The choice of functional forms for hedonic price equations: Comment

doi:10.1016/0094-1190(85)90012-9

Journal of Urban Economics

Volume 18, Issue 2, September 1985, Pages 135-142

https://doi.org/10.1016/0094-1190(85)90012-9 Get rights and content

Abstract

Rosen [13], Freeman [4], Halvorsen and Pollakowski [6], and others have stressed that economic theory does not suggest an appropriate functional form for hedonic price functions.¹ It consequently is reasonable to try several functional forms and utilize the multiple regression equation with the best performance. In this spirit, Halvorsen and Pollakowski [6] recommend using the Box-Cox flexible functional form for hedonic analysis and measuring best performance with a goodness of fit test. The Box-Cox methodology has also been adapted in hedonic studies by Goodman [5], Linneman [10], Blomquist and Worley [1], and Eberts and Gronberg [3].² The Box-Cox is particularly suited for testing functional forms because many familiar forms such as semilog, log linear, and translog are subsets of the flexible Box-Cox permitting nested hypothesis testing.

In this note, we illustrate that the formal hypothesis testing advantage of the Box-Cox functional form is purchased at the expense of other important goals. The goal of most hedonic studies is to estimate the prices of the characteristics, to measure the response to changes in the prices, and/or to predict future expenditures. Using a best fit criterion to choose functional forms does not necessarily lead to more accurate estimates of characteristic prices. In fact, the large number of coefficients estimated with the Box-Cox functional form reduces the accuracy of any single coefficient which could lead to poorer estimates of specific prices. Second, because any negative number raised to a noninteger real power is imaginary, the traditional Box-Cox functional form is not suited to any data set containing negative numbers. Third, the Box-Cox functional form may be inappropriate for prediction. Since the mean predicted value of the untransformed dependent variable need not equal the mean of the sample upon which it is estimated, the predicted untransformed variable (housing value) will be biased. The predicted untransformed dependent variable may also be imaginary. Fourth, the nonlinear transformation results in complex estimates of slopes and elasticities which are often too cumbersome to use properly. We discuss each of these drawbacks and quantify them when possible in the remainder of this note.

References (15)

R. Eberts et al.
Wage gradients, rent gradients, and the price elasticity of demand for housing: An empirical investigation
J. Urban Econ.
(1982)
A. Goodman
Hedonic prices, price indices and housing markets
J. Urban Econ.
(1978)
J. Kau et al.
Urban land value functions and the price elasticity of demand for housing
J. Urban Econ.
(1979)
P. Linneman
Some empirical results on the nature of the hedonic price function for the urban housing market
J. Urban Econ.
(1980)
C. Sirmans et al.
The elasticity of substitution in urban housing production: AVES approval
J. Urban Econ.
(1979)
G. Blumquist et al.
Hedonic prices, demand for urban housing amenities, and benefit estimates
J. Urban Econ.
(1981)
G. Box et al.
An analysis of transformation
J. R. Stat. Soc. Ser. B
(1964)

There are more references available in the full text version of this article.

Cited by (202)

