### Abstract

Let X_{n} = Σ_{i}∞=1 a_{i}ε _{n}-_{i}, where the ε_{i} are i.i.d, with mean 0 and at least finite second moment, and the a_{i} are assumed to satisfy a_{i} = O(_{i}^{-β}) with β > 1/2. When 1/2 < β < 1, X_{n} is usually called a long-range dependent or long-memory process. For a certain class of Borel functions K(x_{1},..., x_{d+1}), d ≥0, from R^{d+1} to R, which includes indicator functions and polynomials, the stationary sequence K (X_{n}, X_{n}+1,..., X_{n+d}) is considered. By developing a finite orthogonal expansion of K (X_{n},..., X_{n+d}), the Berry-Esseen type bounds for the normalized sum Q_{N}/√N, Q_{N} = ε _{n}^{N}=_{1} (K(X_{n},..., X_{n+d}) - EK(X_{n},..., X_{n+d})) are obtained when Q_{N}/√N obeys the central limit theorem with positive limiting variance.

Original language | English |
---|---|

Pages (from-to) | 301-321 |

Number of pages | 21 |

Journal | Bernoulli |

Volume | 14 |

Issue number | 2 |

DOIs | |

Publication status | Published - 2008 May 1 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Statistics and Probability

### Cite this

*Bernoulli*,

*14*(2), 301-321. https://doi.org/10.3150/07-BEJ112