2 Case Study MBA 7715

Week 2 Case Study (Case Study #2) i Part 1 Based on your analysis and recommendations from Case Study #1, you decide to look at joint and individual significance for the three models from Case Study #1. Use the output of the regression models from Case Study # 1 to answer the questions below for Part 1 of Case Study #2. 1. Joint and Individual Significance for the Bays model a. Is there joint significance for the Bays model from Case Study #1 assuming alpha = 0.05? Write your answer in the box below. Considering that the model's significance F is less than 0.05, the Bay model is jointly statistically significant. b. Is there individual significance for the Bays model from Case Study #1 assuming alpha = 0.05? Write your answer in the box below. Bays is individually significance since the model p-value is less than 0.05 significance level. 2. Joint and Individual Significance for the Population model a. Is there joint significance for the Population model from Case Study #1 assuming alpha = 0.05? Write your answer in the box below. Population model is jointly statistically significant since the significance F of the model is less than 0.05 b. Is there individual significance for the Population model from Case Study #1 assuming alpha = 0.05? Write your answer in the box below. Population is individually significance since the model p-value is less than 0.05 significance level. 3. Joint and Individual Significance for the Bays and Population model (Multiple Regression) a. Is there joint significance for the Bays and Population model from Case Study #1 assuming alpha = 0.05? Write your answer in the box below. Given that the significance F of multiple regression is less than 0.05, there is a joint significance for Bays and Population at a significance level of 0.05. b. Is there individual significance for each variable for the Bays and Population model from Case Study #1 assuming alpha = 0.05? Write your answer in the box below. All variables; Bays, and Population are significant since each of the factor has p-value less than 0.05. Part 2 You also receive some new information about the Bays variable. You will use the Bay Type worksheet in the QuickFix Vehicles Case Study Data.xlsx workbook along with the results from Case Study #1 for Part 2 of Case Study #2. If you compare the data in the Bay Type worksheet to the Bays and Population worksheet used in Case Study #1, you will notice that the Bay Type worksheet has the original number

of bays divided into two variables, Oil Bays and Repair Bays . Using the new information, you decide to conduct some additional analyses to determine whether  the two types of bays are significant predictors of Vehicles Served ,  a model with Oil Bays , Repair Bays, and Population is a better fitting model than the model with Bays and Population from Case Study #1, and  whether the effect of Oil Bays is different from the effect of Repair Bays . In the end, you will be deciding whether it is better to use bays as a single variable as in the Bays and Population worksheet or as two separate variables as in the Bay Type worksheet. Perform the steps listed below and provide answers to the questions. 1. Multiple Regression for Oil Bays, Repair Bays, and Population a. Run a multiple regression using Oil Bays, Repair Bays, and Population . Label your results in an Excel workbook using the prompt number. b. Write the regression equation for the Oil Bays, Repair Bays, and Population model using the variable names, intercept coefficient, and slope coefficients from the regression output. Write your answer in the box below. Vehicle Served = 218.073+24.29861*oil Bays+23.00524*Repair Bays + 0.700871*Population c. Interpret the slope coefficients for the model. Write your answer in the box below. o For every additional 1,000 people in the population, there are 0.701 more automobiles available to serve them. o If one additional repair space is added, 23 more automobiles will be served, assuming all other factors stay the same. o For every unit change in the oil bays, an additional 24.29861 autos will be served, assuming all other factors stay the same. 2. Joint and Individual Significance for the Oil Bays, Repair Bays, and Population model (Multiple Regression) a. Is there joint significance for the Oil Bays, Repair Bays, and Population model assuming alpha = 0.05? Write your answer in the box below. Given that the significance F of the multiple regression is less than 0.05, there is a combined significance for the Oil Bays, Repair Bays, and Population at a significance level of 0.05. b. Is there individual significance for each variable for the Oil Bays, Repair Bays, and Population model assuming alpha = 0.05? Write your answer in the box below. P-values below 0.05 indicate that Oil Bays, Repair Bays, and Population are all significant factors. (p-value for Population = 0.01041, for Repair Bays = 0.000322, and for Oil Bays = 0.049) 3. Is the Oil Bays, Repair Bays, and Population model a better fit than the Bays and Population model from Case Study #1? Provide an explanation of how you reached your conclusion including the measure of goodness-of-fit that you used. Write your answer in the box below.

i This case study is adapted from Exercises 17.1, problem 16, page 598 of Business Statistics: communicating with numbers , Jaggia and Kelly, Fourth Edition.