Factors Affecting Housing Prices In Sidney: A Quantitative Study

Housing Price Trend in Sidney

Housing prices in the real estate industry have been seen to fluctuate in the recent decade globally (Dongsheng & Zhong, 2010). This has been confirmed by the house price trend in many cities of the world. Australia’s housing prices have not been any different. To be specific, the city of Sidney has witnessed increased house prices. This has been caused by proximity to the city, forces of demand and supply among others (Hua, 2008) and (Shisong & Hongmei, 2009). Less research has been conducted on the factors affecting housing prices in Sidney therefore it is difficult to attribute this price increase to any factor. However, some of the evident factors affecting house prices in Sidney include the size of land the house is lying on, housing price index and annual percentage change

This research study is focused in creating a model that will be used to predict the house prices in Sidney using the above named variables. For example, the age of the house would be a major component of the model since new houses are likely to fetch high prices due to high demand while old houses are likely to fetch lower prices due to low demand (Nellis, 2011). Another major component of the model will be the size of land on which the house is built (Abelson & Chung, 2005). It is normal that a house sitting on a large area will go at a higher price while a house sitting on a smaller size of land will fetch a lower price in a given area (Quigley , 2009).

The last decade has witnessed a soar in the house prices in Sidney. According to a research done by (Haurin & Gill, 2012), in 2003, the median house price in Sidney was about 473 dollars. About 11 years later in mid-2014, the median price had shot to 811,000 dollars. This is an increase of 70%. According Real Estate Institute of Australia (REIA), the data indicated stability between the year 1990 and 1999.

However, an increase was witnessed in the year 2000. The scenario was even worse during the global financial crisis of 2007/2008 as there was a steady increase. In 2014, a research conducted by demographics 10^th annual survey compared the ratio of family income to median house prices in Australia. The research found that Australia had a very high mean house income price in comparison to developed economies of the world such as japan, UK and US (Karantonis & Ge, 2007).

Data collection

The data used in this study was shared by the Australian Bureau of Statistics. This was under residential property prices. The information gathered included the house values in thousand dollars, the number of years that the houses had stayed the size of land, price index of the city and yearly percentage change in real estate values. The sampling method used by the study to select the years from the year 2002 to 2017 was judgmental sampling where a convenient sample was used. The recent last 15 years were picked for the study. The variables involved in this research study were all numerical variables thereby prompting the use of quantitative analysis. There were both dependent and independent variables. The dependent variable was the house market price while the independent variables were age of the houses, size of land in square meters, price index and annual percentage change.

Data Collection and Analysis Techniques

Data analysis

The research employed quantitative statistics in the analysis of the data. Both inferential and descriptive statistics were conducted. Descriptive statistics involved establishing measures of center as well as measures of dispersion. Measures of central tendency such as mean, mode and median were established. Measures of dispersion such as standard deviation and variance were also calculated. Inferential statistics such as correlation and regression analysis were conducted to establish how dependent variable related with the independent variables. The results were mainly presented in form of tables and graphs for clear interpretation. For the sake of the main objective of this study, simple linear regression and multiple linear regression was established to identify the best model that could be used to predict the house prices in the city of Sidney with a lot of precision.

Limitations

The major limitation in this research study was the fact that there was no enough time for data collection all the way to compiling of the report. This made the study to be rushed which could impact negatively on the results. There was also a problem of multicollinearity when it came to data analysis.

1. Summary – Market price of houses in Sidney

Table 1. Source: Research project

The summary statistics is of market price of houses in Sidney. The analysis results show that the average house price in thousand dollars was 777 dollars. The minimum house price in thousand dollars was 630 dollars while the maximum house price in thousand dollars was 960 dollars. The median price in thousand dollars was 780 dollars.

House market price trend in Sidney from 2002 to 2017

The time series graph above indicates how the house price has been moving since the year 2002 to the year 2017. There is a gentle slope meaning that the price has been increasing gradually from one year to another.

1. Test for correlation

Market price of houses VS age of houses in years

Table 2. Source: Research project

From the correlation analysis above, it can be observed that there is a strong relationship between market house prices and the age of the houses. However, the relationship is in the negative direction. Statistically, the correlation was found to be significant since the p-value is less than 0.05. 

1. Scatterplots

Market price versus price index scatterplot 

A scatterplot of market price versus Sidney price index depicts a linear relationship as can be seen it figure 1 above. The gradient of the relationship is 2.1 indicating that a unit change in Sidney price index causes 2.1 units change in the response variable (house market price). To add on, it can be observed that the value of R² is 0.64. This means that 64% of the change that occurs in the response variable (market price) is explained by the Sidney price index.

