Abstract—This work constitutes, in part, our recent efforts in
exploring more realistic and appropriate approaches for
valuing mortgage backed securities as well as facilitating the
financial management of market participants in China’s
housing market. Unlike structural analysis where usually only
interest rate effect is considered in valuing properties and
relevant securities, this paper focuses on the housing price
dynamics in relation to the house price changes in time and
several key contributing factors in China’s real estate market.
The data used for the study are the monthly housing price
indices from July 2005 to December 2010, collected and
maintained by the National Bureau of Statistic of China.
Several autoregressive models are proposed, analyzed, and
compared to best identify these relations. The study shows that
house price changes in current month are influenced by the
house prices in previous months, with the optimal number of
price lags inferable using regression procedures. Land price
and consumer price index are also contributing factors for
housing price changes.An autoregressive model in the form of
fractional polynomial of contributing factors is shown to have
best forecasting power. Numerical experiments and simulation
are carried out to test the effectiveness and robustness of our
model. In particular, the accuracy and convergence of the
parameter estimation are tested with different sampling
processes.
Index Terms—Housing price, mortgage security,
autoregressive model, parameter estimation.
Jieqiong Wang is with School of Mathematics, the University of
Edinburgh, Scotland, SC005336 UK. (e-mail: J.Wang-45@sms.ed.ac.uk).
DejunXie is with Department of Mathematical Sciences, Xi‟an Jiaotong
Liverpool University, Suzhou, China. (e-mail: Dejun.Xie@xjtlu.edu.cn).
[PDF]
Cite:Jieqiong Wang and DejunXie, "Empirical Analysis of Housing Prices in Chinese Market," International Journal of Trade, Economics and Finance vol.3, no.5, pp. 388-392, 2012.