Bayesian Spatial Filtering for Hedonic Models: An Application for the Real Estate Market

This article presents a Bayesian method based on spatial filtering to estimate hedonic models for dwelling prices with geographically varying coefficients. A Bayesian Adaptive Sampling algorithm for variable selection is used, which makes it possible to select the most appropriate filters for each hedonic coefficient. This approach explores the model space more systematically and takes into account the uncertainty associated with model estimation and selection processes. The methodology is illustrated with an application for the real estate market in the Spanish city of Zaragoza and with simulated data. In addition, an exhaustive comparison study with a set of alternatives strategies used in the literature is carried out. Our results show that the proposed Bayesian procedures are competitive in terms of prediction; more accurate results are obtained in the estimation of the regression coefficients of the model, and the multicollinearity problems associated with the estimation of the regression coefficients are solved.     

HEDONIC ANALYSIS OVER TIME AND SPACE: THE CASE OF HOUSE PRICES AND TRAFFIC NOISE

One consequence of the expanding road network and its associated traffic is increased levels of traffic noise. While the hedonic literature has consistently found a negative relationship between real estate prices and noise levels, research in the United States has typically relied on crude measures of traffic noise. Here, we reduce the measurement error of traffic noise exposure through a detailed model of noise propagation over the landscape. We then estimate the hedonic relationship between noise and single family house prices using over 40,000 transactions throughout the St. Paul, Minnesota, urban area from 2005 to 2010. We implement spatially and temporally flexible local regression techniques and find significant nonstationarity in the hedonic function over time and space.     

THE IMPACT OF CRIME ON APARTMENT PRICES: EVIDENCE FROM STOCKHOLM,SWEDEN

This study uses data of about 9,000 apartment sales in Stockholm, Sweden, to assess the impact of crime on property prices. The study employs hedonic pricing modelling to estimate the impact of crime controlling for other factors (property and neighbourhood characteristics). Geographic Information System (GIS) is used to combine apartment sales by coordinates with offences, land use characteristics and demographic data of the population. The novelty of this research is threefold. First, it explores a set of land use attributes created by spatial techniques in GIS in combination with detailed geographical data in hedonic pricing modelling. Second, the effect of crime in neighbouring zones at one place can be measured by incorporating spatial lagged variables of offence rates into the model. Third, the study provides evidence of the impact of crime on housing prices in a capital city of a traditional welfare state, information otherwise lacking in the international literature. Our results indicate that apartment prices in a specific area are strongly affected by crime in its neighbouring zones, regardless of crime type. When offences were broken down by types, residential burglary, theft, vandalism, assault and robbery individually had a significant negative effect on property values. However, for residential burglary such an effect is not homogenous across space, and apartment prices in central areas are often less discounted by being exposed to crime than those in the city's outskirts.     

A HEDONIC MODEL OF INTERREGIONAL WAGES,RENTS, AND AMENITY VALUES*

ABSTRACT This paper develops a general multimarket hedonic model appropriate for a national, interregional study of wages, housing prices, and location-specific amenities. The model encompasses the effects of interregional location, intraurban location, and city size. Typically, hedonic studies focus on a single market such as labor or housing and ignore interactions implicit in a more global compensation mechanism. Examination of the comparative statics of our model indicates that single-market differentials are partial prices and are unreliable measures of amenity values in an interregional context. Unbiased amenity values are estimated for a comprehensive set of amenities using data on housing prices for 34,414 households and wages for 46,004 workers from the 1980 Census of Population and Housing. Statistically significant differences in housing prices and wages are found due to amenities.     

EVALUATING THE WELFARE EFFECTS OF SCHOOL QUALITY IMPROVEMENTS: A RESIDENTIAL SORTING APPROACH

Las Vegas experienced improvements in math and reading performance between 2006 and 2011. This study evaluates the benefits of these nonmarginal improvements to Las Vegas area homeowners, using a residential sorting model. We estimate households’ preferences for multiple characteristics including the proportion of proficient students in their assigned elementary school. The estimation accounts for the endogeneity of school quality using school boundary fixed effects. The welfare estimates suggest that the school quality improvements provided substantial benefits to the area's households. We find that benefit measures derived from a hedonic price model are substantially larger than our sorting model benefit measures.     

A SPATIAL HEDONIC APPROACH ON LAND USE CHANGE ANTICIPATIONS*

ABSTRACT This paper estimates land use conversion anticipation when zoning is the primary tool of land use regulation. Extending the Capozza and Helsey model (1989) to the case of uncertainty in future land use zoning, a spatialized hedonic model is proposed to estimate such anticipation phenomena at a fine level (cadastral unit). Estimations use Mixed Geographically Weighted Regression (MGWR) techniques with a two‐stage model that links agricultural and developable land markets. This allows for mapping varying spatial parameters that measure anticipation effects within the theoretical framework. Results confirm the influence of anticipation on agricultural land prices in the Provence region. Moreover, the level of data spatialization allows us to take into account intra‐municipalities' heterogeneity of land use conversion anticipation.     

