Time: 14h00, Thursday, November 15, 2018
Location: Room 302, Building A5, Institute of Mathematics
Abstract: In this talk, we consider a multidimensional diffusions with jumps driven by a Brownian motion and a Poisson random measure associated with a Lévy process with possibly infinite Lévy measure, whose drift coefficient depends on a multidimensional unknown parameter. Under some appropriate assumptions on the coefficients of the equation, the ergodicity of the solution and the integrability of the Lévy measure, we prove the local asymptotic normality (LAN) property from high-frequency discrete observations with increasing observation window. To obtain the result, we use the Malliavin calculus techniques and the Girsanov change of measures.