Determinants of Housing Price:

An Analysis of the Cross-section Data on

Countries
Group 1:
Mohapatra, Amisha (USE22003)
Dash, Kinsey (USE22012)
Kaur, Loveleen (USE22023)
Singh, Trisha (USE22024)
Kaur, Simran (USE22025)

Xavier School of Economics

29 March 2024
 1. Introduction
The housing market plays a pivotal role in the economic landscape of any nation, reflecting
both the aspirations of individuals and the broader socio-economic dynamics at play.
Understanding the determinants of housing prices is of paramount importance, not only for
policymakers but also for investors, homeowners, and researchers alike. This research paper
aims to delve into the intricate web of factors influencing housing prices across countries,
specifically focusing on urbanization, economic indicators, and socio-demographic variables.

The housing market is a complex ecosystem influenced by a multitude of factors.

Historically, urbanization has been a significant driver of housing demand, with rapid urban
growth leading to increased pressure on housing supply and subsequent price escalation. The
migration of populations from rural to urban areas changes lifestyle preferences and
economic opportunities, further impacting housing dynamics. Understanding the relationship
between urbanization and housing prices is essential for anticipating future housing trends
and formulating effective urban development policies.

Moreover, economic indicators such as gross national income (GNI), inflation rate, and
mortgage interest rates substantially influence housing prices. Changes in these variables can
significantly impact affordability, investment decisions, and overall market dynamics. For
instance, higher GNI levels indicate increased purchasing power, potentially driving up
demand for housing and leading to price appreciation. Conversely, rising inflation or
mortgage interest rates may erode purchasing power and deter prospective homebuyers,
affecting housing market activity and prices.

Additionally, socio-demographic factors such as population density, unemployment rates, and

affordability indices play crucial roles in shaping housing markets. Population density affects
demand for housing, as higher densities often lead to greater competition for limited housing
stock, thereby exerting upward pressure on prices. Unemployment rates can impact
individuals' purchasing power and housing affordability, with higher unemployment levels
potentially resulting in reduced demand and downward pressure on prices. The affordability
index provides insights into the relationship between income levels and housing costs,
shedding light on the accessibility of housing for different segments of the population.

The objective of the study is to identify and analyse the key determinants of housing prices
by examining a comprehensive set of variables encompassing urbanization, economic
indicators, and socio-demographic factors. This study seeks to pinpoint the primary drivers of
housing price variations across countries.

Another objective is to assess the individual and collective impact of urbanization, economic
indicators, and socio-demographic variables on housing prices. Through rigorous statistical
analysis, we aim to quantify the influence of urbanization, nominal housing prices, inflation
rate, GNI, mortgage interest rate, population density, unemployment, and affordability index
on housing prices, both individually and collectively. This will provide insights into the
relative importance of each factor and their interplay in shaping housing market dynamics.

This research contributes to the existing knowledge of housing market dynamics by

elucidating the multifaceted determinants of housing prices and their implications for policy
formulation and investment decision-making. Through a robust analytical framework, we
seek to unravel the complexities of housing markets and provide valuable insights for
stakeholders navigating this critical aspect of the economy.
2. Brief Review of Literature

The determinants of housing prices have been extensively studied in the literature, and many
researchers have identified a wide range of factors that influence housing prices. The
literature review on the determinants of housing prices based on cross-sectional data on
countries is a significant aspect of housing market research. Cross-sectional data analysis is a
statistical method used to analyse data collected from different groups at a particular point in
time. The significance of cross-sectional data analysis in the literature review on the
determinants of housing prices lies in its ability to provide a comprehensive picture of the
housing market dynamics across different countries. By analysing the data from different
regions, researchers can identify the commonalities and differences in the factors influencing
housing prices.

In the context of housing market research, cross-sectional data analysis examines the
determinants of housing prices across different countries and regions. One of the most
influential works in this area is the study in developed countries, such as the United States by
Rosen (1974), which laid the foundation for the hedonic pricing model. This model suggests
that the price of a housing unit can be broken down into the implicit prices of its various
attributes, such as location, size, age, and amenities.

Location is widely recognized as a crucial determinant of housing prices. Numerous studies

have found that proximity to desirable amenities, such as good schools, parks, and public
transportation, can significantly increase housing prices (Gibbons & Machin, 2008; Cervero
& Duncan, 2004). Conversely, proximity to undesirable factors, such as high crime rates or
environmental hazards, can decrease housing prices (Mustafa et al., 2018; Fitria et al., 2015).