NEIGHBORHOOD DYNAMICS AND PRICE EFFECTS OF SUPERFUND SITE CLEAN‐UP*

ABSTRACT Numerous hedonic price analyses estimate price effects associated with hazardous waste site remediation or other environmental variation. This paper estimates a neighborhood transition model to capture the direct price effect from Superfund site clean‐up and the indirect price effects arising from residential sorting and changes in investment in the housing stock following clean‐up. First‐difference models of neighborhood change and a national sample are used. This approach fails to find consistent positive direct price effects. Positive indirect effects, however, may arise through residential sorting and neighborhood investment spurred by remediation. The findings can be sensitive to policy endogeneity and model specification.     

Time,hedonic migration,and household production

"A hedonic migration model is developed where regional amenities are viewed as influencing household production within the framework of the new demand theory. The inputs to household production are goods, time and housing. It is shown that economic growth in the economy as a whole will increase the relative attractiveness of regions that are relatively time-saving, in the sense that they have a lower time elasticity of household production. Hence, migration will flow into time saving regions and housing costs in those regions will rise as real GDP grows." The implied geographical focus is on the United States.     

BAYESIAN MODEL AVERAGING IN THE CONTEXT OF SPATIAL HEDONIC PRICING: AN APPLICATION TO FARMLAND VALUES

ABSTRACT Specification uncertainty arises in spatial hedonic pricing models because economic theory provides no guide in choosing the spatial weighting matrix and explanatory variables. Our objective in this paper is to investigate whether we can resolve uncertainty in the application of a spatial hedonic pricing model. We employ Bayesian Model Averaging in combination with Markov Chain, Monte Carlo Model Composition. The proposed methodology provides inclusion probabilities for explanatory variables and weighting matrices. These probabilities provide a clear indication of which explanatory variables and weighting matrices are most relevant, but they are case specific.     

What's a School Worth to a Neighborhood? A Spatial Hedonic Analysis of Property Prices in the Context of Accommodation Reviews in Ontario

Due to a change in capital funding formula, many school boards across the Province of Ontario engaged in Accommodation Reviews to rationalize the supply of school capacity. This process led to numerous school closures and raised important policy questions regarding the economic value of a school in terms of its capitalization into property values and, by extension, how the closure of a school might affect local neighborhoods. To explore these questions, this research uses spatial hedonic methods to estimate the implicit value of accessibility to schools in the City of Hamilton, Ontario. Spatial Durbin model results provide evidence of a significant negative correlation between distance to schools and housing prices in the Canadian context. This suggests that accessibility to schools is capitalized into property values and that the closure of a neighborhood school may result in potentially significant losses of economic value in communities.     

Place-to-Place Rent Comparisons among Canadian Cities

This paper estimates average monthly gross rents for comparable rented private-sector accommodation in Census Metropolitan Areas across Canada. By “gross rent” is meant the typical monthly payment in a CMA for a principal residence by a tenant of given traits under the conditions of a standard lease to a for-profit landlord in competitive market equilibrium for premises used exclusively for accommodation, in an arm's length transaction, and includes heating and utility expenses where paid separately by the tenant. A single average gross rent is estimated for each city for dwellings and households, each with specified characteristics. This paper reviews the application of hedonic price models for this purpose, identifies shortcomings of current research in the field, and suggests a new form for such models. This new model is estimated using microlevel data from a sample of renter households taken across the twenty-three largest urban areas in Canada. A classical version of the model is fitted first to renter data for individual cities, and its limitations assessed. A measure of “relative supply” is introduced to help explain city to city variations in the hedonic prices. Then an all-city new model is estimated which incorporates relative supplies. This all-city model is then used to derive place-to-place rent comparisons.     

SPATIAL HEDONIC MODELS OF AIRPORT NOISE,PROXIMITY, AND HOUSING PRICES*

ABSTRACT Despite the refrain that housing prices are determined by “location, location, and location,” few studies of airport noise and housing prices have incorporated spatial econometric techniques. We compare various spatial econometric models and estimation methods in a hedonic price framework to examine the impact of noise on 2003 housing prices near the Atlanta airport. Spatial effects are best captured by a model including both spatial autocorrelation and autoregressive parameters estimated by a generalized moments approach. In our preferred model, houses located in an area in which noise disrupts normal activities (defined by a day–night sound level of 70–75 decibels) sell for 20.8 percent less than houses located where noise does not disrupt normal activities (defined by a day–night sound level below 65 decibels). The inclusion of spatial effects magnifies the negative price impacts of airport noise. Finally, after controlling for noise, houses farther from the airport sell for less; the price elasticity with respect to distance is −0.15, implying that airport proximity is an amenity.     

