Testing For Long Memory In Potentially Nonstationary Perturbed Fractional Processes

In this paper, we propose new tests for long memory in stationary and nonstationary time series possibly perturbed by short-run noise which may be serially correlated. The tests are all based on semiparametric estimators and exploit the self-similarity property of long memory processes. We offer simulation results that show good size properties of the tests, with power against spurious long memory. An empirical study of daily log-squared returns series of exchange rates and DJIA30 stocks shows that indeed there is long memory in exchange rate volatility and stock return volatility.