The structural characteristics of a housing unit, such as size, age, and quality of construction,
also play a significant role in determining its price. Larger houses and those with more
bedrooms and bathrooms tend to command higher prices (Sirmans et al., 2005). However,
older homes may sell at a discount due to potential maintenance issues and outdated features
(Goodman & Thibodeau, 1995).

A cross-sectional analysis of housing prices across different countries can help identify the
macroeconomic factors that influence housing prices across borders, such as interest rates,
employment levels, and income levels. Lower interest rates make mortgages more affordable,
increasing demand and prices (Himmelberg et al., 2005). Higher employment levels and
income growth can also increase housing demand and higher prices (Malpezzi, 1999). The
cross-sectional analysis can also highlight the role of policy and regulation in the housing
market dynamics by examining the impact of zoning regulations and restrictions in different
countries.

Additionally, several studies have examined the impact of supply-side factors on housing
prices. Land availability, zoning regulations, and construction costs can influence the housing
supply and affect prices (Quigley & Raphael, 2005; Malpezzi & Mayo, 1997). It is important
to note that the relative importance of these determinants can vary across different geographic
regions and housing markets (Huang & Tang, 2012; Sui & Rahim, 2011).
Overall, the literature suggests that the determinants of housing prices are complex and
multifaceted. The findings of various studies highlight the importance of considering multiple
factors when analysing housing prices.
Numerous studies have delved into the variables influencing housing prices. Below is a
detailed review of some of the significant research findings:

1. In their work titled "Housing Market Dynamics: Evidence of Mean Reversion and
Downward Rigidity," Capozza, Hendershott, Mack, and Mayer (2002) explored the
factors influencing housing prices. Their findings suggest that a combination of
economic elements (such as income levels and interest rates) and the physical
attributes of the house (including size and age) play a substantial role in determining
housing prices. They also presented evidence of mean reversion in housing prices,
which implies that prices tend to revert to the long-term average over a period.

2. Cook's 2003 study titled "House Price Determinants in UK Regions" demonstrated

that regional aspects, including employment and population density, significantly
impact housing prices. As per the study's findings, an increase in employment levels
leads to a rise in housing prices. This indicates a strong correlation between economic
health and housing prices.

3. Glaeser and Gyourko, in their 2003 study "The Impact of Zoning on Housing
Affordability," concluded that zoning regulations and restrictions could significantly
impact housing prices by limiting the supply of new housing. This study highlights
the role of policy and regulation in the housing market dynamics.

4. Poterba's 2004 study, "The Determinants of the Price of Housing Services," found that
several factors influence the price of housing services. These include the user cost of
housing capital, the price of non-housing consumption, and demographic factors. This
research broadens the scope of understanding housing prices by considering the cost
of housing services.

5. Saiz's 2010 work, "The Geographic Determinants of Housing Supply," discovered that
geographical restrictions, such as land availability and regulatory constraints,
significantly impact the housing supply and, in turn, housing prices. This study
emphasizes the role of geographical limitations in housing affordability.

6. A recent study by Deng, Gyourko, and Wu in 2012 titled "The Determinants of House
Prices in Chinese Cities" suggested that apart from common determinants like income
levels and interest rates, citizens' growth expectations significantly influence housing
prices in China. This highlights the cultural and societal factors that can influence
housing prices.

The synthesis of these studies suggests that a blend of economic factors, physical and
geographical characteristics, regulatory constraints, and demographic factors determine
housing prices. However, the relative importance of these factors can vary across different
regions and countries, highlighting the complexity of the housing market.

3. Data and Methodology

After discussing the potential determinants of the housing prices, we now focus on the
specific panel dataset and variable construction used in this analysis. The empirical model
and estimation methods employed are also outlined.

The analysis utilizes a comprehensive panel dataset spanning multiple countries. This dataset
combines cross-sectional data across different nations, allowing for a more robust
examination of housing price determinants while accounting for variations across countries.

