STATS630 University at Buffalo Week 6 MindTap Regression Analysis –

STATS630 University at Buffalo Week 6 MindTap Regression Analysis –

Mathematics –


Assignments must be completed on MindTap AND a completed workbook with your full completed solutions must be submitted via Sakai. You must submit both in order to receive any credit.

Hardcopies or copies emailed will not be graded.

There is no option for late submissions in MindTap. Failure to submit your submit your assignment on MindTap before the due date will result in zero credit.

Submit your worked data in one single MS Excel Workbook. Start your solution set by using the assignment shell provided on Sakai. Use appropriately labeled worksheets for each problem/section of a problem.

Pay very close attention to the final presentation of your work and make sure it is print-ready. Prepare all spreadsheets so that they are clear, attractive and easy for the untrained eye to follow and understand. While accurate content and precise execution of the techniques is critical, formatting, typographical and grammatical acuteness is also very important. General sloppiness and inconsistent formatting will lower your grade.

Note: Ignore MindTap warning about text-based answers. All open ended questions will be graded as well. In fact, your grade will depend equally on the accuracy of your analytical techniques and your interpretation of the results.

Assignment files should be named as follows:

  • Asg#_FirstInitialLastname
  • e.g. Assignment 1 for Michael Phelps would be named Asg1_MPhelps.xlsx

Question 1. 40 points

The owner of the Original Italian Pizza restaurant chain would like to predict the sales of his specialty, deep-dish pizza. He has gathered data on the monthly sales of deep-dish pizzas at his restaurants and observations on other potentially relevant variables for each of his 15 outlets.

A.Estimate a multiple regression model between the quantity sold (Y) and the explanatory variables in columns C–E.
Let X1 represent the average price.
Let X2 represent the monthly advertising expenditures.
Let X3 represent the disposable income per household.

B.Is there evidence of any violations of the key assumptions of regression analysis?

C.Which of the variables in this equation have regression coefficients that are statistically different from zero at the 5% significance level?

D.Given your findings in part C, which variables, if any, would you choose to remove from the equation estimated in part A?

Question 2. 60 points

The data are for 204 employees at the (fictional) company Beta Technologies.

A.Run a forward stepwise regression of Annual Salary versus Gender, Age, Prior Experience, Beta Experience, and Education.
Would you say this equation does a good job of explaining the variation in salaries?
What is the R2 for this regression?
What is the standard error of estimate for this regression?

B.Add a new employee to the end of the data set, a top-level executive. The values of Gender through Annual Salary for this person are, respectively, 0, 56, 10, 15, 6, and $500,000.
Run the regression in Part A again, including this executive.
Are the results much different?
What is the R2 for this regression?
What is the standard error of estimate for this regression?
Is it “fair” to exclude this executive when analyzing the salary structure at this company?