variable, an F text was conducted to determine if the null hypothesis that a different location would not lead to different sales could be rejected. The p-value was calculated as 0.2492, which is greater than the 0.1 significance level, meaning that the null hypothesis was not rejected. The remaining variables have p-values that are under the 0.1 level set. Initially, the marketing mix that included only the significant variables had a high VIF value, indicating the model may not be a good fit for the variables being analyzed. To address this issue, the numerical variable for store is centered, and the outliers are removed to arrive at the final model, labeled fitcenter. This final model has VIF values all under 5 for each variable, indicating there is no additional corrective measures needed, and the model can accurately predict sales numbers.­­
Benefits:
After conducting linear regression analysis, management was able to determine the ideal marketing mix, allowing them to predict sales levels given a certain value for the independent variable they tested. The model allowed them to determine that although lower prices lead to higher profits as there is an increase in the number of sales, higher prices have a higher net margin. After conducting analysis using the formula, they generated through linear regression using their previous assumption that 70% of the retail price will be revenue, management was able to determine that the initial estimation of sales for the newly launched product were conservative.
Lesson:
Prior to conducting research on the application of linear regression, I never considered how useful it can be to be able to determine whether two variables are related. I never though about how this could allow a company to make estimates or forecasts and evaluate trends they may encounter in their operations. Being able to forecast certain events can allow more informed planning by the management team, and lead to more efficient and optimized business practices.
Article: https://www.atlantis-press.com/proceedings/icfied-22/125971771 Links to an external site.
Reply
Comments from Customer
Discipline: SCMS