A new algorithm for latent state estimation in non-linear time series models

We consider the problem of optimal state estimation for a wide class of non-linear time series models. A modified sigma point filter is proposed, which uses a new procedure for generating sigma points. Unlike the existing sigma point generation methodologies in engineering, where negative probability weights may occur, we develop an algorithm capable of generating sample points that always form a valid probability distribution while still allowing the user to sample using a random number generator. The effectiveness of the new filtering procedure is assessed through simulation examples.

[1]  G. Grimmett,et al.  Probability and random processes , 2002 .

[2]  A. Farina,et al.  Tracking a ballistic target: comparison of several nonlinear filters , 2002 .

[3]  F. Gustafsson,et al.  Complexity analysis of the marginalized particle filter , 2005, IEEE Transactions on Signal Processing.

[4]  Aurora Hermoso-Carazo,et al.  Different approaches for state filtering in nonlinear systems with uncertain observations , 2007, Appl. Math. Comput..

[5]  Paresh Date,et al.  A new moment matching algorithm for sampling from partially specified symmetric distributions , 2008, Oper. Res. Lett..

[6]  Ali Esmaili,et al.  Probability and Random Processes , 2005, Technometrics.

[7]  Charles R. Johnson,et al.  Matrix analysis , 1985, Statistical Inference for Engineers and Data Scientists.

[8]  Guiming Wang,et al.  On the latent state estimation of nonlinear population dynamics using Bayesian and non-Bayesian state-space models , 2007 .

[9]  Jeffrey K. Uhlmann,et al.  Unscented filtering and nonlinear estimation , 2004, Proceedings of the IEEE.

[10]  G. Kitagawa.  Monte Carlo Filter and Smoother for Non-Gaussian Nonlinear State Space Models , 1996 .

[11]  Jesper Lund,et al.  Non-Linear Kalman Filtering Techniques for Term-Structure Models , 1997 .

[12]  T. Alderweireld,et al.  A Theory for the Term Structure of Interest Rates , 2004, cond-mat/0405293.

[13]  Gregory L. Plett,et al.  Sigma-point Kalman filtering for battery management systems of LiPB-based HEV battery packs: Part 1: Introduction and state estimation , 2006 .

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

[15]  Jun S. Liu,et al.  Sequential Monte Carlo methods for dynamic systems , 1997 .

[16]  L. A. Bauer.  Inauguration of the magnetic survey of the North Pacific Ocean , 1905 .

[17]  G. Evensen.  Sequential data assimilation with a nonlinear quasi‐geostrophic model using Monte Carlo methods to forecast error statistics , 1994 .

[18]  P. Bentler,et al.  Greatest lower bound to the elliptical theory kurtosis parameter , 1986 .

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

[20]  P. Houtekamer,et al.  Data Assimilation Using an Ensemble Kalman Filter Technique , 1998 .

[21]  H. Kushner.  Numerical Methods for Stochastic Control Problems in Continuous Time , 2000 .

[22]  Petros G. Voulgaris,et al.  On optimal ℓ∞ to ℓ∞ filtering , 1995, Autom..

[23]  J. Cox.  The Constant Elasticity of Variance Option Pricing Model , 1996 .

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