TY - UNPB AB - We deal with the important question of estimating the long-run variance of a stationary sequence.We derive the asymptotic properties of a generalized Newey-West type of estimator in the case of alinear I(d) process. The results show that the bias and asymptotic distribution of the generalizedNewey-West estimator depend on the memory parameter d. If the series has long memory then theestimator might even have a non-Gaussian limit distribution. The optimal bandwidth parameter qminimising MSE is derived. Theoretical results explain the large bias observed in simulation studieswith arbitrarily chosen q. An alternative estimator is suggested. It has an asymptotic Gaussiandistribution and bias which do not depend on d. The estimator is easy to apply and can be used toconstruct confidence intervals. Simulations confirm the theoretical findings. AU - Abadir,K AU - Distaso,W AU - Giraitis,L PY - 2005/// TI - Two estimators of the long-run variance ER -