Regarding variable construction, we carefully define and operationalize the variables of

interest based on the theoretical foundations discussed earlier. The dependent variable is the
nominal housing price, while the independent variables encompass factors such as
macroeconomic indicators:
• Inflation Rate
• Gross National income
• Mortgage Interest Rate
• Urbanization
• Population density
• Unemployment
• Affordability Index

To analyse the relationships between these variables and the nominal house prices, we
employ an empirical model that allows for the estimation of the relative importance and
statistical significance of each determinant. The model specification is grounded in
established econometric techniques and incorporates appropriate controls and robustness
checks to ensure the validity and reliability of the results.

Furthermore, we describe the estimation methods used to analyse the panel data. These
methods are carefully selected to address potential issues such as unobserved heterogeneity,
endogeneity, and correlation, which can arise in panel data analyses. The chosen estimation
techniques aim to provide consistent and efficient estimates of the determinants' effects on
nominal house prices.

The data for this analysis is obtained from various sources, including the World Bank's World
Development Indicators (WDI) database, the International Monetary Funds (IMF),
Organisation for Economic Co-operation and Development (OECD), and Statista.

The dependent variable in this analysis is the nominal housing prices across countries.

• Nominal Housing Prices: Nominal housing prices, representing the market value of
residential properties, directly influence housing affordability and investment
decisions. Numerous econometric studies have investigated the determinants of
housing prices, including nominal prices, employing various methodologies. For
instance, research by Hsieh and Moretti (2003) utilized hedonic price models to
analyse the drivers of housing prices in the United States, finding that location,
neighbourhood amenities, and housing characteristics significantly affect nominal
prices.
 Nominal Housing Prices(in US $)
250
200
150
100
50
0

Luxembourg
Finland
Afghanistan

Iran

New Zealand
Australia
Bangladesh

Colombia

Russia
Latvia

Ukraine
Chile

Nepal

Switzerland
India

Mexico

Sri Lanka

Uzbekistan
Hungary

Portugal
Philippines

Thailand
Croatia

Slovenia
Brazil

Germany

Republic of Ireland

Zimbabwe
Norway

Vietnam
Denmark
Cameroon

Estonia

Italy

Singapore

South Korea

United Kingdom
The independent variables used to examine the determinants of housing prices are:

• Inflation Rate: The inflation rate can impact housing prices through its effect on
purchasing power, mortgage rates, and investor expectations. Higher nominal housing
prices can contribute to inflationary pressures by increasing the cost of living and
leading to higher consumer spending.

Inflation Rate(in%)
200.00%

150.00%

100.00%

50.00%

0.00%
Luxembourg

Saudi Arabia
Colombia

New Zealand

Switzerland
Pakistan

Turkey
France
Austria

Hungary

Portugal

Venezuela
Canada

Czech Republic

Morocco
Indonesia
Afghanistan

Brazil

Japan
Republic of Ireland

Slovenia
Spain

Zimbabwe
Estonia

United Kingdom

-50.00%

• Gross National Income (GNI): Gross national income reflects the total income
earned by residents of a country, which can influence housing demand and
affordability. Studies have analysed the relationship between GNI and housing prices,
often incorporating income elasticity estimates into econometric models. Increasing
nominal housing prices may positively impact GNI by reflecting a buoyant housing
market, leading to increased economic activity, and potentially higher incomes for
homeowners.
 Gross National Income(in $)
100,000
90,000
80,000
70,000
60,000
50,000
40,000
30,000
20,000
10,000
0 Colombia

New Zealand

Switzerland
Turkey
Brazil

France

Luxembourg

Saudi Arabia
Hungary

Portugal

Venezuela
Canada

Czech Republic

Morocco
Austria

Indonesia

Slovenia
Republic of Ireland
Japan
Afghanistan

Pakistan

Spain

Zimbabwe
Estonia

United Kingdom
• Mortgage Interest Rates: Mortgage interest rates play a crucial role in determining
housing affordability and demand. Nominal housing prices can affect mortgage
interest rates by influencing the demand for mortgage loans and the risk perception of
lenders. Higher housing prices may lead to higher demand for mortgages, putting
upward pressure on interest rates. Changes in interest rates can affect the cost of
borrowing for homebuyers, influencing their purchasing power and housing choices.
Econometric studies have investigated the relationship between mortgage rates and
housing prices, often employing vector autoregression (VAR) models or structural
equation modelling (SEM).

