A NEW HEDONIC REGRESSION FOR REAL ESTATE PRICES APPLIED TO THE SINGAPORE RESIDENTIAL MARKET By

This paper develops a new hedonic method for constructing a real estate price index that utilizes all transaction price information that encompasses both single-sale and repeat-sale properties. The new method is less prone to specification errors than standard hedonic methods and uses all available data. Like the Case-Shiller repeat-sales method, the new method has the advantage of being computationally effi cient. In an empirical analysis of the methodology, we fit the model to all transaction prices for private residential property holdings in Singapore between Q1 1995 and Q2 2014, covering several periods of major price fluctuation and changes in government macroprudential policy. Two new indices are created, one from all transaction prices and one from single-sales prices. The indices are compared with the S&P/Case-Shiller index. The result shows that the new indices slightly outperform the S&P/Case-Shiller index in predicting the price of single-sales homes out-of-sample. However, they underperform the S&P/CaseShiller index in predicting the price of repeat-sales homes out-of-sample. The ∗Jiang Liang, School of Economics, Singapore Management University, 90 Stamford Road, Singapore. Peter C. B. Phillips, Yale University, 30 Hillhouse Avenue, New Haven, CT, 06520, USA; Email: [email protected]; Phillips acknowledges research support from the NSF under Grant No. SES 12-58258. Jun Yu, School of Economics and Lee Kong Chian School of Business, Singapore Management University, 90 Stamford Road, Singapore. Email: [email protected]. URL: http://www.mysmu.edu/faculty/yujun/. Yu thanks the Singapore Ministry of Education for Academic Research Fund under grant number MOE2011-T2-2-096.