基于小波分析经济增长与房市的相关性研究

发布时间：2018-06-01 13:39

本文选题：小波分析 + 奇异点　；参考：《西南财经大学》2014年硕士论文

【摘要】：近二十年来,我国宏观经济高速发展,与此同时国内房地产市场也快速的发展。近几年来我国房价持续上涨,超高的房价严重影响了居民的生活质量。政府对于房市的调控政策陷入两难。一方面,严格的控制房地产价格将会以牺牲经济增长速度为代价,不利于我国国民经济的建设；另一方面,过高的房价严重影响了我国居民的生活质量。本文通过对房地产市场和经济增长的相关性研究,力求在调控房价和经济增长之间找到一个平衡点,为政府进行房地产市场调控提供有力的参考。傅里叶分析和统计相结合是研究经济数据的重要方法之一,但因为傅里叶分析不具备“空间局部性”,因此也束缚了它在分析经济数据中的应用。在傅里叶变换的基础上,小波变换被提出。基于小波变换良好的“自适应性”和“变焦性”等特性,小波变换非常适合于对房市和经济增长这样的“非平稳数据”进行分析。本文以2000年至2013年商品房销售额和房地产投资额的月增长率以及GDP的月增长率为分析数据。 (1)首先我们对上各个数据进行预处理,然后利用MATLAB软件的小波工具箱,对其进行小波分解。房市和经济增长波动的原因是由噪声(即突变因素)造成的,因此对每层的高频分解图进行观察分析,可得出它们的奇异点。并结合现实找出奇异点发生的原因。 (2)利用小波变换其分形的特性,可以将房市和经济增长中的噪声信号进行剔除,从而使得它们的发展趋势显现出来。通过对各层低频信号进行重构。对各自进行周期性的分析。 (3)方差和相关系数是相关性研究的两个主要指标。本文结合最大重复离散小波变换,分别计房市和经济增长的小波方差,及两者之间的小波相关系数。并对这两个指标进行分析,从而得出它们之间长期和短期的相关系数。
[Abstract]:In the past twenty years, the macro-economy of our country has developed rapidly, at the same time, the domestic real estate market has also developed rapidly. In recent years, housing prices in China continue to rise, the super-high housing prices seriously affect the quality of life of residents. The government's regulation of the housing market is in a dilemma. On the one hand, strict control of real estate prices will be at the expense of economic growth rate, which is not conducive to the construction of our national economy; on the other hand, excessive housing prices seriously affect the quality of life of Chinese residents. Through the research on the correlation between real estate market and economic growth, this paper tries to find a balance between housing price control and economic growth, and provides a powerful reference for the government to regulate the real estate market. The combination of Fourier analysis and statistics is one of the important methods to study economic data, but because Fourier analysis does not have "spatial locality", it also restricts its application in the analysis of economic data. Wavelet transform is proposed on the basis of Fourier transform. Based on the good "adaptive" and "zoom" characteristics of wavelet transform, wavelet transform is very suitable for the analysis of "non-stationary data" such as housing market and economic growth. This paper analyzes the monthly growth rate of commercial housing sales and real estate investment from 2000 to 2013 and the monthly growth rate of GDP. Firstly, we preprocess the above data, then use the wavelet toolbox of MATLAB software to decompose them. The reason of the fluctuation of housing market and economic growth is caused by noise (that is, sudden change factor), so the singularity of each layer can be obtained by observing and analyzing the high-frequency decomposition diagram of each layer. Combined with reality, the reason of singularity point is found out. 2) by using the fractal characteristic of wavelet transform, the noise signals in housing market and economic growth can be eliminated, and their development trend can be revealed. The low frequency signals of each layer are reconstructed. To carry on the periodic analysis to each. Variance and correlation coefficient are two main indexes of correlation study. In this paper, the wavelet variance of housing market and economic growth and the wavelet correlation coefficient between them are calculated by using the maximum repeated discrete wavelet transform. The long-term and short-term correlation coefficients between them are obtained by analyzing the two indexes.
【学位授予单位】：西南财经大学
【学位级别】：硕士
【学位授予年份】：2014
【分类号】：F224;F124;F299.23

【参考文献】