A1080
Title: Quasi-likelihood analysis and estimation for a degenerate diffusion process
Authors: Nakahiro Yoshida - University of Tokyo (Japan) [presenting]
Abstract: The quasi-likelihood analysis (QLA) is an abstract framework for statistical inference for stochastic processes. Under easily verified conditions, this theory enables us to obtain a polynomial-type large deviation inequality for the quasi-likelihood random field and, consequently, asymptotic properties, including moments convergence, of the quasi-maximum likelihood estimator and the quasi-Bayesian estimator. This scheme has been used for various parametric models of nonlinear stochastic processes thanks to its universal design and easy handling. A simplified quasi-likelihood analysis is applied to the parametric estimation of a degenerate diffusion process.