Mortgage Interest Rate(in%)

8000.00%
7000.00%
6000.00%
5000.00%
4000.00%
3000.00%
2000.00%
1000.00%
0.00%
Czech Republic
Colombia

New Zealand

Switzerland
France

Luxembourg

Turkey
Hungary

Saudi Arabia
Portugal
Morocco

Venezuela
Austria

Canada

Indonesia
Afghanistan

Brazil

Spain
Republic of Ireland
Japan

Pakistan

Slovenia

Zimbabwe
Estonia

United Kingdom

• Urbanization: Urbanization is a key factor influencing housing prices due to its

impact on demand for housing and land scarcity. As areas become more urbanized,
population density increases, leading to greater demand for housing, which in turn can
drive up prices. In our analysis, we have considered the urban population and rural
population as dummy variables representing the level of urbanization in a country. It
 takes the value of 0 for countries with an urban/ rural population between 0 and
1,000,000 (low urbanization), and 1 for countries with an urban/ rural population
between 1,000,000 and 9,000,000 (high urbanization).

Urban and Rural Population

1E+09
900000000
800000000
700000000
600000000
500000000
400000000
300000000
200000000
100000000
0

Turkey
Colombia

New Zealand

Switzerland
France
Brazil

Luxembourg

Saudi Arabia
Hungary

Portugal
Austria

Canada

Czech Republic

Morocco

Venezuela
Indonesia
Republic of Ireland

Zimbabwe
Japan

Slovenia
Spain
Afghanistan

Pakistan
Estonia

United Kingdom
Urban Population Rural Population

• Population Density: Population density measures the number of people living within
a given area, which can affect housing demand, land values, and urban development
patterns. Studies have explored the relationship between population density and
housing prices, employing spatial econometric techniques to account for spatial
dependence. Higher nominal housing prices are often associated with areas of high
population density due to limited land availability and increased demand for housing.
This can lead to a positive correlation between housing prices and population density.

Population density
8000
7000
6000
5000
4000
3000
2000
1000
0
Ukraine
Colombia

Iran

Russia
Australia

Chile

Finland

Latvia

Nepal
Mexico

New Zealand

Switzerland
Croatia

South Korea
Sri Lanka
India

Luxembourg

Uzbekistan
Hungary

Portugal
Philippines

Thailand
Germany

Republic of Ireland

Norway
Afghanistan

Vietnam
Zimbabwe
Bangladesh
Brazil

Denmark
Estonia

Slovenia
Cameroon

Italy

Singapore

United Kingdom
 • Unemployment: Unemployment rates can influence housing demand and affordability
by affecting household incomes and consumer confidence. Studies have examined the
relationship between unemployment and housing prices, often incorporating labour
market indicators into econometric models. Nominal housing prices can impact
unemployment rates through their effects on consumer confidence, construction
activity, and overall economic growth. Rising housing prices may stimulate
employment in construction and related industries but could also lead to affordability
challenges for potential homebuyers, potentially affecting overall unemployment
rates.

Unemployment
35
30
25
20
15
10
5
0
Iran
Colombia

Russia
Australia

Finland

Latvia

Nepal

Switzerland
New Zealand

Ukraine
Chile

Luxembourg

Sri Lanka
Hungary
India

Mexico

Norway

Portugal

Uzbekistan
Germany

Philippines

Thailand
Croatia

Vietnam
Afghanistan

Bangladesh
Brazil

Republic of Ireland

Slovenia
Denmark

Zimbabwe
Italy

Singapore
Cameroon

Estonia

South Korea

United Kingdom
• Affordability Index: Affordability indices measure the ratio of housing costs to
household incomes, providing insights into housing affordability and market
conditions. Research has investigated the relationship between affordability indices
and housing prices, often employing regression analysis and housing affordability
models. Increasing nominal housing prices can negatively impact housing
affordability, as higher prices relative to incomes make it more difficult for
individuals to purchase homes. This can lead to a decline in the affordability index,
indicating worsening affordability conditions.

