Memory Parameter Estimation in the Presence of Level Shifts and Deterministic Trends

We propose estimators of the memory parameter of a time series that are robust to a wide variety of random level shift processes, deterministic level shifts and de- terministic time trends. The estimators are simple trimmed versions of the popular log-periodogram regression estimator that employ certain sample size-dependent, and in some cases, data-dependent trimmings which discard low-frequency components. Regardless of whether the underlying long/short-memory process is contaminated by level shifts or deterministic trends, our estimators are shown to be consistent and asymptotically normal with the same limiting variance as the standard log-periodogram estimator. An extensive simulation study shows that our estimators perform their in- tended purpose quite well, substantially decreasing both nite sample bias and root mean-squared error in the presence of these contaminating components. Furthermore, we assess the tradeos involved with their use when such components are not present but the underlying process exhibits strong short-memory dynamics or is contaminated by noise. To balance the potential nite sample biases involved in estimating the mem- ory parameter, we recommend a particular version of our estimators that performs well in a wide variety of circumstances. Finally, we apply our estimators to stock market volatility and hydrological data to nd that many of the time series typically thought to be long-memory processes actually appear to be short-memory processes contaminated by level shifts or deterministic trends.