| HAL : hal-00625117, version 4 |
| arXiv : 1109.4533 |
| Fiche détaillée | Récupérer au format |
|
|
| Versions disponibles : | v1 (21-09-2011) | v2 (12-03-2012) | v3 (21-06-2012) | v4 (03-07-2012) |
|
|
|
|
| Construction of an informative hierarchical prior distribution. Application to electricity load forecasting |
|
|
| Tristan Launay 1, 2Anne Philippe 1 |
|
|
| (20/09/2011) |
|
|
| n this paper, we are interested in the estimation and prediction of a parametric model on a short dataset upon which it is expected to overfit and perform badly. To overcome the lack of data (relatively to the dimension of the model) we propose the construction of a hierarchical informative Bayesian prior based upon another longer dataset which is assumed to share some similarities with the original, short dataset. We apply the methodology to a basic model for the electricity load forecasting on both simulated and real datasets, where it leads to a substantial improvement of the quality of the predictions. |
|
|
|
|
|
|
|
|
|
|
| 1 : | Laboratoire de Mathématiques Jean Leray (LMJL) |
| CNRS : UMR6629 – Université de Nantes – École Centrale de Nantes | |
| 2 : | E.D.F. Division Recherche et Développement [Clamart] |
| EDF | |
|
|
|
|
|
|
|
|
| Domaine | : | Mathématiques/Statistiques Statistiques/Théorie |
|
|
| informative prior – mcmc algorithms – small dataset – electricity load forecasting |
|
|
| Liste des fichiers attachés à ce document : | |||||
|
|
|
| hal-00625117, version 4 | |
| http://hal.archives-ouvertes.fr/hal-00625117 | |
| oai:hal.archives-ouvertes.fr:hal-00625117 | |
| Contributeur : Anne Philippe | |
| Soumis le : Mardi 3 Juillet 2012, 14:11:17 | |
| Dernière modification le : Mardi 3 Juillet 2012, 15:19:32 | |