| HAL : hal-00122817, version 1 |
| arXiv : math.ST/0701154 |
| Fiche détaillée | Récupérer au format |
|
|
| (2003) |
|
|
|
|
| Efficient estimators : the use of neural networks to construct pseudo panels |
|
|
| Marie Cottrell 1, 2Patrice Gaubert 3 |
|
|
| (2003) |
|
|
| Pseudo panels constituted with repeated cross-sections are good substitutes to true panel data. But individuals grouped in a cohort are not the same for successive periods, and it results in a measurement error and inconsistent estimators. The solution is to constitute cohorts of large numbers of individuals but as homogeneous as possible. This paper explains a new way to do this: by using a self-organizing map, whose properties are well suited to achieve these objectives. It is applied to a set of Canadian surveys, in order to estimate income elasticities for 18 consumption functions.. |
|
|
|
|
|
|
|
|
|
|
| 1 : | Statistique Appliquée et MOdélisation Stochastique (SAMOS) |
| Université Paris I - Panthéon-Sorbonne | |
| 2 : | Modélisation Appliquée, Trajectoires Institutionnelles et Stratégies Socio-Économiques (MATISSE) |
| CNRS : UMR8595 – Université Paris I - Panthéon-Sorbonne | |
| 3 : | LEMMA (LEMMA) |
| Université du Littoral Côte d'Opale | |
|
|
|
|
|
|
|
|
| Domaine | : | Mathématiques/Statistiques Sciences de l'Homme et Société/Economies et finances |
|
|
| Pseudo panels – self-organizing maps |
|
|
| Liste des fichiers attachés à ce document : | |||||
|
|
|
| hal-00122817, version 1 | |
| http://hal.archives-ouvertes.fr/hal-00122817 | |
| oai:hal.archives-ouvertes.fr:hal-00122817 | |
| Contributeur : Marie Cottrell | |
| Soumis le : Vendredi 5 Janvier 2007, 10:42:43 | |
| Dernière modification le : Lundi 22 Janvier 2007, 15:15:21 | |