Parameter estimation for a discrete sampling of an intergrated Ornstein-Uhlenbeck process

We study the estimation of parameters θ=(μ, σ2) for a diffusion when we observe a discreatization wiht step Δ of the integral To keep computations tractable we focus on the case of an Ornstein–Uhlenberck process, but our results provide informations on how to deal with other processes. We study an efficient estimator θ n based on the Gaussian property of the process and we give an estimator θ n based on Ryden's idea of maximum likehood split data. We compare these different estimators: first we give some numerical results, then we give a theoretical explanations for these results.