1# RECORD 009443a37464c7bfc0c1892b4c485e939d19af7c2# TITLE: Testing Housing Price Drivers in Santiago de Chile: A Hedonic Price Approach3# YEAR: 2023.0 VENUE: Critical Housing Analysis DOI: 10.13060/23362839.2023.10.2.5584# AUTHORS: Francisco Vergara-Perucich5# PAGES: 14 CANDIDATE TABLE PAGES (1-based): [7]6# ABSTRACT: Hedonic modelling is an empirical analysis technique that is widely used to review the housing market and unpack the main determinants of price. A correct determination of housing price drivers allows a weighted prediction of the value of each dwelling for sale or rent. This paper reviews the fundamental determinants of housing prices that have been published in the literature to see which ones have a better predictive fit for the case of the housing market in the city of Santiago, Chile. From a record of 456,000 property transactions, a dataset composed of 11 explanatory variables is elaborated. Through a semi-logarithmic regression, 4 variables that contribute to explaining the formation of housing prices in Santiago, Chile, are identified. The results indicate that the socioeconomic characterisation of urban areas where housing is traded, the price of copper on the London Metal Exchange, the mortgage interest rate, the age of residential buildings are the main drivers for the main drivers of prices in Santiago. Given the crisis of access to housing in Chile, the article provides relevant information for decision-makers in housing policy.789===== PAGE 1 (score 4, numeric-paren 0, table-words 0, var-words 4) =====1011Volume 10 | Issue 2 | 2023 | 44-57 12Available online at www.housing-critical.com 13https://doi.org/10.13060/23362839.2023.10.2.558 14 1544 16 17Testing Housing Price Drivers in Santiago de Chile: A 18Hedonic Price Approach 19 20José Francisco Vergara-Perucich 21 22Universidad de Las Américas, Chile 23jvergara@udla.cl 24https://orcid.org/0000-0002-1930-4691 25 26 27Abstract: Hedonic modelling is an empirical analysis technique that is widely used to review the housing market 28and unpack the main determinants of price. A correct determination of housing price drivers allows a weighted 29prediction of the value of each dwelling for sale or rent. This paper reviews the fundamental determinants of 30housing prices that have been published in the literature to see which ones have a better predictive fit for the case 31of the housing market in the city of Santiago, Chile. From a record of 456,000 property transactions, a dataset 32composed of 11 explanatory variables is elaborated. Through a semi-logarithmic regression, 4 variables that 33contribute to explaining the formation of housing prices in Santiago, Chile, are identified. The results indicate that 34the socioeconomic characterisation of urban areas where housing is traded, the price of copper on the London 35Metal Exchange, the mortgage interest rate, the age of residential buildings are the main drivers for the main 36drivers of prices in Santiago. Given the crisis of access to housing in Chile, the article provides relevant 37information for decision-makers in housing policy. 38 39Keywords: hedonic economics; housing in developing countries; urban policy and planning; land markets and 40housing policy. 41 42 434445===== PAGE 7 (score 18, numeric-paren 0, table-words 5, var-words 2) =====4647Volume 10 | Issue 2 | 2023 | 44-57 48Available online at www.housing-critical.com 49https://doi.org/10.13060/23362839.2023.10.2.558 50 5150 52 53of various variables on housing prices in Greater Santiago, rather than focusing solely on the 54predictive capabilities of the hedonic price model. 55 56 57Results 58 59During the period under investigation, a total of 456,133 official transactions were analysed. 60Among these transactions, 44.5% were related to house transactions, 47% were apartment 61transactions, and 1.5% were land transactions. It is important to note that a significant number 62of the houses transacted were likely demolished to make way for future development. 63 64Table 3 provides a comprehensive summary of descriptive statistics for each variable. The 65average price per square metre of housing during the study period was found to be USD 1,882, 66while the price of land was USD 369. Additionally, Table 2 illustrates that the average size of 67a housing unit was 115.92 m2. This figure may seem high, but it is important to consider that 68the value is influenced by the initial phase of the analysis, during which the production of houses 69closely matched the sale of apartments. 70 71Overall, the data highlight the diverse nature of the transactions and shed light on the prices and 72sizes associated with different types of properties. 73 74Table 3: Descriptive statistics of the variables studied 75 76Variables 77Mean 78Median 79Std. dev. 80Skewness 81Kurtosis 82Ln housing prices 833.887 843.895 850.240 860.143 87-0.559 88IDSE 890.762 900.758 910.015 920.863 93-0.170 94m2 95115.920 96112.740 9721.271 982.186 998.970 100Sales 1013366.100 1023873.000 1031582.300 104-0.444 105-1.148 106Age of residential building 10750.710 10849.540 1099.270 1100.519 111-0.081 112Construction cost index 1134779.800 1144889.900 115632.100 116-0.243 117-1.313 118Wage index 1195.779 1205.846 1211.152 122-0.406 1231.076 124Population 1255361100 1265322700 127179700 1280.756 129-0.288 130Mortgage interest rate 1314.071 1324.140 1330.545 1340.720 1351.069 136Ln land price 1372.270 1382.243 1390.174 1400.457 1410.415 142Ln copper price on the 143London Metal Exchange 1441.077 1451.128 1460.233 147-0.807 1480.717 149Ln money supply 1508.338 1518.393 1520.325 153-0.360 154-1.192 155Blue-chip index (IPSA) 1564135.100 1574055.500 158745.030 159-0.092 1600.128 161Source: Author based on sources indicated in Table 1 and Table 2. 162 163Most of the values of skewness and kurtosis fall within the range of 2 and -2 (George and 164Mallery 2010). Among the values analysed, only the average square metre of a property (m2) 165exhibits high kurtosis, while most other variables demonstrate normality. Figure 1 displays the 166plots of the transformed data. The variables population, construction costs, and money supply 167exhibit a distinct deterministic trend, which was excluded from the regression model using the 168stepwise technique owing to the potential presence of a spurious relationship with the dependent 169variable. 170 171Figure 1: Variable plots 172173174===== PAGE 8 (score 2, numeric-paren 0, table-words 1, var-words 0) =====175176Volume 10 | Issue 2 | 2023 | 44-57 177Available online at www.housing-critical.com 178https://doi.org/10.13060/23362839.2023.10.2.558 179 18051 181 182 183 184 185 186Source: Author’s calculations. 187 188Table 4 presents the estimations obtained through multiple linear regression. The model 189successfully explains 60.74% of the variance in the natural logarithm of the housing price, 190providing a statistically reliable fit for predictive scenarios. Importantly, there is no evidence 191of collinearity among the relevant variables. Additionally, the White test for heteroskedasticity 192