An Analysis of Long Memory in the SSE's Component Index

Stock returns can reflect the behavior of investors in the securities and financial markets. We test for the presence of long memory in the Shenzhen Stock Exchange (SSE) using the R/s and KPSS tests. In addition, the parameter of long memory is estimated by the LP regression method. This analysis provides significant evidence to show that returns recorded by the SSE’s Component Index exhibit long memory processes. This evidence suggests that the SSE stock market is not efficient, contradicting the martingale model.