Search results

The purpose of this study is to compare the predictive performance of the hedonic multivariate regression model with the probabilistic neural network (PNN)-based general regression neural network (GRNN) model of housing prices in “Pune-India.”

Data on 211 properties across “Pune city-India” is collected. The price per square feet is considered as a dependent variable whereas distances from important landmarks such as railway station, fort, university, airport, hospital, temple, parks, solid waste site and stadium are considered as independent variables along with a dummy for amenities. The data is analyzed using a hedonic type multivariate regression model and GRNN. The GRNN divides the entire data set into two sets, namely, training set and testing set and establishes a functional relationship between the dependent and target variables based on the probability density function of the training data (Alomair and Garrouch, 2016).

While comparing the performance of the hedonic multivariate regression model and PNN-based GRNN, the study finds that the output variable (i.e. price) has been accurately predicted by the GRNN model. All the 42 observations of the testing set are correctly classified giving an accuracy rate of 100%. According to Cortez (2015), a value close to 100% indicates that the model can correctly classify the test data set. Further, the root mean square error (RMSE) value for the final testing for the GRNN model is 0.089 compared to 0.146 for the hedonic multivariate regression model. A lesser value of RMSE indicates that the model contains smaller errors and is a better fit. Therefore, it is concluded that GRNN is a better model to predict the housing price functions. The distance from the solid waste site has the highest degree of variable senstivity impact on the housing prices (22.59%) followed by distance from university (17.78%) and fort (17.73%).

The study being a “case” is restricted to a particular geographic location hence, the findings of the study cannot be generalized. Further, as the objective of the study is restricted to just to compare the predictive performance of two models, it is felt appropriate to restrict the scope of work by focusing only on “location specific hedonic factors,” as determinants of housing prices.

The study opens up a new dimension for scholars working in the field of housing prices/valuation. Authors do not rule out the use of traditional statistical techniques such as ordinary least square regression but strongly recommend that it is high time scholars use advanced statistical methods to develop the domain. The application of GRNN, artificial intelligence or other techniques such as auto regressive integrated moving average and vector auto regression modeling helps analyze the data in a much more sophisticated manner and help come up with more robust and conclusive evidence.

To the best of the author’s knowledge, it is the first case study that compares the predictive performance of the hedonic multivariate regression model with the PNN-based GRNN model for housing prices in India.

The purpose of this paper is to test the asymptotic properties and prediction accuracy of two innovative methods proposed along the hedonic debate: the geographically weighted regression (GWR) and the generalized additive model (GAM).

The authors assess the asymptotic properties of linear, spatial and non-linear hedonic models based on a very large data set in Germany. The employed functional form is based on the OLS, GWR and the GAM, while the estimation methodology was chosen to be iterative in forecasting, the fitted rents for each quarter based on their 1-quarter-prior functional form. The performance accuracy is measured by traditional indicators such as the error variance and the mean squared (percentage) error.

The results provide evidence for a clear disadvantage of the GWR model in out-of-sample forecasts. There exists a strong out-of-sample discrepancy between the GWR and the GAM models, whereas the simplicity of the OLS approach is not substantially outperformed by the GAM approach.

For policymakers, a more accurate knowledge on market dynamics via hedonic models leads to a more precise market control and to a better understanding of the local factors affecting current and future rents. For institutional researchers, instead, the findings are essential and might be used as a guide when valuing residential portfolios and forecasting cashflows. Even though this study analyses residential real estate, the results should be of interest to all forms of real estate investments.

Sample size is essential when deriving the asymptotic properties of hedonic models. Whit this study covering more than 570,000 observations, this study constitutes – to the authors’ knowledge – one of the largest data sets used for spatial real estate analysis.

This study aims to estimate the quality-adjusted changes in residential mobile consumer prices by controlling for the changes in the relevant service characteristics and quality, in a case study on Hungary between 2015 and 2021; compare the results with changes measured by the traditionally calculated official telecommunications price index of the Statistical Office; and discuss separating the hedonic price changes from the effect of a specific government intervention that occurred in Hungary, namely, the significant reduction in the value added tax rate (VAT) levied on internet services.

Since the price of commercial mobile offers does not directly reflect the continuous improvements in service characteristics and functionalities over time, the price changes need to be adjusted for changes in quality. The authors use hedonic regression analysis to address this issue.

The results show significant hedonic price changes over the observed seven-year period of over 30%, which turns out to be primarily driven by the significant developments in the comprising service characteristics and not the VAT policy change.

This paper contributes to the literature on hedonic price analyses on complex telecommunications service plans and enhances this methodology by using weights and analysing the content-related features of the mobile packages.

