Abstract
The location of new homes defines the urban–rural fringe and determines many facets of the urban–rural interaction set in motion by construction of new homes in previously rural areas. Home, neighborhood and school district characteristics play a crucial role in determining the spatial location of new residential construction, which in turn defines the boundary and spatial extent of the urban–rural fringe. We develop and apply a spatial hedonic variant of the Blinder (J Hum Resour 8:436–455, 1973) and Oaxaca (Int Econ Rev 9:693–709, 1973) price decomposition to newer versus older home sales in the Columbus, Ohio metropolitan area during the year 2000. The preferences of buyers of newer homes are compared to those who purchased the nearest neighboring older home located in the same census block group, during the same year. Use of the nearest older home purchased in the same location represents a methodology to control for various neighborhood, social–economic-demographic and school district characteristics that influence home prices. Since newer homes reflect current preferences for home characteristics while older homes reflect past preferences for these characteristics, we use the price differentials between newer and older home sales in the Blinder–Oaxaca decomposition to assess the relative significance of various house characteristics to home buyers.
Similar content being viewed by others
Notes
Use of matrices W 1,W 2 with m values of 1/m in each row produce a row-stochastic matrix (the row-sums are unity) which results in the restriction that the parameter ρ must be less than unity, see LeSage and Pace (2004).
We note that this approach represents a special case of the more general treatment described in Oaxaca and Ransom (1994, 1998). Specifically, the group 1 wage structure is considered the nondiscriminatory standard, so that using the notation of Oaxaca and Ransom (1998), \(\Omega = I, \Gamma_1 = 0, \Gamma_2 = {\bar{X}}_2^{\prime}, {\hat{\delta}}_{12} = 0, {\hat{D}}_{12} = {\hat{\delta}}_{12}.\) Our approach can be extended to the more general treatment described in Oaxaca and Ransom (1994, 1998), but for clarity of exposition we deal with this most frequently used variant of the more general model. We also note that the correlations between the residuals from the newer and older homes for the two samples used in our applied illustration were 0.1059 and 0.1379, so covariance between newer and older homes is negligible.
Most applied work ignores this third term, and we follow this convention.
Strictly speaking, the characteristics effects term in (5) is not non-spatial since the parameter estimates \({\hat{\beta}}_1, {\hat{\beta}}_2\) are derived from a spatial autogressive model, not a non-spatial least-squares model. As we will see in the next section, least-squares estimates are biased in the presence of spatial dependence, so we would not wish to employ these in the decomposition.
Public domain algorithms programmed in the MATLAB matrix programming language that implement the estimation methodology used here can be found at http://www.spatial-econometrics.com.
Of course, there were similar biases in the case of least-squares versus the spatial model estimates for Sample 1.
Although the dependent variable reflects log of house selling price and the living area variable as well as lot size variables have been log-transformed as well, other variables in the model do not have a convenient comparable interpretation in terms of magnitude, e.g., the number of full baths.
References
Blinder AS (1973) Wage discrimination: reduced form and structural estimates. J Hum Resour 8:436–455
Brasington, David M (2006) Free housing data set, along with variation definitions available at: http://www.bus.lsu.edu/academics/economics/faculty/dbrasington/personal/data. htm
Brasington, David M (2007) Private schools and the willingness to pay for public schooling. Educ Finance Policy 2(2):152–174
Brasington, Donald R. Haurin (2006) Educational outcomes and house values: a test of the value-added approach. J Reg Sci 46(2):245–268
Brasington, David M., Diane Hite (2006) A mixed index approach to identifying hedonic price models. Working paper, Louisiana State University Department of Economics
Gelfand AE, Smith AFM (1990) Sampling-based approaches to calculating marginal densities. J Am Stat Assoc 85:398–409
Gelman A, Carlin JB, Stern HS, Rubin DB (1995) Bayesian data analysis. Chapman & Hall, London
Geweke J (1993) Bayesian treatment of the independent Student t linear model. J Appl Econom 8:19–40
Keith K, LeSage JP (2004) Robust decomposition analysis of wage differentials. J Econ Soc Meas 29(4):487–505
LeSage JP (1997) Bayesian estimation of spatial autoregressive models. Int Reg Sci Rev 20:113–129
LeSage JP (2004) Spatial regression models. In: Altman M, Gill J, McDonald M (eds) Numerical issues in statistical computing for the social scientist. Wiley, London, pp 199–218
LeSage JP, Pace RK (2004) Issue introduction: spatial statistics and real estate. J Real Estate Finance Econ 29(2):147–148
Oaxaca RL (1973) Male–female wage differentials in urban labor markets. Int Econ Rev 9:693–709
Oaxaca RL, Ransom MR (1994) On discrimination and the decomposition of wage differentials. J Econom 61:5–21
Oaxaca RL, Ransom MR (1998) Calculation of approximate variances for wage decomposition differentials. J Econ Soc Meas 24:55–61
Stanley TD, Jarrell SB (1998) Gender wage discrimination bias? A meta regression analysis. J Hum Resour 33:947–973
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
LeSage, J.P., Charles, J.S. Using home buyers’ revealed preferences to define the urban–rural fringe. J Geograph Syst 10, 1–21 (2008). https://doi.org/10.1007/s10109-007-0055-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10109-007-0055-z