Factors Affecting House Prices in London
Real estate is a key economic player in United Kingdom because the housing industry contributes a significant percentage of taxes to the government (Hofman and Aalbers, 2019, pp. 89-100). Therefore, it is important to determine trends and factors affecting this industry. Data analytics comes in handy because it helps in providing insights that in turn helps decision makers make well-informed and productive decisions. This paper will investigate factors that affect house prices in London and come up with an appropriate statistical model to help in predicting housing prices.
I will include six variables in my model and they include Tax & Rates, House Content Insurance, Energy, Land/Geographical location, Housing and Household services and then CPI-Consumer Price Index (Cloyne et al, 2019, pp. 2104-2136). In real estate, it is difficult to avoid property tax rates because it plays a significant role in house price volatility. There is a negative impact of property tax rates on housing price volatility whereby house price volatility reduces when there is an increase in property tax rates (Oliviero et al., 2019, pp. 776-792). We then have a house content insurance factor which again plays an important role in determining house prices. This depends on the value of the house as well as the insurer that the house owner has. Different houses are located at different places with different architectural designs and taste which will attract different amount of insurance which will the price of that house.
Another significant factor is energy which entails electricity, gas, fuel, water. A house will be priced depending on its energy consumption and more importantly, depending on the government rates of energy (McCord et al., 2020). In addition, we have land that is an important factor in determining house prices. Some pieces of land are expensive depending on their location and this increases capital requirements and to cater for this increment, houses end up being priced highly (Gautier and Vuuren, 2019, p. 101646). Land policies or land use regulations also play a vital role in affecting house prices through housing supply and demand (Gautier and Vuuren, 2019, p. 101646). Another important factor of interest is housing and household services. These are services performed by home owners in order to maintain the house in a good condition as well as other ordinary house services. For instance, security, waste collection, renovations and mail deliveries.
The last factor is CPI which means consumer price index. It is a measure of price changes over time that consumers pay for a given basket of goods and services (Christou et al., 2018, pp. 15-26). Therefore, this index indicates inflation, employment or unemployment. For instance, an increase in CPI means there is inflation which further indicates that first, prices of housing property and services will increase which consequently will lead to an increase in house prices (Christou et al., 2018, pp. 15-26). Also, a high CPI indicates the state of the economy-poor and this will affect demand and supply in real estate industry and hence housing prices need to be adjusted to accommodate the new changes (Christou et al., 2018, pp. 15-26).
Methodology
The above six independent variables affect housing prices in one way or the other and thus the need for a statistical modelling in order to determine which factors significantly affect housing prices. The statistical model will also help in establishing whether the theory and literature on the predictor variables is true about their impact on housing prices.
The study used data from National Statistics Office website from the 2000-2020. The data was collected for each of the six independent variables and then put together in a one Excel file for analysis. Analysis ToolPark in Excel was used.
Regression analysis entails determining the effect of factor variable(s) on response variable(s) (Sarstedt and Mooi, 2019, pp. 209-256). In this case study, our response variable is London House Prices and the predictor variables are Tax & Rates, House Content Insurance, Energy, Land/Geographical location, Housing and Household services and then CPI. The study used iteration method to determine the best model.
Using iteration technique, the study incorporated four predictor variables into the model namely Tax & Rates, Energy, Land/Geographical location and CPI. This is because the combination of these predictor variables had the largest R Squared value and the result is shown below.
Figure 1: Regression analysis Results
From figure 1, R-Squared value was 92.06% which is greater than 0.5 and it is approaching 1 which has an implication that our four predictor variables are good at predicting or explaining house prices in London because the IVs explains 92.06% variability of the response variable (Sarstedt and Mooi, 2019, pp. 209-256). The F statistic value is greater than 1 while F Significance<0.001 implying that our general model is significant and generally good in fitting the data (Sarstedt and Mooi, 2019, pp. 209-256).
Let define the coefficients and p-values. The constant term for the regression model is -2406136.365, Tax & Rate, Energy, Land and CPI have coefficients of 467.16, 2427.45, 1333.86 and -45282.97 respectively. For p-values, Tax & Rate, Energy, Land and CPI have 0.53, 0.02, 0.04 and 0.11 respectively. A positive coefficient implies that there is a positive relationship between a particular IV and housing price whereby an increase in one variable leads to an increase in another variable (Sarstedt and Mooi, 2019, pp. 209-256). On the other hand, a negative coefficient implies that an increase in a particular IV leads to a decrease in the response variable (Sarstedt and Mooi, 2019, pp. 209-256). In our case study, Tax & Rates, Energy and Land have a positive relationship with London housing prices while CPI has a negative relationship. For the p-values, a p-value<0.05 implies that a particular IV is significant at explaining or predicting the response variable (Sarstedt and Mooi, 2019, pp. 209-256). Therefore, in this case study, Energy and Land are significant in explaining housing prices while Tax & Rates and CPI are not significant. The following is our multivariate regression model.
