Optimal filtering of doubly stochastic auto-regressive processes (Q1295087)

Here the authors derive exact finite-dimensional filters for a class of doubly stochastic auto-regressive models, the parameters of such processes varying according to a nonlinear function of a Gauss-Markov process. A characterization of the general solution is provided, and examples in which the state of the filter is determined by a finite number of sufficient statistics are furnished.