Empirical Modelling of Regional House Prices and the Ripple Effect

This paper investigates the stationarity properties and long-run relationship of Taiwan's regional house prices from 1993Q1 to 2009Q2. It applies the recent unit-root test of the panel seemingly unrelated regressions augmented Dickey-Fuller (SURADF) test developed by Breuer et al. The empirical results illustrate that Taiwan's regional house prices are a mixture of stationary and non-stationary processes, showing that the stationarity properties of these prices are dependent on the structure and properties of the various regions. Secondly, the findings of the cointegration test provide substantive evidence for a long-run relationship among all regions except Taipei City, implying a diffusion of regional house prices among each regional market except Taipei City. Finally, the results of the weak exogeneity test indicate that uni-directional causality relationships exist for three regions-Taipei County, Taoyuan-Hsinchu and Tainan-Kaohsiung-towards Taichung. The regional house price efficiently diffuses itself among these regions, caused by a much smaller public housing sector and the pre-sale system in Taiwan.