Y= -2406136.365+467.16×1+2427.45×2+1333.86×3-45282.97×4
Where;
Y= London House Prices
X1=Tax & Rates
X2= Energy
X3=Land (Geographical location)
X4= CPI
From our results section, Tax & Rates had a positive coefficient with housing prices and this means that an increases in taxes and rates on house property will definitely lead to increased house prices in order to compensate for the high taxes and this agrees with the past literature reviews. Energy also had a positive coefficient with housing prices meaning that when energy prices is high or consumption is high, house prices will be set high. This is expected because compensation have to be made by increasing house prices when consumption and rates are high and this again agrees with the past literature reviews. Another obvious expectation was a positive relationship between land and housing prices. London is the capital city of UK and it is a center for businesses and as such, it is expected that it lands rates will be high. Being in urban location, and having high land rates with constant land regulations, then housing prices are expected to be high and hence a positive relationship between the two. Consumer Price Index had a negative relationship with housing prices and to some extend it is expected. When CPI is high, it means there is inflation and prices for goods and services is high and hence the demand for goods reduces. In order to attract customers, house owners have to reduce house prices and hence bringing about the negative relationship.
The p-values results for these independent variables shows that only Energy and Land are significant at determining house prices. Again this agrees with findings from literature reviews. Contrary to the expectations, the regression results showed that Tax & Rates as well as CPI are not significant in determining house prices. Though house owners and real estate decision makers consider Tax & Rates and CPI as vital factors in explaining housing prices, the regression results disagree because these variables have less impact on housing prices. As a result, the decision makers need to focus on other predictor variables for instance employment rate, population.
Forecasting involves predicting future values and we can use past values, models and visualizations. In this case study the study used visualization and this entails plotting a graph and then determining patterns or trend from the graph. The regression model was also used determine the trend in house prices.
Figure 2: Line Graph
From the graph, there will be an increase in house prices due to increase in Tax & Rates and Land. Considering that land was significant in predicting house prices, then we expect house prices to increase in future due to an increasing trend in the land rates.
Using the regression model, let set Tax & Rates and CPI at zero (They are insignificant) while Energy and Land at 1, then our prediction will be;
Y= -2406136.365+467.16*0+2427.45*1+1333.86*1-45282.97*0
= -2402374
Conclusion
There is no doubt that data analytics is significant in helping decision makers to make well-informed and productive decisions. This study used multivariate regression analysis to determine a statistical model that best describes the housing prices problem in London. The results indicated that the independent variables Tax & Rates and CPI were not significant in explaining house prices while Energy and Land were significant. Therefore, the study recommends that decision makers should shift their focus from Tax & Rates and CPI and determine other variables that significantly explains housing prices in London.
References
Cloyne, J., Huber, K., Ilzetzki, E. and Kleven, H., 2019. The effect of house prices on household borrowing: a new approach. American Economic Review, 109(6), pp.2104-36. https://www.aeaweb.org/articles?id=10.1257/aer.20180086.
Christou, C., Gupta, R., Nyakabawo, W. and Wohar, M.E., 2018. Do house prices hedge inflation in the US? A quantile cointegration approach. International Review of Economics & Finance, 54, pp.15-26. https://doi.org/10.1016/j.iref.2017.12.012.
Gautier, P.A. and Van Vuuren, A., 2019. The effect of land lease on house prices. Journal of Housing Economics, 46, p.101646. https://doi.org/10.1016/j.jhe.2019.101646.
Hofman, A. and Aalbers, M.B., 2019. A finance-and real estate-driven regime in the United Kingdom. Geoforum, 100, pp.89-100. https://doi.org/10.1016/j.geoforum.2019.02.014.
McCord, M., Haran, M., Davis, P. and McCord, J., 2020. Energy performance certificates and house prices: A quantile regression approach. Journal of European Real Estate Research. https://www.emerald.com/insight/content/doi/10.1108/JERER-06-2020-0033/full/html.
Oliviero, T., Sacchi, A., Scognamiglio, A. and Zazzaro, A., 2019. House prices and immovable property tax: Evidence from OECD countries. Metroeconomica, 70(4), pp.776-792. https://onlinelibrary.wiley.com/doi/full/10.1111/meca.12253.
Sarstedt, M. and Mooi, E., 2019. Regression analysis. In A Concise Guide to Market Research (pp. 209-256). Springer, Berlin, Heidelberg. https://link.springer.com/chapter/10.1007/978-3-662-56707-4_7.
Order an Essay Now & Get These Features For Free:
Turnitin Report
Formatting
Title Page
Citation
Outline
