Finite dimensional optimal filters for a class of ltô- processes with jumping parameters
Tomas Björk · Stochastics · 1980
We consider a finite state Markov process θ, feeding the coefficients of a linear Itô-equation with state ξ. The θ-process is observed in white noise, and it is shown that the optimal nonlinear filter for ξ, is of finite dimension. We also derive finite dimensional equations for optimal prediction and smoothing.