Affordability Index
6
5
4
3
2
1
0
Republic of…

Switzerland
France
Colombia

New Zealand
Luxembourg

Saudi Arabia

Turkey
Morocco
Hungary

Portugal
Austria

Canada

Czech Republic

Venezuela
Afghanistan

Brazil

Indonesia

Spain

Zimbabwe
Japan

Pakistan

Slovenia
Estonia

United Kingdom
To analyse the determinants of housing prices across countries, a multiple regression analysis
will be conducted using the EViews software. The regression model will take the following
form:

Nominal Housing Price = β0 + β1(Inflation Rate) + β2(GNI) + β3(Mortgage Interest Rate) +

β4(Urbanization) + β5(Population Density) + β6(Unemployment) + β7(Affordability Index) +
u

Where:
- Nominal Housing Price is the dependent variable, representing the nominal housing prices
of different countries.
- β0 is the constant term or the intercept.
- β0, β1, β2, β3, β4, β5, β6 and β7 are the coefficients associated with the respective independent
variables.
- u is the error term, representing the unexplained variation in housing prices.

The regression analysis will be performed using a panel data approach, which combines
cross-sectional data (data across countries). This approach allows for controlling for
unobserved heterogeneity across countries, providing more robust and reliable estimates.

Diagnostic tests, such as tests for multicollinearity and heteroscedasticity will be conducted
to ensure the validity of the regression assumptions. Appropriate remedial measures, such as
robust standard errors or the use of ordinary least squares (OLS) estimation techniques, will
be employed if necessary.

The regression results will provide estimates of the coefficients (β1, β2, β3, β4, β5, β6 and β7),
which will indicate the direction and magnitude of the impact of each independent variable
on housing prices. Statistical significance tests, such as t-tests and F-tests, will be conducted
to assess the significance of the individual coefficients and the overall model fit.

The analysis will provide insights into the relative importance of various determinants, such
as inflation, income levels, mortgage interest rates, urbanization, population density,
unemployment, and affordability, in explaining the variation in housing prices across
countries. Additionally, the results can be used to identify potential policy implications and
inform decision-making processes related to housing markets and urban planning.
 4. Regression Results

Table: 1

In our exploration of the factors influencing nominal house prices, we employ a cross-
sectional data model to analyse the relationship between variables. Within Table 1, we
provide detailed summary statistics for each variable utilized in the regression models to
facilitate a comprehensive understanding of our research findings.

INTERPRETATION OF REGRESSION MODEL 1:

The regression equation that we have used here is as stated:

housing price = β0 - β1(inflation rate) - β2 (mortgage interest rate) - β3(unemployment) - β4
(urban population) + u

Upon analysing the model, it was evident that the presence of certain regressors significantly
impacts the nominal housing prices across various countries globally. These regressors
encompass key factors such as Urban Population, Inflation Rate, Unemployment, and
Mortgage Interest Rate. Notably, our findings revealed an intriguing negative correlation
between urbanization, as indicated by the Urban Population measure. Delving deeper into this
relationship, it becomes apparent that several underlying factors contribute to this
phenomenon.
 The primary driver of the negative correlation between urbanization

One primary^driver is the prevalent issue of land scarcity within urban areas, where the
limited availability of land for new construction, especially in high-demand or densely
populated cities, exerts upward pressure on land prices. Consequently, this elevated cost of
land translates into higher expenses for housing development, ultimately burdening buyers,
and renters with increased housing prices. Another critical aspect influencing housing
affordability in urban settings is income disparities. The diverse socioeconomic landscape of
urban regions often results in varying levels of affordability, with some residents being able
to afford upscale housing options while others face challenges in accessing affordable
accommodations. As housing prices spiral upwards, lower-income individuals and families
may find themselves excluded from certain neighbourhoods or compelled to allocate a
significant portion of their income towards housing expenses, thereby exacerbating
affordability issues. The intricate interplay between these socioeconomic dynamics and the
housing market is further corroborated by established research sources, such as the seminal
works of Quigley & Raphael (2005) and Malpezzi & Mayo (1997). As highlighted in the
literature review, these studies emphasize the significance of considering supply-side factors
in understanding housing price dynamics. Furthermore, the statistical analysis within our
study provides concrete evidence supporting the negative association between urbanization
and housing prices, reflected in the coefficient value of -8.302589. It is noteworthy that the p-
value exceeding 0.01 signifies that the Urban Population variable lacks statistical significance
in explaining the variation in housing prices. This comprehensive examination underscores
the multifaceted nature of urbanization's impact on housing market dynamics, shedding light
on the complex relationship between urban development, land economics, and housing
affordability.

