A1199
Title: Kernel density estimation for continuous Riemannian stochastic processes
Authors: Vincent Monsan - Universite Felix Houphouat boigny Abidjan Cocody (Cote d'Ivoire)
Anne Francoise Yao - Universite Clermont Auvergne/LMBP (France) [presenting]
Axel Mothe - Ecole des Ponts Paris Tech (France)
Djack Guy-Aude Kouadio - Universite Felix Houphouet Boigny - Laboratoire LAMI (Cote d'Ivoire)
Catherine Aaron - Universite Clermont Auvergne (France)
Abstract: The focus is on kernel density estimation of the univariate marginal distribution of a strongly mixing continuous time process. This topic has been widely treated in the literature in the case where the process has values in an Euclidean space. However, the situation where the process lives in a Riemannian submanifold has not yet been treated. The estimator appears as the integral counterpart of a recent work, which generalized the results of a prior study to the case of stochastic processes under some mixing conditions. Namely, some consistent results and applications to some diffusion processes are given.
