|
系统工程理论与实践 2006
Long-Term Memory in Stock Returns of Shanghai Stock Exchange: Evidence from V/S Statistic
|
Abstract:
For the first time,the rescaled variance test is applied to investigate the long-term memory effect in China's stock returns.We examine the full sample daily stock market returns of Shanghai A and B shares.Based on the detection of changes of variance using the iterated cumulative sum of squares algorithm,we study the long-term memory effect of stock market returns in different sub-periods. Some randomly selected stocks are also considered.Results obtained include: there exists little evidence of long-term memory in the full sample stock market returns of Shanghai A and B shares,with regard to A shares,the B shares shows relatively more significant long-term memory;there are 2 and 4 notable variance changes in A and B shares respectively,and for each sub-period of A shares,there does not exist notable long-term memory,however,there does exist considerable long-term memory in some sub-periods of B shares.Study of the randomly selected stocks concludes that among the 10 selected stocks,only 1 stock's return series displays significant long-term memory,and with regard to A shares,the B shares shows relatively more significant long-term memory.