This paper aims to examine house price drivers in Dubai, addressing nonlinearity and heterogeneity.

The study applies a combination of linear and nonlinear, as well as quantile regression, specifications to address these concerns and better explain the real-world phenomenon.

The study shows the double-log quantile regression approach is an overarching description of house price drivers, confirming that not only the price of housing and its determinants are non-linearly related but also that their relationship is heterogeneous across house price quantiles. The findings reveal the prevalence of sub-market differentials in house price sensitivity to house attributes such as size (in square meters), location and type of house, as well as government laws. The study also identifies the peaks and deflation, as well as the rebounding nature of the house price bubble in Dubai.

The data used are limited, in that information on only a few house attributes was available. Future research should include data on other house attributes such as house quality, zip codes and composition.

The findings of this study are expected to suggest results with significant ramifications for researchers, practitioners and policy makers. From a policy perspective, there is an obvious interest in understanding whether the price of housing is affected by different attributes differently along its distribution.

This study allows policy makers, developers and buyers of higher-priced houses to behave differently from buyers of lower-priced or medium-priced houses.

Methodologically, it demonstrates alternative linear and nonlinear, as well as quantile regression, specifications to address two increasing concerns in the house price literature: nonlinearity and heterogeneity. Unlike most other studies, this study used a rich data (140,039 day-to-day transactions of 10 years’ pooled data). The Dubai housing market presents an interesting case. UAE (Dubai, in particular) is named as the second-hottest marketplace for global residential property investors, ahead of Singapore, the UK and Hong Kong (Savills plc, 2015).

This paper applies the hedonic pricing model (HPM) approach to identify critical determinants of apartment value and employs the technique to develop a valuation model that can accurately estimate the value of apartments.

The research employed a case study design that was limited to transaction sales and attribute data of apartments in Nyali estate, Mombasa County in Kenya. A sample of 120 sales of apartments obtained from registered real estate firms was analyzed using quantitative methods.

According to the study results, the hedonic valuation model developed comprises four critical determinants of apartment value, namely, number of parking lots, presence of swimming pool, age of apartment and provision of balcony. The hedonic model was tested and found to be accurate and reliable in estimating apartment value.

The model will improve accuracy, reliability and efficiency in valuation. The application of the model in the valuation of apartments is, however, limited to the case study area where the data are obtained. The scope of application of the model may be improved by increasing the sample size to include apartment sales data from other estates in Mombasa County.

Previous studies that have used the HPM technique in analysis of apartment values have focused on the “explanatory” and “contributory” power of attributes on apartment values, rather than the development and use of the model to measure value. The present study is the first to develop a HPM equation for property value estimation in the apartment real estate sector in Kenya.

The purpose of this paper is to construct a hedonic property price index in the segmented housing market.

Three different research questions are investigated. The first considers how to identify separate local housing markets, with the use of a regression‐tree approach, and the second concerns when it is possible to update a price index, with a recursive regression approach. Finally, the question about seasonal adjustment is investigated.

Overall, the hedonic approach is the best method to use. Moreover, the County of Stockholm is not one market in the sense that the market can be represented by only one property price index. It can be best described as a number of different sub‐markets where the property prices grow differently. The results suggest that there exist at least five different price indexes in the County of Stockholm. The results also support that recursive regressions are two appropriate methods to answer the research questions. Here, the empirical analysis suggests that the parameter estimates converge relatively fast toward the estimate using all observations.

The paper illustrates how to derive sub‐markets in the construction of a price index and when to update a price index series.

The introduction of new financial products, such as property derivatives, to the market has made the construction and quality of property price indexes more important. High quality price indexes are vital when it comes to, for example, pricing property derivatives. The paper facilitates this.

The aim of this paper is to present estimation results of hedonic price models as well as housing price indices for the Warsaw secondary market.

Three direct methods of constructing a hedonic price index and four indices that allow for quality adjustment are presented. The paper also discusses theoretical issues related to the estimation and interpretation of hedonic models.

It is shown that the imputation and the time dummy variable indices are subject to less variation than the characteristic price index. It is also shown that in comparison to the mean and the median, hedonic indices are less variable, which can be interpreted as partial control for quality changes in dwellings sold.

As this research project represents one of the first attempts of hedonic modelling applied to the Polish housing market, its results may be employed by appraisers to gain insight into behaviour of the Warsaw housing market. Practical implications focus on reliable measurement of house price dynamics in Poland. This paper supplies an appropriate methodology for addressing this question and offers empirical solutions.

