The hedonic regression method is a regression technique used to determine the value of a good, service, or asset by fractionating the product into constituent parts or characteristics. It is done to determine the contributory value of each characteristic separately through regression analysis.

The regression model should be able to place values and weights on each component or contributory factor to determine the value of the composite product. Hedonic methods can be linear, non-linear, variable interaction, or other valuation scenarios of different complexities.

Hedonic methods are used to estimate the price of assets absent on the market in certain periods, but the information on their pricing is crucial in constructing price relatives. It is based on the theory that the price of an asset is a function of its quantifiable characteristics, which can be plotted in a regression model to determine how the price changes with regard to changes in each characteristic.

Asset characteristics differ according to the asset but can include various elements, such as weight, color, speed, power, size, location, form, etc. There can be non-numeric characteristics that are represented by dummy variables, and the regression coefficients represent the contributory characteristics of the product price. Hence, the hedonic model is used to estimate the effects of changes in the quality of a product on its price.

Hedonic methods are largely used in real estate pricing to estimate the value of properties. Real estate pricing is determined by a variety of factors that make hedonic regression the perfect estimation tool. Hedonic methods are also used in constructing consumer price indices (CPI) by using the hedonic model to adjust for differences in characteristics between assortments of goods in calculating the CPI.

Application of Hedonic Regression Method to Real Estate Pricing

The hedonic regression method’s most widely applicable use is in the real estate sector to estimate the value of property prices. The regression models assume that property prices will reflect the value of characteristics that are considered important by people making the purchase, including environmental characteristics.

To apply hedonic regression methods to property pricing, participants should first carry out a data-gathering exercise on property sales for a predetermined period.

The data should include the following:

Property selling prices and the respective locations of the properties

Property characteristics that affect property selling prices, such as type of property, size, number of rooms, size of rooms, etc.

Neighborhood characteristics that affect prices, such as property tax, crime rate, scenic views, quality of schools, etc.

Accessibility characteristics that affect prices, such as proximity to shopping centers, malls, and workplaces, availability of public transport, etc.

Environmental characteristics that affect prices, such as quality of water and air, etc.

The data is analyzed using hedonic regression methods to find the effect of a variety of characteristics on the price of the property. The regression results will indicate how much the value or price of properties will change for a given change in each characteristic, holding other characteristics constant.

Complications in the analysis can be brought about by factors such as the relationship between the price and any of its characteristics that may not be linear – i.e., property prices may increase at a decreasing or increasing rate when there are changes in the characteristics.

Multicollinearity between variables/characteristics is also another challenge, where their changes are highly correlated. Hence, different functional forms and model specifications for data analysis should be proposed and considered.

Hedonic Regression Function

The hedonic regression function is illustrated in the following steps. The function illustrates the relationship between the price of the asset (being the dependent variable) and the components/characteristics of the asset (being the independent or explanatory variables).

pi = j (ci)

Where:

p is the price of a variety i of a good

ciis a vector of characteristics associated with the variety of the good

We will use a real estate example to demonstrate the hedonic regression function in an applicable format.

p = (loc, str, acc, env, nei)

Where:

p is the price of a property

The explanatory variables are the characteristics that determine the price of a property being:

loc is the location characteristics, i.e., urban, rural, distance from the city center, etc.

str is the structure of the property, i.e., number and size of rooms, size of the stand, property age, etc.

acc is the accessibility of the property, i.e., proximity to social amenities, public transport accessibility, etc.

env is the environmental quality, i.e., quality of air, quality of water, etc.

neiis the neighborhood characteristics, i.e., crime rate, scenic views, quality of schools, etc.

Therefore, a change in the price of the property as a result of a marginal change in any one of these characteristics is termed hedonic price. It is the additional cost of buying a property that is marginally superior in terms of any one of the explanatory characteristics. The hedonic price is also called the implicit price or the rent differential.

The basic assumption of the hedonic function is that it has a multiplicative functional form where, as a characteristic increases, the price of a property increases but at a decreasing rate. This assumption can be expressed as follows:

p = (b0locb1, strb2, accb3, envb4, neib5)

The parameters b1 to b5 are elasticities. They measure the proportional change in prices as a result of a proportional change in characteristics. The hedonic price of any particular characteristic is the slope of the above equation with regard to that specific characteristic.

The hedonic price of property environmental characteristics depends on the value of the parameter b4, the price of the property, and the property’s environmental characteristics. The hedonic price of a characteristic can be construed as the willingness to pay due to a marginal increase in that specific characteristic.

The next section of the hedonic regression model estimates the willingness to pay the price for a property taking into account different incomes and preferences. The function for willingness to pay is as follows:

Ploc = W (loc, Y, Z)

Hence, the willingness to pay for the location component is dependent on the following attributes:

Loc is the location of the property

Yis income level

Zis tastes/preferences based on race, social background, age, etc.

Advantages of Hedonic Regression Pricing

The hedonic regression method can be used to estimate property and other asset values based on purchasers’ actual choices.

Property markets are comparatively information efficient, and the use of hedonic pricing is likely to result in good indications of value.

The use of hedonic regression methods in real estate is effective, as property sales data is readily available, and relatable secondary data to get descriptive variables can easily be accessed or generated.

Hedonic pricing is versatile, enabling it to be adapted to other market goods and services and environmental quality.

Limitations of Hedonic Regression Methods

1. Information

All parties should obtain prior knowledge of all the positive and negative externalities about the asset to be purchased. It involves knowing all the information that should affect the demand or decision to purchase the asset or product.

2. Validity of measurement of explanatory components

There is a need for high-quality measures of explanatory characteristics or components. Using low-quality measurements can result in erroneous explanatory coefficients being generated, as well as invalid regression models.

3. Market limitations

The model needs to have a wide variety of assets or properties to choose from with a mixture of characteristics that a purchaser may require. It means individuals should be in a position to identify all their desired characteristics in a product. However, in the real world, it seldom happens like that, as some characteristics are met while others may be totally absent.

4. Multicollinearity

Multicollinearity is a situation where two or more explanatory variables are highly correlated or linearly related. When it comes to real estate, large houses with expansive acreage are commonly found in suburbs and the country, and more compact smaller houses are found in urban areas. It is because population density is higher in the urban areas than in the country and suburbs. Hence, it becomes difficult to separate population density and property size in an accurate manner.

5. Price changes

The hedonic model assumes an automatic adjustment in market price due to changes in any of the explanatory characteristics. However, in reality, there may be a lag related to the change, particularly where the market is not that vibrant or active.

6. Environmental benefits

The scope of environmental benefits is largely limited to issues relating to the property.

The hedonic method assumes purchasers can select a combination of their preferred features in relation to their income. However, the property market may be affected by other factors, such as taxes, interest rates, etc.

The hedonic regression method can be complex to execute and interpret and needs people with statistical expertise.

Results of the model are largely reliant on model specifications.

A large amount of data needs to be gathered and manipulated

Additional Resources

Thank you for reading CFI’s guide to Hedonic Regression Method. To keep advancing your career, the additional CFI resources below will be useful:

Develop analytical superpowers by learning how to use programming and data analytics tools such as VBA, Python, Tableau, Power BI, Power Query, and more.