Similarly, the rise in Mortgage interest rates can have a significant impact on the financial
landscape for prospective homebuyers. With higher interest rates, the monthly mortgage
payments tend to increase as well. Consequently, individuals seeking to purchase homes may
find themselves constrained by reduced spending power, forcing them to either settle for
smaller mortgages or allocate a larger portion of their income towards housing expenses. This
financial burden poses a challenge for many buyers in the real estate market. This clearly
supports the document (Himmelberg et al., 2005) as mentioned in the literature review
section. Furthermore, the ripple effects of rising interest rates extend beyond just individual
homebuyers. The broader housing market may experience a shift in dynamics due to the
reduced affordability caused by higher borrowing costs. This could lead to a decrease in
demand for housing, as a segment of potential purchasers find themselves priced out of the
market. As a result, sellers may be compelled to reconsider their pricing strategies, potentially
lowering property prices to attract a smaller pool of buyers amidst the shrinking demand and
heightened competition in the market.

Furthermore, when examining the impact of Unemployment on housing prices, it is important

to note that the coefficient in this case is -1.217845, indicating a negative relationship.
Despite not showing significant effects, the economic rationale behind this negative
correlation is rather straightforward. High levels of unemployment create a sense of job
insecurity among individuals and reduce their disposable income, thereby limiting their
ability to afford housing. Consequently, this reduces the pool of potential homebuyers,
resulting in decreased demand for housing. As a result of diminished demand, sellers may be
pressured to lower prices to entice buyers, subsequently exerting downward pressure on
housing prices. Moreover, the presence of high unemployment rates can also lead to an
increase in mortgage defaults and foreclosures as individuals struggle to meet their mortgage
obligations without a stable income. This, in turn, leads to distressed properties being
introduced into the market at reduced prices, exerting a further downward influence on
overall housing prices within the region. We have also given a reference to this factor as
(Malpezzi, 1999).

Lastly in this model we have a very important variable i.e., “Inflation Rate”. High inflation
erodes the purchasing power of money over time. This means that the same amount of money
will buy fewer goods and services. If wages do not keep pace with inflation, consumers may
have less money available for housing expenses, including mortgage payments. This reduced
purchasing power can dampen demand for housing and potentially lead to lower housing
prices.

In this model, we have found that the regressors we initially considered appear to be
insignificant. This lack of significance can be attributed to the high degree of correlation
between the variables. Furthermore, the adjusted R-squared value of 0.048150, equivalent to
4.815%, indicates that only a very small proportion of the variability seen in the dependent
variable is explained by the independent variables included in the model. In essence, this
suggests that the model is not providing a robust explanation for the outcomes observed.
Therefore, it can be concluded that the independent variables utilized in regression model 1
are insufficient in accurately predicting the values of the dependent variable. This inadequacy
in prediction arises from the limited explanatory power possessed by the included variables.
As a result, the model falls short in providing a comprehensive understanding of the
relationships between the variables and the outcomes they influence. Hence, it is imperative
to explore alternative variables or factors that could enhance the predictive capability and
overall effectiveness of the model in capturing the complexities of the underlying data.

INTERPRETATION OF REGRESSION MODEL 2:

In this model, we have adjusted by excluding certain regressors from the initial Model 1
while introducing two new independent variables. One of the newly incorporated factors is
population density, which surprisingly shows a negative correlation with housing prices
evident from its coefficient of -0.018397. The statistical analysis further validates this
relationship as the t-ratio points to its significance in the model. This negative correlation
might be attributed to the strain high population density puts on infrastructure, resulting in
issues such as overcrowding, traffic congestion, and a decline in overall liability.
Consequently, individuals might feel compelled to relocate from densely populated regions in
pursuit of more economically feasible housing alternatives that offer an improved quality of
life.

Conversely, the rural population variable does not exhibit statistical significance in relation to
housing prices. Despite this lack of significance, there exists a discernible negative
association between rural population and housing price trends, albeit not prominent enough to
sway the overall model.

Even, the value of adjusted R-squared is not that significant as we can observe clearly. Thus,
moving to another regression model.

