AN EXAMINATION OF THE TIME SERIES NATURE AND THE FORECASTING OF SINGAPORE �S PRIVATE RESIDENTIAL PROPERTY PRICES

Abstract

This study examines the time series data of the private residential market prices in Singapore from 1988 to 2010, through adopting the multivariate regression model, and incorporating the first and fifth order autoregressive terms. Apriori analysis of the market demand and supply helps to contribute the key factors that affect private residential market price changes. The resulting multivariate regression model also incorporates dummy variables, which are the demand-led and supply-led government policies that seem to have a significant impact on private residential market prices. To incorporate the autoregressive terms in the multivariate regression model, the time series data needs to be tested for stationarity using the Augmented Dickey Fuller test. In addition, the Granger Causality test also helps to determine whether or not the addition of the lagged exogenous variables would contribute to the predictive power of the resulting model. The determination of the appropriate number of lags is carried out through the use of Schwarz Information Criterion and Akaike Information Criterion. Subsequently, the corresponding real estate market analysis of the Singapore private residential market is conducted to better understand the potential fluctuations of selected exogenous variables, so that the forecast results could be fed into the resulting multivariate regression model to predict quarterly movements in the short term of the private residential price index from 2011 to 2012. Results from the multivariate regression model indicate that interest rates, strong demand policies, the three-quarter lag change in the occupied stock and the Straits Times Index, are the most significant factors in explaining the private residential market price changes. Subsequently, The resulting multivariate regression model is then used to generate three different forecasting scenarios, namely, the most probable scenario, the boom and bust scenarios, to show the short-term future trends of the private residential property price index in Singapore.