Résumé
There exists a wide literature on parametrically or semi-parametrically modelling strongly dependent time series using a long-memory parameter d, including more recent work on wavelet estimation. As a generalization of these latter approaches, in this work we allow the long-memory parameter d to be varying over time. We adopt a semi-parametric approach in order to avoid fitting a time-varying parametric model, such as tvARFIMA, to the observed data. We study the asymptotic behavior of a local log-regression wavelet estimator of the time-dependent d. Both simulations and a real data example complete our work on providing a fairly general approach.
| langue originale | Anglais |
|---|---|
| Pages (de - à) | 813-844 |
| Nombre de pages | 32 |
| journal | Stochastic Processes and their Applications |
| Volume | 121 |
| Numéro de publication | 4 |
| Les DOIs | |
| état | Publié - 1 avr. 2011 |
| Modification externe | Oui |
Empreinte digitale
Examiner les sujets de recherche de « Locally stationary long memory estimation ». Ensemble, ils forment une empreinte digitale unique.Contient cette citation
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver