The Tobit Kalman Filter: An Estimator for Censored Measurements

Tobit model censored data arise in multiple engineering applications through saturating sensors, limit-of-detection effects, and image frame effects. In this brief, we introduce a novel formulation of the Kalman filter for Tobit Type 1 censored measurements. Our proposed formulation, called the Tobit Kalman filter, is identical to the standard Kalman filter in the no-censoring case. At or near the censored region, the Tobit Kalman filter utilizes a local approximation of the probability of censoring in order to provide a fully recursive estimate of the state and state error covariance. The additional computational burden of the method compared with the standard Kalman filter is limited to the calculation of m normal probability density functions and m normal cumulative density functions per update, where m is the number of measurements.

[1]  H. T. Banksa,et al.  Estimation and Prediction With HIV-Treatment Interruption Data , 2007 .

[2]  H Putter,et al.  A Bayesian approach to parameter estimation in HIV dynamical models , 2002, Statistics in medicine.

[3]  Soummya Kar,et al.  Kalman Filtering With Intermittent Observations: Weak Convergence to a Stationary Distribution , 2009, IEEE Transactions on Automatic Control.

[4]  A. Doucet,et al.  Particle filtering for partially observed Gaussian state space models , 2002 .

[5]  John B. Hampshire,et al.  Tobit maximum-likelihood estimation for stochastic time series affected by receiver saturation , 1992, IEEE Trans. Inf. Theory.

[6]  Neil J. Gordon,et al.  A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking , 2002, IEEE Trans. Signal Process..

[7]  Econo Metrica.  REGRESSION ANALYSIS WHEN THE DEPENDENT VARIABLE IS TRUNCATED NORMAL , 2016 .

[8]  Gabriele Fiorentini,et al.  Estimating variances and covariances in a censored regression model , 1993 .

[9]  Y. Bar-Shalom,et al.  Censoring sensors: a low-communication-rate scheme for distributed detection , 1996, IEEE Transactions on Aerospace and Electronic Systems.

[10]  Michael J. Piovoso,et al.  Modelling HIV-1 2-LTR dynamics following raltegravir intensification , 2013, Journal of The Royal Society Interface.

[11]  E. Bai,et al.  Block Oriented Nonlinear System Identification , 2010 .

[12]  J. Tobin.  Estimation of Relationships for Limited Dependent Variables , 1958 .

[13]  Eric Moulines,et al.  Comparison of resampling schemes for particle filtering , 2005, ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005..

[14]  P.J. Zufiria,et al.  A Kalman filter with censored data , 2005, IEEE International Workshop on Intelligent Signal Processing, 2005..

[15]  Harvey Thomas Banks,et al.  Receding Horizon Control of HIV , 2011 .

[16]  Hulin Wu,et al.  Hierarchical Bayesian inference for HIV dynamic differential equation models incorporating multiple treatment factors , 2010, Biometrical journal. Biometrische Zeitschrift.

[17]  Fouad Giri,et al.  Frequency Identification of Nonparametric Wiener Systems , 2010 .

[18]  Pramod K. Varshney,et al.  Sequential Bayesian estimation with censored data , 2012, 2012 IEEE Statistical Signal Processing Workshop (SSP).

[19]  Richard T. Carson,et al.  The Tobit Model With a Non-Zero Threshold , 2005 .

[20]  Robert A. Moffitt,et al.  The Uses of Tobit Analysis , 1980 .

[21]  Michael J. Piovoso,et al.  Nonlinear estimators for censored data: A comparison of the EKF, the UKF and the Tobit Kalman filter , 2015, 2015 American Control Conference (ACC).

[22]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[23]  Richard Blundell,et al.  An Exogeneity Test for a Simultaneous Equation Tobit Model with an Application to Labor Supply , 1986 .

[24]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[25]  T. Wigren.  Convergence analysis of recursive identification algorithms based on the nonlinear Wiener model , 1994, IEEE Trans. Autom. Control..

[26]  Wendelin Schnedler,et al.  Likelihood Estimation for Censored Random Vectors , 2005 .

[27]  Takeshi Amemiya,et al.  The Estimation of a Simultaneous-Equation Tobit Model , 1979 .

[28]  Davide Spinello,et al.  Nonlinear Estimation With State-Dependent , 2010 .

[29]  Mark Ilg,et al.  Ballistic Roll Estimation using EKF Frequency Tracking and Adaptive Noise Cancellation , 2013, IEEE Transactions on Aerospace and Electronic Systems.

[30]  Mark Ilg,et al.  Kalman filter-based tracking of multiple similar objects from a moving camera platform , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).