LAND BANK 2.0: AN EMPIRICAL EVALUATION

In 2009, Cuyahoga County, Ohio (Cleveland and 58 suburbs), established a land bank to acquire low‐value properties, mitigate blighted housing, and slow the decline of property values. This empirical study evaluates the effectiveness of the land bank by estimating spatially corrected hedonic price models using sales near the land‐bank homes. The land bank reduces the negative externalities of the properties it acquires. Its largest impact is the preservation of equity in unsold homes. We also estimate the recovered value for homes sold during the study period and the property tax revenue that may have been forgone, absent the land bank.     

Impacts of an Iron and Steel Plant on Residential Property Values

The hedonic price method is used to estimate the relationship between residential property values and proximity to an integrated iron and steel plant located in the outskirts of Gijón, a city in the north of Spain. Empirical results suggest that there is a statistically significant negative relationship between housing values and the distance from the iron and steel plant. From a partial equilibrium analysis, increasing the distance from the plant, decreasing plant production or dismantling the plant would lead to an increase in the value of the housing units. The results show as well that the housing units located nearest to the factory would be the most favoured by applying the aforementioned changes.     

VALUING ENVIRONMENTAL QUALITY: A SPACE‐BASED STRATEGY*

ABSTRACT This paper develops and applies a space‐based strategy for overcoming the general problem of deriving the implicit demand for nonmarket goods. It focuses specifically on evaluating one form of environmental quality, distance from Environmental Protection Agency designated environmental hazards, via the single‐family housing market in the Puget Sound region of Washington State. A spatial two‐stage hedonic price analysis is used to: (i) estimate the marginal implicit price of distance from air release sites, hazardous waste generators, hazardous waste handlers, superfund sites, and toxic release sites; and (ii) estimate a series of implicit demand functions describing the relationship between the price of distance and the quantity consumed. The analysis, which represents an important step forward in the valuation of environmental quality, reveals that the information needed to identify second‐stage demand functions is hidden right in plain sight—hanging in the aether of the regional housing market.     

The Value of an Ocean View: an Example of Hedonic Property Amenity Valuation

This paper presents a method of quantifying variation in quality in an amenity as a component of an hedonic property amenity valuation. The paper considers the residential land amenity of an ocean view, a situation where there is typically substantial variation in the quality of the view between sites. The method is effectively a scoring system based on three sub-characteristics of the ocean view. It is illustrated by application to a coastal housing subdivision in Western Australia. The results provide an estimate of the increase in the sale price of a site attributable to the quality of the site’s ocean view. The method has a potential role in coastal land use management decisions.     

Housing Price Gradients: The Intersection of Space and Built Form

A hedonic housing price model, implemented for the Dallas region, reveals a housing market structured around multiple nodes, some of which give rise to positive and others to negative externalities. The utility/disutility derived from relative location is capitalized into the size and quality of the housing stock and the nature of neighborhood amenities. The result is a convergence of space and built form.     

RESEARCH IN PROGRESS IN SCANDINAVIA

The authors quantitatively analyze the effect of railroad construction on agricultural land values in the often overlooked, agriculturally oriented, trans-Mississippi West. This region is unique in American history in that, at the end of the nineteenth century, the railroad itself preceded widespread settlement. Using a hedonic model, they show that railroad transport increased agricultural land values in this region by more than 20 percent, which had a larger impact than recent studies have found for other regions. Moreover, the authors found that the addition of a railroad to a county significantly increased its growth in land values. This finding is contrary to that of existing studies. Finally, the authors show statistically that the railroad and land values were not endogenously determined, lending credibility to the causality of the results presented in their hedonic and growth models. These results indicate a valuable alternative approach to use in the historical analysis of transportation infrastructure and its impact on land prices.     

AMENITIES VERSUS LABOR MARKET OPPORTUNITIES: CHOOSING THE OPTIMAL DISTANCE TO MOVE*

ABSTRACT. A recent debate in the regional economics literature has focused attention on the motivation behind an individual's decision to migrate. Human-capital migration models emphasize labor market disequilibria whereas alternative (hedonic) migration models stress households’altered demand for nontraded goods. In this paper, we test the relative importance of these two possible motivations for moving between metropolitan areas. We use an intercity hedonic model to decompose wages into equilibrium and disequilibrium components. We then compare the separate influences of amenities and the disequilibrium component of wages on the distance moved between two metropolitan areas. Our findings indicate that both economic factors and amenity differentials are significant factors in explaining regional migration.     

TRAFFIC EXTERNALITIES AND SINGLE-FAMILY HOUSE PRICES*

ABSTRACT. This study is the first to lend empirical support to the common belief that traffic intensity affects property values. Using a standard hedonic pricing model, this paper investigates the price effects on housing of traffic within a neighborhood. Results using data on single-family housing transactions for two different locations in a medium-sized city show a substantial negative price effect of traffic externalities. The magnitude of the effect is shown to be location specific.