Abstract : This paper deals with efficient estimation in exchangeable nonlinear dynamic panel models with common unobservable factor. The specification accounts for both micro- and macro-dynamics, induced by the lagged individual observation and the common stochastic factor, respectively. For large cross-sectional and time dimensions, and under a semiparametric identification condition, we derive the efficiency bound and introduce efficient estimators for both the micro- and macro-parameters. In particular, we show that the fixed effects estimator of the micro-parameter is not only consistent, but also asymptotically efficient.The results are illustrated with the stochastic migration model for credit risk analysis.
Type de document :
Communication dans un congrès
41èmes Journées de Statistique, SFdS, Bordeaux, 2009, Bordeaux, France, France. 2009
https://hal.inria.fr/inria-00386744
Contributeur : Conférence Jds2009
<>
Soumis le : vendredi 22 mai 2009 - 09:17:47
Dernière modification le : mercredi 18 avril 2018 - 12:24:30
Document(s) archivé(s) le : lundi 15 octobre 2012 - 10:56:07
Patrick Gagliardini, Christian Gourieroux. Efficiency in large dynamic panel models with common factor. 41èmes Journées de Statistique, SFdS, Bordeaux, 2009, Bordeaux, France, France. 2009. 〈inria-00386744〉
