Estimation for Stochastic Damping Hamiltonian Systems under Partial Observation. II Drift term

Patrick Cattiaux (1) , José R. León (2) , Clémentine Prieur (3, 4)

1 IMT - Institut de Mathématiques de Toulouse UMR5219
2 Escuela de Matematicas [Caracas]
3 MOISE - Modelling, Observations, Identification for Environmental Sciences
4 GdR MASCOT-NUM - Méthodes d'Analyse Stochastique des Codes et Traitements Numériques

This paper is the second part of our study started with \citet*{CLP}. For some ergodic hamiltonian systems we obtained a central limit theorem for a non-parametric estimator of the invariant density, under partial observation (only the positions are observed). Here we obtain similarly a central limit theorem for a non-parametric estimator of the drift term. This theorem lies on the previous result for the invariant density.

Domaines: Statistiques [math.ST]; Théorie [stat.TH]

Patrick Cattiaux, José R. León, Clémentine Prieur. Estimation for Stochastic Damping Hamiltonian Systems under Partial Observation. II Drift term. 2013. ⟨hal-00877054v1⟩