Long-memory behavior analysis of China stock market based on Hurst exponent

2017 ◽  
Author(s):  
XiaoYue Wang ◽  
Ting Lei ◽  
Zhuo Liu ◽  
ZhaoBin Wang
Keyword(s):  
Stock Market ◽  
Behavior Analysis ◽  
Long Memory ◽  
Hurst Exponent ◽  
China Stock Market

scholarly journals Searching for long memory effects in time series of central Europe stock market indices

2008 ◽  
Vol 56 (3) ◽  
pp. 187-200
Author(s):  
Luboš Střelec
Keyword(s):  
Time Series ◽  
Stock Market ◽  
Central Europe ◽  
Long Memory ◽  
Hurst Exponent ◽  
Financial Time Series ◽  
Memory Effects ◽  
Stock Index ◽  
Source Data ◽  
Independent Process

This article deals with one of the important parts of applying chaos theory to financial and capital markets – namely searching for long memory effects in time series of financial instruments. Source data are daily closing prices of Central Europe stock market indices – Bratislava stock index (SAX), Budapest stock index (BUX), Prague stock index (PX) and Vienna stock index (ATX) – in the period from January 1998 to September 2007. For analysed data R/S analysis is used to calculate the Hurst exponent. On the basis of the Hurst exponent is characterized formation and behaviour of analysed financial time series. Computed Hurst exponent is also statistical compared with his expected value signalling independent process. It is also operated with 5-day returns (i.e. weekly returns) for the purposes of comparison and identification nonperiodic cycles.

scholarly journals PORTUGUESE STOCK MARKET: A LONG-MEMORY PROCESS?

2011 ◽  
Vol 12 (1) ◽  
pp. 75-84 ◽  
Author(s):  
Sameer Rege ◽  
Samuel Gil Martín
Keyword(s):  
Stock Market ◽  
Stock Prices ◽  
Long Memory ◽  
Hurst Exponent ◽  
Linear Trend ◽  
Fluctuation Analysis ◽  
Generation Process ◽  
Data Generation ◽  
Data Generation Process ◽  
Daily Returns

This paper gives a basic overview of the various attempts at modelling stochastic processes for stock markets with a specific application to the Portuguese stock market data. Long-memory dependence in the stock prices would completely alter the data generation process and econometric models not considering the long-range dependence would exhibit poor forecasting abilities. The Hurst exponent is used to identify the presence of long-memory or fractal behaviour of the data generation process for the daily returns to ascertain if the process follows a fractional brownian motion. Detrended fluctuation analysis (DFA) using linear and quadratic trends and the Geweke Porter-Hudak methods are applied to detect the presence of long-memory or persistence. We find that the daily returns exhibit a small amount of long memory and that the quadratic trend used in the DFA overestimates the value of the Hurst exponent. These findings are corroborated by the use of the Geweke Porter-Hudak method wherein the Hurst exponent is close to the DFA using the linear trend.

Sign in / Sign up

Export Citation Format

Share Document