基于主成分分析与谱分析的福建省房地产周期实证研究

An empirical study of Fujian real estate cycle based on principle component and spectral analyses

研究房地产周期的首要步骤是识别及证实其实际存在性。选取福建省房地产1991-2011年的相关统计数据来研究其周期,周期的合成指数采用主成分分析法确定。同时,对周期的合成指数经HP滤波数据预处理,利用谱密度函数来分析合成指数的各主要频率分量,并根据谱峰值来识别周期。研究结果显示:福建省房地产市场自1991年以来存在为期3.33年的主周期和10年的次周期。

On the research of real estate cycle, the foremost step is to identify and demonstrate its real existence. This article selects yearly statistical data of 1991 -2011 to study the real estate cycle in Fujian. Firstly, the principal component analysis is used to determine the synthetic index of the cycle. Secondly, data of the synthetic index, pretreated by HP filter, is used in spectral density function to analyze the synthetic index of the main frequency component, and to identify cycle according to the spectrum peak. The result shows that the real estate market in Fujian has a primary cycle of 3.33 years and a secondly cycle of around 10 years since 1991.