Explore BrainMass
Share

Regression Analysis Model: Forecast sales price for car

This content was STOLEN from BrainMass.com - View the original, and get the already-completed solution here!

See attached file.

Dan Jones is thinking about purchasing of a car. One of his main concerns is how well the car will maintain its value. In particular, he is wondering how certain options affect a car's resale value, including the model year, type of transmission, mileage, air conditioning, leather interior, and the average number of miles driven per year.

One car Dan is considering is a Ford Mustang two-door coupe. To analyze the situation, Dan contacted a friend who works at a used car lot. He provided Dan with a spreadsheet with data on all 25 two-door Mustang coupes that were sold in 2005. (See Excel spreadsheet.)

1. Develop a regression model for the sales price with factors model year, type of transmission, mileage, air conditioning and leather interior. Eliminate factors that seem inappropriate and compute a formula for the sales price.

2. Dan is unsure whether the 'mileage' factor should be replaced by 'mileage per year' (computed by taking the mileage and dividing with the number of years used with the current year being 2005). Repeat problem 1 above with 'mileage per year' instead of 'mileage'.

3. For each of the regression models above, compute its MAD value (difference between the actual sales value and the forecast value from the model). Which method has a smaller MAD?

What would be the best formula to use to forecast the sales price? And please help with the regression analysis or steer me in the correct path.

© BrainMass Inc. brainmass.com October 25, 2018, 4:54 am ad1c9bdddf
https://brainmass.com/business/sales-revenue/regression-analysis-model-forecast-sales-price-for-car-398933

Attachments

Solution Preview

See attached file.

I completed this work in Excel for you. Start with the first tab to the left of the initial data, where I turn all variables ...

Solution Summary

I completed this work in Excel. Start with the first tab to the left of the initial data, where I turn all variables into numerical format (dummy variables). Next, I ran an exploratory regression to find out which variables were significant. Three of the five variables were good predictors so I threw out the two insignificant ones and ran a regression with just the significant three. Then, I computed miles per year and ran a regression substituting mileage with miles per year. The two prediction equations are shown and the MAD are computed for both equations.

$2.19
See Also This Related BrainMass Solution

Paper on Regression Analysis

Project Paper Business Statistics

Bryant/Smith manual Case 28: We want to find an equation that gives the selling price of a house.

Things you'll want to do are:
1. Use regression analysis to derive a model of selling prices of houses in Eastville. Interpret your final model and its coefficients within the context of this problem. 2. Prepare a formula to use in predicting selling prices. Explain your formula in nontechnical terms. 3. Tell what additional information you'd like to have to predict the selling prices of these homes more accurately.
You will want to prepare a summary of your findings to present to a Board of Realtors. You should use a nontechnical discussion of your forecasting model.

Must include:
Explain why you chose a particular statistical methodology. Describe your assumptions. Show your statistical analysis. Give a correct statistical conclusion.

How to Organize the Report

I. The executive summary
A. Describe the most important facts and conclusions.
B. One paragraph, no more!

II. The introduction
A. Several paragraphs.
B. Contents
1.Background on the problem.
2.Questions of interest, problem statement, and/or hypotheses.
3.The nature of the data set - describe your sample.

III. Analysis and methods section
A. Interpret the statistical summaries
1.Tell the reader what you found in the data (results, facts only).
2.Explain what those findings mean with regard to the problem (interpret results).
B. Design - describe the most important aspects of how the data was collected.

IV. Conclusions and summary section.
A. What has the analysis revealed?
B. Why was the analysis done? (Refers back to your background.)
C. What of value was discovered? (Any unexpected results.)
D. How have your questions been answered? (Refers back to questions of interest, problem statement, and/or hypotheses

V. References

VI. Appendix

View Full Posting Details