Abstract
In this paper we compare alternative specifications of the semi-log hedonic regression for a specific market area. We find that the most common specification employing floor area and number of rooms, as well as one that includes average room size, may be misspecified. Further, a straightforward alternative specification is shown to avoid the specification error problem and improve modestly the predictive power of the regression.
Highlights
Hedonic regression analysis of a housing market typically includes total floor space and numberofrooms in a standard semi-log specification
We find that the most common specification employing floor areaandnumberofrooms, as wellas onethatincludes average room size, may be misspecified
Recall that average room size does not allow the marginal value of floor space to decline with increases in floor space, a hypothesis that is strongly supported by the results reported in Regression 3
Summary
Hedonic regression analysis of a housing market typically includes total floor space and numberofrooms in a standard semi-log specification. Widely employed, this specification does not capture the way in which floor space and the number of rooms interact to determine room size, a prime determinant of the value of residential living space. An intuitive understanding ofthis problem is straightforward The estimated coefficients of number of rooms and floor area in the semi-log specification frequently are positive, an expected result since both are generally desirable housing characteristics. Given a 1,600-square-foot house, persons familiar with real estate markets would notbecertain that the addition of another room would have a positive impact Some researchers have included an average room size variable (floor area divided by number of rooms) to capture the effects of average room size. A straightforward alternative specification is shown to avoid the specification error problem and improve modestly the predictive power of the regression
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.