Consider the following regression model: ln(price) = β0 + β1 ln(lotsize) + β2 colonial + u, where price is price of the house measured in $100,000; lotsize is lot size of the house; and colonial is a dummy variable for house being in colonial side.
The OLS estimates for this model are given by:
variable
beta
s.e.
In(lotsize)
0.20
0.01
colonial
0.03
0.01
constant
1.26
0.3327
How do you interpret the coefficient estimate of colonial variable?
We predict that, holding all else constant, price of a house in colonial side is $300,000 higher compared to houses that are not in colonial side.
We predict that, holding all else constant, price of a house in colonial side is 3% higher compared to houses that are not in colonial side.
We predict that, holding all else constant, price of a house in colonial side is 0.03% higher compared to houses that are not in colonial side.
We predict that, holding all else constant, price of a house in colonial side is $3 higher compared to houses that are not in colonial side.
Leave a Reply