Consistency of maximum likelihood estimation for some dynamical systems (Q2338917)

The aim of the present paper is to study the asymptotic consistency of maximum likelihood estimation for parametrized families of deterministic systems observed with noise. In this direction, the authors manage to prove that, under suitable conditions in terms of statistical properties of the family of dynamical systems and the observations regarding ideas from information theory and the theory of dynamical systems, the maximum likelihood parameter estimation is consistent. Furthermore, the authors manage to give the implications of general statistical properties related to the maximum likelihood estimation for some well-studied properties of dynamical systems as well as to give several applications related to the above results such as shifts of finite type with Gibbs measures and Axiom A attractors with Sinai-Ruelle-Bowen measures.