Next Multiple Regression

Next Multiple Regression - Example Does school quality...

Info iconThis preview shows pages 1–3. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Applied Business Tools ECO 6416 Extensions to Multiple Regression Example Does school quality affect housing prices? Other things equal, are houses worth more when located in zones for better schools? Economic framework: hedonic model for prices of goods that are bundles of characteristics. Price of house viewed as a function of Price of house viewed as a function of characteristics of the property (like size, whether it has a pool) and characteristics of the neighborhood (like quality of school). Research Design for this Example Study site is Temple Terrace, in Tampa area. Small enough that many neighborhood characteristics might plausibly be assumed constant throughout, such as crime rates. Bears on omitted variables bias. Same property tax rates throughout, etc. Three elementary schools that all feed into the same middle and high schools. Thus, if school quality affects housing prices, it must be elementary school quality in this particular case. Housing Data Cross-sectional, micro data – 195 houses, their sales prices, characteristics, and elementary school zone. Housing characteristics: square footage, age, number of bedrooms, number of bathrooms, and dummy variables for: Whether house has a swimming pool Whether house has a fireplace. Whether house is on waterfront. Natural logarithm of sales price is dependent variable. School Data In this example, school quality is measured by the grade assigned by the state, based mainly on the school’s performance on the prior FCAT. Schools are graded A to F. The three schools in Temple Terrace earned AB dC one A, one B, and one C. Consider FCAT grade a categorical variable with three categories (in this case): grade of A, B or C. We need two dummy variables . Descriptive Statistics Variable Mean S.D. Price 201066.62 153167.46 Sqft 1803.52 802.87 Age 30.82 14.57 Bed 3.02 0.87 Bath 2.20 0.59 Pool 0.50 Fireplace 0.27 Waterfront 0.09 Agrade 0.58 Bgrade 0.25 Cgrade 0.16
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
2 Regression Results Coeffs Std Err t Stat P-value Intercept 10.3827 0.09826 105.665 2.5E-167 Sqft 0.00056 3.8E-05 14.7225 5.59E-33 Age 0.00622 0.0015 4.15372 4.99E-05 Bed 0.09718 0.02856 3.40292 0.000817 Bath 0.08356 0.03928 2.12695 0.03475 Pool -0.0578 0.0361 -1.6015 0.11097 Fireplace -0.0067 0.04127 -0.1628 0.870843 Waterfront 0.23293 0.05832 3.99378 9.37E-05 Bgrade 0 1689 0 04308 3 9211 0 000124 -0.1689 0.04308 -3.9211 0.000124 Cgrade -0.0523 0.0543 -0.9627 0.336935 R Square 0.87952 ANOVA df SS MS F Sig F Regression 9 65.3839 7.26487 150.0558 4E-80 Residual 185 8.95668 0.04841 Total 194 74.3406 Interpretations? When the dependent variable is in log form, and the independent variables are in linear form… Coefficients of quantitative variables measure the proportionate effect on Y of a 1-unit increase in X. We usually multiply the coefficient by 100 and interpret it as the % effect on Y of a 1-unit change in X. Example, an additional bedroom, holding other housing characteristics constant, is estimated to add 9.7% to the sales price of a house. Interpretations?
Background image of page 2
Image of page 3
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 11/15/2010 for the course ECO 6416 taught by Professor Staff during the Spring '08 term at University of Central Florida.

Page1 / 12

Next Multiple Regression - Example Does school quality...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online