Chapter 15.3, Problem 17E

Quality of Fit in Predicting House Prices. Revisit exercise 9, where we develop an estimated regression equation that can be used to predict the selling price given the number of bathrooms, square footage, and number of bedrooms in the house.

1. a. Does the estimated regression equation provide a good fit to the data? Explain.
2. b. In part c of exercise 9 you developed an estimated regression equation that predicts selling price given the square footage and number of bedrooms. Compare the fit for this simpler model to that of the model that also includes number of bathrooms as an independent variable.

9. House Prices. Spring is a peak time for selling houses. The file SpringHouses contains the selling price, number of bathrooms, square footage, and number of bedrooms of 26 homes sold in Ft. Thomas, Kentucky, in spring 2018 (realtor.com website).

1. a. Develop scatter plots of selling price versus number of bathrooms, selling price versus square footage, and selling price versus number of bedrooms. Comment on the relationship between selling price and these three variables.
2. b. Develop an estimated regression equation that can be used to predict the selling price given the three independent variables (number of baths, square footage, and number of bedrooms).
3. c. It is argued that we do not need both number of baths and number of bedrooms. Develop an estimated regression equation that can be used to predict selling price given square footage and the number of bedrooms.
4. d. Suppose your house has four bedrooms and is 2650 square feet. What is the predicted selling price using the model developed in part c.