Use of the Kalman filter for inference in state-space models with unknown noise distributions

The Kalman filter is frequently used for state estimation in state-space models when the standard Gaussian noise assumption does not apply. A problem arises, however, in that inference based on the incorrect Gaussian assumption can lead to misleading or erroneous conclusions about the relationship of the Kalman filter estimate to the true (unknown) state. This paper shows how inequalities from probability theory associated with the probabilities of convex sets have potential for characterizing the estimation error of a Kalman filter in such a non-Gaussian (distribution-free) setting.

[1]  T. W. Anderson.  The integral of a symmetric unimodal function over a symmetric convex set and some probability inequalities , 1955 .

[2]  S. Sherman.  A Theorem on Convex Sets with Applications , 1955 .

[3]  A. Jazwinski.  Stochastic Processes and Filtering Theory , 1970 .

[4]  S. Gupta,et al.  A generalization of Anderson’s theorem on unimodal functions , 1976 .

[5]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[6]  Robert Kohn,et al.  Prediction mean squared error for state space models with estimated parameters , 1986 .

[7]  G. Kitagawa.  Non-Gaussian State—Space Modeling of Nonstationary Time Series , 1987 .

[8]  James C. Spall,et al.  [That BLUP is a Good Thing: The Estimation of Random Effects]: Comment: The Kalman Filter and BLUP , 1991 .

[9]  Nicholas G. Polson,et al.  A Monte Carlo Approach to Nonnormal and Nonlinear State-Space Modeling , 1992 .

[10]  J. Spall.  THE DISTRIBUTION OF NONSTATIONARY AUTOREGRESSIVE PROCESSES UNDER GENERAL NOISE CONDITIONS , 1993 .

[11]  Guanrong Chen,et al.  Suboptimal Kalman Filtering for Linear Systems with Non-Gaussian Noise , 1993 .

[12]  K. V. Ramachandra,et al.  A three-state Kalman tracker using position and rate measurements , 1993 .

[13]  J. C. Spall,et al.  The distribution of nonstationary autoregressive processes under general noise conditions , 1993, Proceedings of 32nd IEEE Conference on Decision and Control.

[14]  Hisashi Tanizaki,et al.  Prediction, filtering and smoothing in non-linear and non-normal cases using Monte Carlo integration , 1994 .

[15]  James C. Spall,et al.  Uncertainties for recursive estimators in nonlinear state-space models, with applications to epidemiology , 1995, Autom..

[16]  James C. Spall.  The Kantorovich inequality for error analysis of the Kalman filter with unknown noise distributions , 1995, Autom..

[17]  James C. Spall,et al.  Use of the Kalman Filterfor Inference in State-Space Models with Unknown Noise Distributions , 1996 .