Employment of hedonic models for construction of quality‐adjusted housing price indices has not yet been explored in Poland. The theoretical and practical aspects of hedonic indices presented in the paper open promising directions for the development of Polish statistics of real estate prices.

This study aims to assess housing affordability and estimate demand using a hedonic regression model in the context of Lucknow city, India. This study assesses housing affordability by considering various housing and household-related variables. This study focuses on the impoverished urban population, as they experience the most severe housing scarcity. This study’s primary objective is to understand the demand dynamics within the market comprehensively. An understanding of housing demand can be achieved through an examination of its characteristics and components. Individuals consider the implicit values associated with various components when deciding to purchase or rent a home. The components and characteristics have been obtained from variables relating to housing and households.

A socioeconomic survey was conducted for 450 households from slums in Lucknow city. Two-stage regression models were developed for this research paper. A hedonic price index was prepared for the first model to understand the relationship between housing expenditure and various housing characteristics. The housing characteristics considered for the hedonic model are dwelling unit size, typology, condition, amenities and infrastructure. In the second stage, a regression model is created between household characteristics. The household characteristics considered for the demand estimation model are household size, age, education, social category, income, nonhousing expenditure, migration and overcrowding.

Based on the findings of regression model results, it is evident that the hedonic model is an effective tool for the estimation of housing affordability and housing demand for urban poor. Various housing and household-related variables affect housing expenditure positively or negatively. The two-stage hedonic regression model can define willingness to pay for a particular set of housing with various attributes of a particular household. The results show the significance of dwelling unit size, quality and amenities (R² > 0.9, p < 0.05) for rent/imputed rent. The demand function shows that income has a direct effect, whereas other variables have mixed effects.

This study is case-specific and uses a data set generated from a primary survey. Although household surveys for a large sample size are resource-intensive exercises, they provide an opportunity to exploit microdata for a better understanding of the complex housing situation in slums.

All the stakeholders can use the findings to create an effective housing policy. The variables that are statistically significant and have a positive relationship with housing costs should be deliberated upon to provide the basic standard of living for the urban poor. The formulation of policies should duly include the housing preferences of the economically disadvantaged population residing in slum areas.

This paper uses primary survey data (collected by the authors) to assess housing affordability for the urban poor of Lucknow city. It makes the results of the study credible and useful for further applications.

Traditionally, early-stage investment decisions on buildings purely based initial capital costs and simply ignored running costs and total lifecycle cost. This was basically due to the absence of estimating models that yield running costs at the early design stage. Often, when the design of a building, which is responsible for 10–15% of its total cost, is completed, 80% of the total cost is committed. This study aims to develop a building characteristic-based model, which is an early-stage determinant of running costs of buildings, to predict the running costs of commercial buildings.

A desk study was carried out to collect running costs data and building characteristics of 35 commercial buildings in Sri Lanka. A Pareto analysis, bivariate correlation analysis and hedonic regression modelling were performed on collected data.

According to Pareto analysis, utilities, services, admin work and cleaning are four main cost constituents, responsible for 80% of running costs, which can be represented by highly correlated building characteristics of building height, number of floors and size. Approximately 94% of the variance in annual running costs/sq. m is expressed by variables of number of floors, net floor area and working hours/day together with a mean prediction accuracy of 2.89%.

The study has utilised a sample of 35 commercial buildings due to non-availability and difficulty in accessing running cost data.

Early-stage supportive running costs estimation model proposed by the study would enable construction professionals to benchmark the running costs and thereby optimise the building design. The developed hedonic model illustrated the variance of running costs concerning the changes in characteristics of a building.

This study aims to examine the impact of relative importance of local characteristics, distance from the city centre and unobservable spatial relation in explaining values of constant‐quality apartment units in Vienna.

Drawing on recent developments in spatial econometrics and spatial hedonic house price modelling, the rent gradient hypothesis is examined by means of hedonic regression and spatial hedonic regression. Spatial autocorrelation tests are applied in order to assess possible presence of spatial dependence. The authors borrow Florax et al.'s specification search strategy in order to choose the most appropriate spatial model specification.

This research shows that local characteristics – or particularities – proxied by district and distance from the city centre are important location variables with regard to the Viennese apartment market. The spatial analysis suggests that the apartment prices are spatially autocorrelated and the Viennese apartment market has a distance‐based neighbourhood structure. The main finding is, however, that residents are willing to bid more for constant‐quality apartment units that are close to the centre of the city.

Rent gradient hypothesis is usually tested within non‐spatial hedonic frameworks: this study estimates a spatial hedonic model additionally in order to allow for comparison of results. This is also the first article to apply recent developments in spatial econometrics to examine explicitly rent gradient theory in the context of the Viennese apartment market.