| Titre | Méthodes d'estimation de l'exposant de Hurst. Application aux rentabilités boursières | |
|---|---|---|
| Auteur | Valérie Mignon | |
 |
Revue | Economie et prévision |
| Numéro | no 132-133, 1998/1-2 | |
| Rubrique / Thématique | Méthodes |
|
| Page | 193-214 | |
| Résumé anglais |
Methods for Estimating the Hurst Exponent: Application to Stock Market Returns
by Valérie Mignon
This paper analyses whether long memory is a characteristic of stock returns. It starts by defining the main long memory processes, such as fractional Gaussian noise and ARFJJVIA processes, which are characterised by a parameter called the Hurst exponent. We then review various methods for estimating this exponent. Finally, we apply these procedures to time series of weekly stock returns. Our findings suggest that Italian and Japanese stock returns display long memory persistence. Since long memory is directly related to the issue of market efficiency, these findings raise questions about the efficiency of Italian and Japanese capital markets. Source : Éditeur (via Persée) |
|
| Article en ligne | http://www.persee.fr/web/revues/home/prescript/article/ecop_0249-4744_1998_num_132_1_5909 |
