Regression analysis can be used to analyze how a change in one variable impacts the other variable, such as an increase in marketing budget increasing sales. Find a unique area of your life where one variable impacts the other variable (being sure that are both measurable) and conduct a regression analysis on it. Remember to include the coefficient of determination as well as the test of significance. Share your results and make any comments as to whether or not there is a possibility of potential problems (causation or extrapolation) with your results.
——- Example number one
Age vs. Height
My kids grow like weeds — fast! An example of one variable that affects another is age affects height; evidently, the older a child gets (in general) the greater his or her height (up to a point). I guess this makes sense. From the data cards that the doctor’s office provided over the years, I have compiled a set of data for one of my sons. See the attached graph with both the “equation of the line” and “R^2” value. What does the “R^2” value tell us about the relationship between age and height? What types of problems might occur if we try to extrapolate this data into the future?
Age_v.height1.jpg
——Example number 2
Working in sales, I have utilized various avenues in reaching potential clients. One of the most well-known and highly effective strategies is phone follow-up. Email is great, but I was more likely to make a sale talking one-on-one with my prospect over the phone. I discovered that the number of calls one makes per day affects the number of cars sold per month. I used Desmos to conduct a regression analysis. The x-axis reflects the number of calls made per day. The y-axis shows the number of cars sold. We can observe a strong positive relationship between the x and y values. The equation of the regression line is y=0.147x – 2.73. The coefficient of determination is 0.96, and the coefficient of correlation is 0.98.
Screen Shot 2020-10-26 at 11.58.31 AM.pngScreen Shot 2020-10-26 at 11.58.42 AM.png
The chart supports my assumption that having a meaningful conversation with clients improves the sales numbers. However, there are a few areas of concern, such as extrapolation and causation. According to the chart, if a salesperson makes no phone calls, he or she will sell -3 cars, which is impossible. Similarly, making 200 phone calls will not yield 27 sales. In reality, making less than 20 calls will not result in any additional sales, while making over 110 calls will take up most of the day and diminish the quality of conversations. In this case, one should be careful when making predictions for values that are far from those that were used to construct the model. Another potential problem is causation. Simply calling 100 random people will not produce the desired results. There are many lurking variables such as salesperson’s training and experience, a well-researched list of potential buyers, and even the time when a call is made.
References
Assemi, R. (2020, September 24). 40 shocking sales stats that will change the way you sell. The Close Sales Blog. https://blog.close.com/39-shocking-stats-that-will-change-the-way-you-sell/
OpenStax. (2019). Introductory statistics. Houston, TX: OpenStax College. CC BY-SA. Retrieved from https://cnx.org/contents/MBiUQmmY@23.21:kcV4GRqc@17

The post Regression analysis can be used to analyze how a change in one variable impacts appeared first on Essay Desk.

0 replies

Leave a Reply

Want to join the discussion?
Feel free to contribute!

Leave a Reply

Your email address will not be published. Required fields are marked *