INTERPRETATION OF REGRESSION MODEL 3:

Previously in our analysis, we identified that most of the variables were insignificantly
influencing the model, leading us to eliminate them from consideration. In lieu of the
discarded variables, we introduced additional factors into the model, such as Gross National
Income, log-transformed affordability index, and an interaction term between urban
population and rural population. Despite these adjustments, our findings revealed that, apart
from the log (affordability index), the remaining independent variables displayed
insignificance with p-values below 0.1. Nevertheless, the model's adjusted R-square
improved to 20.7%, indicating a slight enhancement from the previous iteration. It is notable,
however, that the lack of significance in the variables persists, hinting at the need for further
refinement and possibly different variable selections to yield a more robust and explanatory
model.
INTERPRETATION OF REGRESSION MODEL 4:

Upon evaluating the model, we noted its significance primarily due to the notably high
adjusted R-square of 31.58%. However, during our analysis, we identified unemployment as
a variable that lacked statistical significance. Consequently, we have decided to omit this
variable from our regression analysis to refine our model's accuracy and explanatory power.
By removing this insignificant regressor, we aim to enhance the model's overall effectiveness
in capturing the relationships between the variables under consideration. This process of
refinement and adjustment is crucial in ensuring that our model provides a more precise
representation of the underlying data and can yield more reliable insights into the factors
influencing the phenomenon of interest. As we move forward with formulating a new model,
we are attentive to the importance of selecting variables that contribute meaningfully to the
predictive capabilities of our regression analysis, thereby enabling us to derive more robust
and actionable conclusions from our statistical findings.

INTERPRETATION OF REGRESSION MODEL 5:

housing price = β0 - β1(inflation rate) - β2(mortgage interest rate) + β3 log (affordability index)
+ β4 (gross national income*inflation rate) + u
After conducting thorough experimentation and analysis, our team successfully derived the
ultimate model, incorporating key independent variables such as the Inflation Rate, Mortgage
Interest Rate, Log (Affordability Index), and the interaction term of Gross National Income
and Inflation Rate. Notably, our findings revealed a negative correlation between inflation
rate and mortgage interest rate with housing prices, aligning with previous economic
discussions supported by pertinent literature in Model 1. Unlike the previous model, in this
iteration, these variables exhibited statistical significance, signified by their p-values falling
below 0.1. Additionally, the current model shed light on two variables, the log (affordability
index) and the interaction term of Gross National Income and Inflation Rate, which
demonstrated a positive relationship with housing prices. The significance of these variables,
evident from their p-values below 0.1, highlights their impact in the model. Exploring the
economic rationale, we understand that an increase in median household incomes enhances
purchasing power, rendering homes more affordable even at elevated prices. This
phenomenon explains the positive association between income growth and housing prices,
reinforcing the correlation between the Affordability Index and housing prices.
Furthermore, surpassing all previous models, the current one exhibits the most optimal data
fit, standing at an impressive 40.4%. Given these compelling outcomes, we confidently
designate this model as our final iteration.

Checking for Heteroskedasticity for our final model:

We utilized the Breusch-Pagan-Godfrey Test as it is widely recognized for examining

Heteroskedasticity. To determine whether heteroskedasticity is present, a common guideline
is to evaluate the Observed R-squared Chi-Square value. If this value is less than 0.05, it
indicates the presence of heteroskedasticity; conversely, a value greater than 0.05 suggests
homoskedasticity. In our specific assessment, our Chi-Square value was calculated to be
0.0635, exceeding the 0.05 threshold. This outcome signifies that our data closely aligns with
the regression line, with minimal variability observed. Consequently, this alignment
strengthens the argument that our model is well-suited to represent the data accurately and
effectively.

5. Conclusion

This study aimed to investigate the key determinants of housing prices across countries by
analysing a comprehensive set of variables encompassing urbanization, economic indicators,
and socio-demographic factors. Through an extensive examination of cross-sectional data and
rigorous statistical analysis, the research has provided valuable insights into the factors
influencing housing market dynamics.

The findings revealed that the final regression model, incorporating the inflation rate,
mortgage interest rate, log(affordability index), and the interaction term of gross national
income and inflation rate, exhibited the most robust explanatory power, with an adjusted R-
squared of 40.4%. The model highlighted the significant negative influence of inflation rate
and mortgage interest rate on housing prices, aligning with economic theory and previous
literature.

Notably, the log(affordability index), which captures the relationship between housing costs
and household incomes, exhibited a positive association with housing prices, underscoring
the importance of income levels in determining housing affordability. Additionally, the
interaction term between gross national income and inflation rate emerged as a significant
positive determinant, suggesting that the interplay between income growth and inflation can
influence housing price dynamics.

The analysis also demonstrated the absence of heteroskedasticity in the final model,
indicating a strong fit between the data and the regression line, further validating the model's
reliability.

