In a study of the housing demand, the county assessor is interested in developing a regression model to estimate the market value (Selling price) of residential property within his/her jurisdiction. The assessor feels that the most important variable affecting selling price (measure in thousands of dollars) is the size of house (measured in hundreds of square feet). In addition, the assessor feels that the total number of rooms, age, and whether or not the house has an attached garage might be important variables affecting selling price.
Data on Various Variables for Randomly Selected Houses
i Y X 1 X 2 X3 X4
House Selling_Price Size Number_Rooms Age Attached_Garage
1 $265.2 12.0 6 17 0
2 $279.6 20.2 7 18 0
3 $311.2 27.0 7 17 1
4 $328.0 30.0 8 18 1
5 $352.0 30.0 8 15 1
6 $281.2 21.4 8 20 1
7 $288.4 21.6 7 8 0
8 $292.8 25.2 7 15 1
9 $356.0 37.2 9 31 1
10 $263.2 14.4 7 8 0
11 $272.4 15.0 7 17 0
12 $291.2 22.4 6 9 0
13 $299.6 23.9 7 20 1
14 $307.6 26.6 6 23 1
15 $320.4 30.7 7 23 1
1. Speculate the expected relationship between the selling price and each of the independent variables according to economic theory.
2. prepare the equation of selling price model.
3. Interpret the coefficients of the explanatory variables.
4. Which variables are statistically significant determinants of the selling price?
5. Find the elasticity or sensitivity of the selling price to a given percentage change in the size of a typical house at the mean of the variables at the conventional level of significance (i.e. a = 0.05 level of significance).