Parametric estimation of a diffusion process with delays (Q1190303)

This paper studies the problem of estimating the parameters of a continuous-time stochastic process. The process is assumed to satisfy an autoregressive-like equation. This equation expresses the derivative of the process as a function of its past evolution, and it has a form which is quite different from that of the usual autoregressive equation. Using previous results obtained by Ibragimov and Khasminski and by Kutoyants, the authors make use of the asymptotic properties of the likelihood process to derive a number of results on the convergence, asymptotic normality and statistical efficiency of the proposed parameter estimator.