The Study Of Long Memory Of Chinese Stock Earnings Yield

Even the traditional time series theory has become mature, it base on the short memory characteristic. But lots of time series have performed long memory characteristic in our life. In the recent 20 years, long memory of economic, financial time series array become economics, finance study research focus of field. Have taken the lead in finding the memory for a long time (long memory) in the series of hydrology time from Hurst from the tide data. From this point of view, this paper has researched and analyzed the long memory time series in detail.At first, this paper has introduced the research status in quo and its application background, it also introduced the conventional linear time series model, and from the disadvantage point that traditional time series models can not simulate the long memory time series well, so long memory time series theory is proposed. Secondly, this paper has defined long memory concepts from time filed angle and frequency filed. It depicts R/S analytic method. Then the paper presents the fractional differenced noise model and the autoregressive fractional integrated moving average model. It compared traditional time series models with ARFIMA model.Lastly, the paper has used earnings yield which comes from integrated share index of Shanghai and Shenzhen to make analysis demonstrations. They use R/S analytic method to check up earnings yields, and find that both of earnings yields have long memory characteristic. It also performs short memory characteristic along with changes of sample's initial time and interzone of time series. The average circular period of Shanghai's stock market is 250 days, and Shenzhen's is 400 days.