A SAMPLE ECONOMETRIC MODEL
Title: An Econometric Model of Housing Prices
The Model: πΜ = ππ + π1 π1 + π2 π2 + π3 π3 + π4 π4 where, πΜ = the predicted value of house price π1 = floor area (square foot) π2 = age (year) π3 = dummy variable for excellent condition (1 for excellent, 0 otherwise) π4 = dummy variable for mint condition (1 for mint, 0 otherwise)
Theoretical Framework: Cite the relevant economic theory or theories here. A one paragraph discussion per theory is enough.
Conceptual Framework: Explain here the relationship(s) between your independent variable(s) and your dependent variable. This serves as an explanation to your schematic diagram. One sentence per relationship is enough. In this example, you might say that, βFloor area, age of the house and house condition affect the price of the house. Houses with larger floor area tend to command a higher price. Older houses tend to be cheaper than newer houses. The better the condition of the houses, the higher the price of the house.β
Schematic Diagram:
Floor Area
Age of the House
House Condition ο· Excellent ο· Mint ο· Good
Price of the House
Data: House Price ($) 95,000 119,000 124,800 135,000 142,000 145,000 159,000 165,000 182,000 183,000 200,000 211,000 215,000 219,000 Cite the source
Floor Area (square foot) 1,926 2,069 1,720 1,396 1,706 1,847 1,950 2,323 2,285 3,752 2,300 2,525 3,800 1,740
Age of the House (years) 30 40 30 15 32 38 27 30 26 35 18 17 40 12
House Condition Good Excellent Excellent Good Mint Mint Mint Excellent Mint Good Good Good Excellent Mint
Note: You may fold the computer print-out if it exceeds the page of your test booklet. For simple regression, attach also a scatterplot.
Result:
πΜ = 121,674.14 + 56.49π1 β 3,970.46π2 + 33,247.74π3 + 47, 271.71π4 p-value:
(0.0000)
(0.0000)
(0.0000)
(0.0231)
(0.0016)
Note: It is customary to report the p-value below the coefficients. The p-value of intercept, 6.37221E-05, means moving the decimal point 5 places to the left, 0.0000637221, a value very close to zero. Rounding this value to 4 decimal places will make it 0.0000
Interpretation: Declare your level of significance, πΌ, beforehand. You may say, βI choose the level of significance, πΌ = 5%β βFor every one square foot increase in the floor area of the house, the price of the house will increase by $56.49. For every one year increase in the age of the house, the price of the house will decrease (careful with the sign of the coefficients) by $3,970.46. Price of houses that are in excellent condition are on the average higher by $33,247.74 compared to houses that are in good condition. Price of houses that are in mint condition are on the average higher by $47,271.71 compared to houses that are in good condition.β (Note that good condition is our base category, the category in which all value of the dummy variables are zero.) βThe price of the house is $121,674.14 when its floor area and age are all zero and the house is in good condition. Since its impossible to have a house that has zero floor area and zero age, the intercept has no economic meaningβ βSince the p-value of all the coefficients are lower than my πΌ of 5%, all the coefficients are statistically significant.β βThe model has an adjusted π
2 of 0.8534. This means that 85.34% of the variation of housing prices is captured by the model.β βSince the p-value of the F-test is lower than my than my πΌ of 5%, the model as a whole is statistically significant.β
Note: Ideal Topic 1. Interesting and imaginative model 2. Good theory 3. Plenty of observations (large n) 4. Low p-value 5. High π
2