Improving hedonic housing price models by integrating optimal accessibility indices into regression and random forest analyses
2024, Expert Systems with Applications
Location indices are key in explaining variation in house prices. However, the definition of comprehensive indices capturing all locational features, along with their efficient and timely calculation, is usually one of the most complex dimensions of house price modeling. Existing difficulties result in partial location specifications, mostly due to three hurdles: (1) there is not a consensus on the best method to construct these indices, (2) what features (variables) to include: labor, demographic, commuting, etc., and (3) its creation requires granular and updated datasets. We introduce a methodology based on computer algorithms to create car and walk accessibility indices that address the previous concerns and capture location interactions among a wide range of variables. The selection of variables is based on an automated search of the best performing utility bearing gravitational accessibility indices for price prediction. Once these optimal indices are obtained, the method applies principal components analysis to secure their orthogonality. Using a unique dataset from a leading real estate portal in Europe, we illustrate and test for the city of Madrid their applicability in several house asking price models that are estimated using regression analysis and random forests (as a representative family of machine learning techniques). The experimental analysis reveals that using the optimal indices results in significant improvements in accuracy, for both regression-based models (13%) and random forests (21.6%), while achieving a substantial reduction in spatial autocorrelation (around 35%). The generated indices are clearly interpretable, which makes them a valuable tool for urban analyses (planning, transportation, sustainability, etc.). Finally, the methodology can be extended to other types of real state (commercial, industrial, etc.) and location (country, region, etc.).
Does district heating affect residential property prices? Case study of an urban area in South Korea
2023, Utilities Policy
This article investigates whether the residential heating method affects property prices in an urban area of South Korea. Sales data for 1760 apartments in Seocho District, Seoul, the country's capital, are employed. The property price equation is estimated, including the heating method as one attribute. The gap between the price of properties with a district heating system (DHS) and those with other heating methods, such as an individual heating system or central heating system, accounted for about 21.7% of apartment prices. Specifically, apartments with a DHS were more expensive than apartments with other heating methods.
International acceptance of automated modern tools use must-have for sustainable real estate market development
2022, Land Use Policy
Citation Excerpt :
The Automated Valuation Modelling evolution is strictly related to development of analytic methods and Information Technology Systems advancement. The selection of the analytic solutions and technology depends on researchers and aims of modelling (Cassel and Mendelsohn, 1985; d’Amato, 2018). The structure of automated valuation modelling is characterised by a few (constant) stages that are core of the solutions regardless of the technique, method or technology used.
The main aim of the paper is to systematise the terms and methodologies used in the property valuation and market analyses domain (single property or mass valuation). The need for this is justified by different semantic and procedural approaches and legal regulations in countries around the world. The research was carried out using the method of critical analysis of current state-of-art literature of the subject, valuation standards, and opinions of practitioners and experts of real estate markets available on social media. Answers of international respondents were gathered as well by using questionnaires. The paper fulfils the gap in perception and comprehension of specific terms and modern tools by entities connected with real estate domain. The clash of two extreme realities is being dealt with: on the one hand, traditional solutions based on universally accepted methods and techniques as well as faith in the infallibility and objectivity of a human analysing the real estate market dominate; on the other, modern technologies that are boldly entering. The main conclusion of the study is that entities should change perception of different automated solutions (e. g. AVM, CAMA, AAVM) as being operating in contradiction to ingrained methods and use them as an additional tool.
Which types of shopping malls affect housing prices? From the perspective of spatial accessibility
2020, Habitat International
Citation Excerpt :
According to hedonic price theory, the price of the commodity can be decomposed into the characteristic price or the implied price corresponding to each characteristic. Previous scholars have conducted significant research on the characteristic prices of housing prices, including education (Bae & Chung, 2013; Clark & Herrin, 2000), landscape (Cassel & Mendelsohn, 1985; Hui, Chau, Pun, & Law, 2007; Jim & Chen, 2010), transportation (So, Tse, & Ganesan, 1997; Golub, Guhathakurta, & Sollapuram, 2012; Yang, Zhou, & Shyr, 2019) and others. The shopping mall is a convenience for residents, and as such, consistently plays an important role in residential characteristics.
The shopping mall plays an important role in the daily life of a city's residents, as well as the economic development of the city, especially in neighboring areas. However, the mechanisms that shape the impact of shopping malls on housing prices remain unclear, particularly in the context of urban China. Considering both the location and quality of shopping malls, this study investigates two questions: 1) Which types of shopping malls impact housing prices, and 2) does this impact change with location? Using Hangzhou, China as an example, data for shopping malls built in Hangzhou prior to 2014 and second-hand housing transaction data from 2014 were collected and analyzed. Based on these data, shopping malls were further divided into several types, according to scale, grade, and tenant mix. Then, spatial accessibility to shopping malls was characterized using two gravity-based models. A geographically weighted model was also used to further analyze the spatial heterogeneity of the accessibility effects of shopping malls on housing prices, especially between the city center and the non-core areas. The study finds that the gravity-based model performed well, and that spatial accessibility to shopping malls had a significant positive impact on housing prices on a whole-city level, but this impact changed with the type of shopping mall and the urban area. Large-scale and high-end shopping malls only had a significant positive impact in the non-core areas of the city. In contrast, high-leisure shopping malls had a significant positive effect on most areas, including the city center.
Valuing bushfire risk to homeowners: Hedonic property values study in Queensland, Australia
2019, Economic Analysis and Policy
Bushfires are a common occurrence and are an inevitable natural event in many regions of Australia in most years. Despite the dangers of such bushfires to nearby properties and human life, humans continue to live in close proximity to bushfire prone areas. The pertinent questions asked in this study are whether residents are aware of the dangers of living in such areas- and if so, is it reflected in lower property values? Such residents have the choice of either discounting the risks of bushfires in their neighbourhoods or deciding to pay more to live in bushfire areas for the positive amenity values afforded by forested bushland settings. Buyers paying a premium price to live in close proximity to green space are well documented in hedonic property (HP) values studies. We examine this phenomenon using data available for forested bushfire prone areas in the immediate environs of the city of Brisbane, Queensland, Australia using an HP values approach. For this study sales data of 1028 houses in four suburbs are used. The regression results clearly show that residents in fact are paying more to be close to green space (forested areas) which is also clearly identified as bushfire prone areas. The threat of bushfires may have an effect on property prices but it is dominated by the desire to live close to green spaces.
Understanding the local impact of urban park plans and park typology on housing price: A case study of the Busan metropolitan region, Korea
2019, Landscape and Urban Planning
The valuation of urban parks using hedonic pricing has been thoroughly documented in a number of studies set in many cities. Just as the value of existing parks can be estimated by investigating the relationship between housing prices and parks, the value of future parks can also be estimated using this approach. This study recognized that a series of planning processes and land use transitions to create urban parks not only influences the perceptions of real estate buyers but also the quality of the local environment. From the apartment sales data for the Busan metropolitan region of Korea, data on 11,498 sales of apartments within walking distance to planned parks (as well as existing parks) were collected. These data were applied in an analysis comprising three categories describing different planning contexts for the parks: “comprehensive plans,” “implementation plans,” and “completed parks.” A set of explanatory variables representing housing, park, and neighborhood characteristics was selected, with additional remarks regarding the planning specifications that might influence apartment buyers’ perceptions, such as the park type and the age of a plan, as defined in the official plans of the city. The results showed that smaller park types in residential settings were preferred throughout the processes of park planning, while all types were preferred once the processes were completed. The preference in park types is likely associated with the quality of the planning guidelines as well as the size of the project and the duration of planning.

View all citing articles on Scopus

¹: The only theoretical restriction on the hedonic price function is that its price elasticity must lie in between the price elasticities of supply and demand. Since both the supply and demand curves are not observable, even this mild restriction is not very helpful in choosing functional forms.

²: The Box-Cox functional form has been used in several other urban contexts by Kau and Lee [8], Kau and Sirmans [9], Sirmans et al. [14], Sirmans and Redman [15], and McDonald [11]. Some of the problems, for example with prediction, raised in this paper on hedonics apply to these uses as well.

View full text

The choice of functional forms for hedonic price equations: Comment

Abstract

J. Urban Econ.

J. Urban Econ.

J. Urban Econ.

J. Urban Econ.

J. Urban Econ.

Hedonic prices, demand for urban housing amenities, and benefit estimates

J. Urban Econ.

An analysis of transformation

J. R. Stat. Soc. Ser. B