ROBUST KALMAN FILTER AND ITS APPLICATION IN TIME-SERIES ANALYSIS

A method of robustification of the Kalman filter is suggested in the paper. In general, the method provides approximative recursive formulas for robust estimation of the state but in some special cases exact recursive formulas can be derived. The steady model and the AR(1) model are investigated in more details including a simulation study and the strong consistency of the recursive formulas for the robust estimation of the autoregressive parameter.