Nonparametric estimation of the derivatives of the stationary density for stationary processes - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue ESAIM: Probability and Statistics Année : 2013

Nonparametric estimation of the derivatives of the stationary density for stationary processes

Emeline Schmisser
  • Fonction : Auteur
  • PersonId : 857737

Résumé

Abstract In this article, our aim is to estimate the successive derivatives of the stationary density $f$ of a strictly stationary and $ \beta$-mixing process$ \left(X_{t}\right)_{t\geq0}$. This process is observed at discrete times $t=0,\Delta,\ldots,n\Delta$. The sampling interval $\Delta$ can be fixed or small. We use a penalized least-square approach to compute adaptive estimators. If the derivative $f^{(j)}$ belongs to the Besov space $\mathcal{B}_{2,\infty}^{\alpha}$, then our estimator converges at rate $\left(n\Delta\right)^{-\alpha/(2\alpha+2j+1)}$. Then we consider a diffusion with known diffusion coefficient. We use the particular form of the stationary density to compute an adaptive estimator of its first derivative $f'$. When the sampling interval $\Delta$ tends to 0, and when the diffusion coefficient is known, the convergence rate of our estimator is $\left(n\Delta\right)^{-\alpha/(2\alpha+1)}$. When the diffusion coefficient is known, we also construct a quotient estimator of the drift for low-frequency data.
Fichier principal
Vignette du fichier
estimation_f_ang.pdf (407.69 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-00507025 , version 1 (30-07-2010)

Identifiants

Citer

Emeline Schmisser. Nonparametric estimation of the derivatives of the stationary density for stationary processes. ESAIM: Probability and Statistics, 2013, 17, pp33-69. ⟨10.1080/02331888.2011.591931⟩. ⟨hal-00507025⟩
135 Consultations
158 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More