Parameter estimation via artificial data generation with the “two-stage” approach

In this paper, we consider one of the most classical estimation problem, that of identifying an unknown parameter in a given model from measurements of input/output data. We present a new method named the two-stage approach which provides efficient estimates. The method is based on the preliminary generation of artificial data, and it is fully non-Bayesian. In this way, it is possible to avoid the well known difficulties encountered when resorting to Kalman filtering techniques in parameter estimation.