Nonparametric drift estimation for diffusions from noisy data

Abstract : Let us consider a diffusion process \left(X_{t}\right)_{t\geq0}, with drift b(x) and diffusion coefficient \sigma(x). This process is assumed to be strictly stationnary, \beta-mixing and ergodic. At discrete times t_{k}=k\delta for k from 1 to M, we have at disposal noisy data of the sample path, Y_{k\delta}=X_{k\delta}+\varepsilon_{k}. The random variables \left(\varepsilon_{k}\right) are i.i.d, centred and independent of \left(X_{t}\right). In order to reduce the noise effect, we split data into groups of equal size p and build empirical means. The group size p is chosen such that \Delta=p\delta is small whereas M\delta is large. Then, we estimate the drift function b in a compact set A in a nonparametric way by a penalized least squares approach. We obtain a bound for the risk of the resulting adaptive estimator. We also provide several examples of diffusions satisfying our assumptions and realise various simulations. Our simulation results illustrate the theoretical properties of our estimators.
Type de document :
Article dans une revue
Statistics & Decisions, 2011, 28 (2), pp.119-150. <10.1524/stnd.2011.1063>
Liste complète des métadonnées
Contributeur : Emeline Schmisser <>
Soumis le : vendredi 25 septembre 2009 - 16:46:52
Dernière modification le : mardi 11 octobre 2016 - 11:58:28
Document(s) archivé(s) le : mardi 16 octobre 2012 - 11:25:19


Fichiers produits par l'(les) auteur(s)




Emeline Schmisser. Nonparametric drift estimation for diffusions from noisy data. Statistics & Decisions, 2011, 28 (2), pp.119-150. <10.1524/stnd.2011.1063>. <hal-00419954>



Consultations de
la notice


Téléchargements du document