×

On improving sensitivity of the Kalman filter. (English) Zbl 1264.62083

Summary: The impact of additive outliers on the performance of Kalman filters is discussed and a less outlier-sensitive modification of the Kalman filter is proposed. The improved filter is then used to obtain an improved smoothing algorithm and an improved state-space model parameter estimation.

MSC:

62M20 Inference from stochastic processes and prediction
65C60 Computational problems in statistics (MSC2010)
PDFBibTeX XMLCite
Full Text: Link

References:

[1] Anderson B. D. O., Moore J. B.: Optimal Filtering. Prentice-Hall, Englewood Cliffs, N. J. 1979 · Zbl 1191.93133
[2] Box G. E. P., Tiao G. C.: Bayesian Inference in Statistical Analysis. Addison-Wesley, London 1973 · Zbl 0850.62004
[3] Cantarelis N., Johnston F. R.: On-line variance estimation for the steady state Bayesian forecasting model. J. Time Ser. Analysis 3 (1982), 225-234 · Zbl 0502.62084 · doi:10.1111/j.1467-9892.1982.tb00345.x
[4] Cipra T.: Some modifications of recursive time series methods. ROBUST ’96 - Collection of Discussion Papers, Union of the Czech Mathematicians and Physicists, Praha 1997
[5] Cipra T., Rubio A.: Kalman filter with a non-linear non-gaussian observation relation. Trabajos de Estadistica 6 (1991), 111-119 · Zbl 0748.62052 · doi:10.1007/BF02873526
[6] Cipra T., Rubio, A., Canal J. L.: Robust smoothing and forecasting procedures. Central European J. Oper. Research 1 (1992), 41-56 · Zbl 0951.91508
[7] Durbin J., Koopman S. J.: Time series analysis of non-Gaussian observations based on state space models from both classical and Bayesian perspectives. J. Roy. Statist. Soc. 62 (2000), 3-56 · Zbl 0945.62084 · doi:10.1111/1467-9868.00218
[8] Franěk P.: Kalman Filter. KPMS Seminair Works Series, MFF UK, Praha 1999
[9] Hosking J. R. M., Pai J. S., Wu L. S.+ Y.: An algorithm for estimating parameters of state-space models. Statist. Probab. Letters 28 (1996), 99-106 · Zbl 0852.62090 · doi:10.1016/0167-7152(95)00098-4
[10] Jazwinski A. H.: Stochastic Processes and Filtering Theory. Academic Press, New York 1972 · Zbl 0203.50101
[11] Kalman R. E.: A new approach to linear filtering and prediction problems. Trans. Amer. Soc. Mech. Eng. - J. Basic Eng. 82 (1960), 35-45 · doi:10.1115/1.3662552
[12] Kitagawa G.: Non-Gaussian state-space modelling of nonstationary time series. J. Amer. Statist. Assoc. 82 (1987), 1032-1050 · Zbl 0644.62088 · doi:10.2307/2289375
[13] Kitagawa G.: Self-organizing state-space model. J. Amer. Statist. Assoc. 93 (1998), 1203-1215 · doi:10.2307/2669862
[14] Künsch H. R.: State space and hidden Markov models. Complex Stochastic Systems (O. E. Barndorf-Nielsen, D. R. Cox, and C. Klüppelberg, Chapman & Hall / CRC, Boca Raton 2001, pp. 109-173 · Zbl 1002.62072
[15] Masreliez C. J.: Approximate non-Gaussian filtering with linear state and observation relations. IEEE Trans. Automat. Control AC-20 (1975), 107-110 · Zbl 0298.93018 · doi:10.1109/TAC.1975.1100882
[16] Masreliez C. J., Martin R. D.: Robust Bayesian estimation for the linear model and robustifying the Kalman filter. IEEE Trans. Automat. Control AC-22 (1975), 361-371 · Zbl 0354.93054 · doi:10.1109/TAC.1977.1101538
[17] Meinhold R. J., Singpurwalla N. Z.: Robustification of the Kalman filter. J. Amer. Statist. Assoc. 84 (1989), 479-486 · doi:10.1080/01621459.1989.10478794
[18] Ruckdeschel P.: Ansätze zur Robustifizierung des Kalman-filters. Doctoral Thesis, Bayreuth University, Bayreuth 2001 · Zbl 0995.93001
[19] Tanizaki H.: Nonlinear and non-Gaussian state estimation: A quasi-optimal estimator. Comm. Statist. - Theory Methods 29 (2000), 2805-2834 · Zbl 1016.93068 · doi:10.1080/03610920008832638
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.