Nonparametric estimation of scalar diffusions based on low frequency data
Gobet, Emmanuel ; Hoffmann, Marc ; Reiß, Markus
Ann. Statist., Tome 32 (2004) no. 1, p. 2223-2253 / Harvested from Project Euclid
We study the problem of estimating the coefficients of a diffusion (Xt,t≥0); the estimation is based on discrete data X,n=0,1,…,N. The sampling frequency Δ−1 is constant, and asymptotics are taken as the number N of observations tends to infinity. We prove that the problem of estimating both the diffusion coefficient (the volatility) and the drift in a nonparametric setting is ill-posed: the minimax rates of convergence for Sobolev constraints and squared-error loss coincide with that of a, respectively, first- and second-order linear inverse problem. To ensure ergodicity and limit technical difficulties we restrict ourselves to scalar diffusions living on a compact interval with reflecting boundary conditions. ¶ Our approach is based on the spectral analysis of the associated Markov semigroup. A rate-optimal estimation of the coefficients is obtained via the nonparametric estimation of an eigenvalue–eigenfunction pair of the transition operator of the discrete time Markov chain (X,n=0,1,…,N) in a suitable Sobolev norm, together with an estimation of its invariant density.
Publié le : 2004-10-14
Classification:  Diffusion processes,  nonparametric estimation,  discrete sampling,  low frequency data,  spectral approximation,  ill-posed problems,  62G99,  62M05,  62M15
@article{1098883788,
     author = {Gobet, Emmanuel and Hoffmann, Marc and Rei\ss , Markus},
     title = {Nonparametric estimation of scalar diffusions based on low frequency data},
     journal = {Ann. Statist.},
     volume = {32},
     number = {1},
     year = {2004},
     pages = { 2223-2253},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1098883788}
}
Gobet, Emmanuel; Hoffmann, Marc; Reiß, Markus. Nonparametric estimation of scalar diffusions based on low frequency data. Ann. Statist., Tome 32 (2004) no. 1, pp.  2223-2253. http://gdmltest.u-ga.fr/item/1098883788/