Approximation of the solution of the backward stochastic differential equation. Small noise, large sample and high frequency cases
- 77 Downloads
We present a review of some recently obtained results on estimation of the solution of a backward stochastic differential equation (BSDE) in the Markovian case. We suppose that the forward equation depends on some finite-dimensional unknown parameter. We consider the problem of estimating this parameter and then use the proposed estimator to estimate the solution of the BSDE. This last estimator is constructed with the help of the solution of the corresponding partial differential equation. We are interested in three observation models admitting a consistent estimation of the unknown parameter: small noise, large samples and unknown volatility. In the first two cases we have a continuous time observation, and the unknown parameter is in the drift coefficient. In the third case the volatility of the forward equation depends on the unknown parameter, and we have discrete time observations. The presented estimators of the solution of the BSDE in the three casesmentioned are asymptotically efficient.
KeywordsSTEKLOV Institute Maximum Likelihood Estimator Regularity Condition Fisher Information Matrix Small Noise
Unable to display preview. Download preview PDF.
- 6.K. Kamatani and M. Uchida, “Hybrid multi-step estimators for stochastic differential equations based on sampled data,” Stat. Inference Stoch. Processes, doi: 10.1007/s11203-014-9107-4 (2014).Google Scholar
- 15.M. Sørensen, “Estimating functions for diffusion-type processes,” in Statistical Methods for Stochastic Differential Equations, Ed. by M. Kessler, A. Lindner, and M. Sørensen (CRC Press, Boca Raton, FL, 2009), pp. 1–107.Google Scholar
- 16.L. Zhou, “Problèmes statistiques pour des EDS et les EDS rétrogrades,” PhD Thesis (Univ. Maine, Le Mans, 2013).Google Scholar