This paper proposes a class of algorithms for analyzing event count time series, based on state space modeling and Kalman filtering. While the dynamics model is kept Gaussian linear, nonlinear observation function chosen. In order to estimate states, an iterated extended filter employed. Positive definiteness covariance matrices preserved by square-root filtering approach, singular value decomp...

The validity of magnetotelluric time-series processing methods has been lacking reasonable testing criteria. Since the time series synthesized by existing techniques are not fully derived from a given model, they reliable. In this paper, we present novel approach to synthesize based on forward modeling and correspondence between frequency domain electromagnetic fields. approach, obtain response...