Time Series Modeling Based on Different Frequencies

摘要：

This paper separates the frequency of time series, and models it The time series is filtered with discrete cosine transform, and the discrete cosine transform coefficients of the low frequency are used to reconstruct the long period trend of the time series. To the rest high frequency component, the models structure is determined by time delay autocorrelation analyzing. The simulation test of daily closing prices of stocks for several years discovers that the model can simulate the changing tendency of the time series to some extent, proving the effectiveness of the proposed modeling method of time series.

关键词： time series frequency component auto-regression and moving average discrete cosine transform forecast

作者: Tian Tian Li Xingye

作者单位: School of Business, University of Shanghai for Science and Technology, Shanghai 200093, China

会议类型: 国际会议

会议名称: 2011 International Conference on Information and Industrial Electronics(2011年信息与工业电子国际会议 ICIIE 2011)

会议地点: 成都

会议语种:英文

页码: 365-368

在线出版日期: 2011-01-14（万方平台首次上网日期，不代表论文的发表时间）