Market price versus annual % change scatterplot

A scatterplot of market price versus annual percentage change depicts a linear relationship as can be seen it figure 2 above. The gradient of the relationship is 6.03 indicating that a unit change in annual percentage change causes 6.03 units change in the response variable (house market price). To add on, it can be observed that the value of R² is 0.16. This means that 16% of the change that occurs in the response variable (market price) is explained by the annual percentage change.

1. Market price versus area in meters scatterplot

Limitations of the Study

A scatterplot of market price versus area in square meters depicts a linear relationship as can be seen it figure 3 above. The gradient of the relationship is 0.56 indicating that a unit change in area in square meters causes 0.56 units change in the response variable (house market price). To add on, it can be observed that the value of R² is 0.09. This means that 9% of the change that occurs in the response variable (market price) is explained by the area in square meters.

Market Price and age of house scatterplot

A scatterplot of market price versus age of house in years depicts a linear relationship as can be seen it figure 4 above. The gradient of the relationship is -4.13 indicating that a unit change in age of house in years causes -4.13 units change in the response variable (house market price). To add on, it can be observed that the value of R² is 0.45. This means that 45% of the change that occurs in the response variable (market price) is explained by the age of house in years.

The full regression model

Table 1. Source: Research project 

1. Least square regression equation

From the regression results above, the below regression model is formed.Above are results of multiple linear regression. The dependent variable is market price while the independent variables age of the houses, size of land in square meters, price index and annual percentage change.  A unitary change in the variable Sidney price index results into 1.96 change in market price. A unitary change in the variable size of land in square meters results into 0.52 change in market price. To add on, a unitary change in the annual percentage change results into 1.52 change in market price. A unitary change in the variable age of the houses in years results into 2.49 change in market price. The value of the constant is 548.98.

This means that the value of house market price in Sidney is 548.98 in thousand dollars when all variables are held constant. To add on, it can be observed that the value of R² is 0.79. This means that 79% of the change that occurs in the response variable (market price) is explained by the four independent variables.

Interpretation of 95% confidence interval for each parameter

Table 2. Source: Research project

The research also sought to establish the limits within which the coefficients lie. A precision of 95% confidence interval was used. The second and the third column of table 2 above show where the coefficients will lie 95 times out of 100.

Linear regression model for relationship between the market price and land size in square meters

Table 3. Source: Research project

The regression equation for the above is as The value of R² is 0.1. This means that 10% of the change that occurs in the response variable (market price) is explained by the area of land in square meters. 

Comparison of the two models

In order to select the best model, we rely on the value of R². The higher the value of r-squared, the better the model. So if we compare the value of R² which are 0.1 and 0.79, we choose the model with the r-squared of 0.79 because it is able to explain much of the variation that occurs in response variable. The models compared are as below.

With R² value of 0.1

And; 

With R² value of 0.79 

Conclusion

The main objective of this research was to identify the major determinants of prices of houses in the city of Sidney in Australia. The size of land in square meters, house price index, annual price change and age of the house were identified as the major determinants of the house prices in the city. Various scatterplots have been drawn to establish the relationship that exists between the dependent variable (house market price) and independent variables. The independent variable that was found to have the strongest influence on the house market price was the annual percentage change while the variable with the least influence was the size of land in meters. The research study also found that there was a negative relationship between age of house in years and the house market price. The model that the research study arrived at had r-squared value of 0.79.

References

Abelson, P., & Chung, D. (2005). “The Real story of housing prices in Australia from 1970 to 2003”. The Australian Economic Review, 38(3), 265-280.

Dongsheng, C., & Zhong, M. (2010). The bad effects of high housing price on urbanization of China. Yangtze Forum, 3, 3-7.

Haurin, D. R., & Gill, H. L. (2012). “Effect of income variability on the demand for owner-occupied housing”. Journal of Urban Economics, 22, 136-150.

Hua, Z. (2008). An analysis of supply and demand curve of real estate market and its policy implication.. (Vol. 3). Jianghuai Tribune.

Karantonis, A., & Ge, X. J. (2007). “An empirical study of the determinants of Sydney’s dwelling price”. Pacific Rim Property Research Journal, 13(4), 493-509.

Nellis, J. G. (2011). An empirical analysis of determination of house prices in the United Kingdom. Urban Studies. (1 ed., Vol. 19).

Quigley , M. J. (2009). Real estate prices and economic cycles. International Estate Review, 2, 5-8.

Shisong, H., & Hongmei, C. (2009). The mystery of housing price. Beijing: Social Sciences Academic Press.

Order an Essay Now & Get These Features For Free:

Turnitin Report

Formatting

Title Page

Citation

Outline

Place an Order