While urbanization and population density initially exhibited negative correlations with
housing prices, these variables lost significance in the final model, suggesting that their
impact may be overshadowed by other factors or require further exploration with additional
variables or data sources.

This research contributes to the existing body of knowledge by elucidating the multifaceted
determinants of housing prices and their implications for policy formulation and investment
decision-making. The findings underscore the importance of considering economic
indicators, affordability measures, and their interplay in shaping housing market dynamics
across countries.

Future research could explore additional factors, such as regulatory environments, geographic
constraints, and cultural influences, to provide a more comprehensive understanding of
housing price determinants. Additionally, incorporating time-series data or panel data analysis
could yield insights into the dynamic relationships between variables over time, further
enhancing the robustness of the analysis.
Overall, this study provides a valuable foundation for stakeholders, policymakers, and
researchers to navigate the complexities of housing markets and formulate informed
strategies and policies to address housing affordability challenges and foster sustainable
urban development
 6. Bibliography

Capozza, D. R., Hendershott, P. H., Mack, C., & Mayer, C. J. (2002). Determinants of real
house price dynamics. NBER Working Paper, 9262.

Cervero, R., & Duncan, M. (2004). Neighbourhood composition and residential land prices:
Does exclusion raise or lower values? Urban Studies, 41(2), 299-315.

Cook, S. (2003). House price determinants in UK regions. London: London Economics.

Deng, Y., Gyourko, J., & Wu, J. (2012). The determinants of house prices in Chinese cities.
Journal of Real Estate Finance and Economics, 45(3), 641-664.

Fitria, R., Hudalah, D., & Firman, T. (2015). The impacts of airport development on housing
values: A case study of Jakarta, Indonesia. Jurnal Ekonomi Malaysia, 49(2), 71-81.

Gibbons, S., & Machin, S. (2008). Valuing school quality, better transport, and lower crime:
Evidence from house prices. Oxford Review of Economic Policy, 24(1), 99-119.

Glaeser, E. L., & Gyourko, J. (2003). The impact of zoning on housing affordability.
Economic Policy Review, 9(2), 21-39.

Goodman, A. C., & Thibodeau, T. G. (1995). Age-related heteroskedasticity in hedonic house

price equations. Journal of Housing Research, 6(1), 25-42.

Himmelberg, C., Mayer, C., & Sinai, T. (2005). Assessing high house prices: Bubbles,
fundamentals and misperceptions. Journal of Economic Perspectives, 19(4), 67-92.

Hsieh, C. T., & Moretti, E. (2003). Can free entry be inefficient? Fixed commissions and
social waste in the real estate industry. Journal of Political Economy, 111(5), 1076-1122.

Huang, H., & Tang, Y. (2012). Residential land use regulation and the US housing price cycle
between 2000 and 2009. Journal of Urban Economics, 71(1), 93-99.

Malpezzi, S. (1999). A simple error correction model of house prices. Journal of Housing
Economics, 8(1), 27-62.

Malpezzi, S., & Mayo, S. K. (1997). Getting housing incentives right: A case study of the
effects of regulation, taxes, and subsidies on housing supply in Malaysia. Land Economics,
73(3), 372-391.

Mustafa, A., Noor, N. M., Murad, W., & Khalid, A. R. (2018). The effects of neighbourhood
factors on housing prices in Kuala Lumpur, Malaysia. International Journal of Housing
Markets and Analysis, 11(5), 917-935.

Poterba, J. M. (2004). The determinants of the price of housing services. In Econometrica,

72(3), 745-763.

Quigley, J. M., & Raphael, S. (2005). Regulation and the high cost of housing in California.
American Economic Review, 95(2), 323-328.
Rosen, S. (1974). Hedonic prices and implicit markets: Product differentiation in pure
competition. Journal of Political Economy, 82(1), 34-55.

Saiz, A. (2010). The geographic determinants of housing supply. The Quarterly Journal of
Economics, 125(3), 1253-1296.

Sirmans, G. S., Macpherson, D. A., & Zietz, E. N. (2005). The composition of hedonic pricing
models. Journal of Real Estate Literature, 13(1), 3-43.

Sui, J. C. K., & Rahim, N. H. (2011). House price determinants in Malaysia: Affordability as
a re-look. African Journal of Business Management, 5(12), 4741-4760.