## Abstract

The bias-reduced log-periodogram estimator d̂ _{LP}(r), r ≥ 1 of Andrews and Guggenberger (2003, Econometrica 71, 675-712) for the long-memory parameter d in a stationary long-memory time series reduces the asymptotic bias of the original log-periodogram estimator d _{GPH} = d̂ _{LP}(0) of Geweke and Porter-Hudak (1983) by an order of magnitude but inflates the asymptotic variance by a multiplicative constant c _{r}, for example, C _{1} = 2.25 and c _{2} = 3.52. In this paper, we introduce a new, computationally attractive estimator d̂ _{WLP}(r) by taking a weighted average of d̂ _{LP}(0) estimators over different bandwidths. We show that, for each fixed r ≥ 0, the new estimator can be designed to have the same asymptotic bias properties as d̂ _{LP}(r) but its asymptotic variance is changed by a constant c* _{r} that can be chosen to be as small as desired, in particular smaller than c _{r}. The same idea is also applied to the local-polynomial Whittle estimator d̂ _{LW}(r) in Andrews and Sun (2004, Econometrica 72, 569-614) leading to the weighted estimator d̂ _{WLW}(r). We establish the asymptotic bias, variance, and mean-squared error of the weighted estimators and show their asymptotic normality. Furthermore, we introduce a data-dependent adaptive procedure for selecting r and the bandwidth m and show that up to a logarithmic factor, the resulting adaptive weighted estimator achieves the optimal rate of convergence. A Monte Carlo study shows that the adaptive weighted estimator compares very favorably to several other adaptive estimators.

Original language | English (US) |
---|---|

Pages (from-to) | 863-912 |

Number of pages | 50 |

Journal | Econometric Theory |

Volume | 22 |

Issue number | 5 |

DOIs | |

State | Published - Oct 2006 |

## All Science Journal Classification (ASJC) codes

- Social Sciences (miscellaneous)
- Economics and Econometrics