Estimation with Missing Data

DOI10.1076/MCMD.5.3.220.3681MaRDI QIDQ4700086zbMATH OpenOpenAlexFDO

Authors Graham C. Goodwin, Arie Feuer

Publication date 1 December 1999

Published in Mathematical and Computer Modelling of Dynamical Systems (Search for Journal in Brave)

Full work available at URL http://hdl.handle.net/10.1076/mcmd.5.3.220.3681

zbMATH Keywords

estimationexpectation maximization algorithmfilteringfixed interval smoothinghidden Markov model

Mathematics Subject Classification ID

Estimation and detection in stochastic control theory (93E10)

Review text

The paper is a clearly written review of estimation problems with missing data. A hidden Markov model is considered, \[ x_{t+1}= Ax_t+ \nu_t;\quad y_t= Cx_t+ w_t. \] Here \(x_t\in \mathbb{R}^n\) form an unobserved state sequence, \(y_t\in \mathbb{R}^m\) are measured data, \(A\) and \(C\) are constant matrices, \(\{\nu_t\}\) and \(\{w_t\}\) are mutually independent i.i.d. sequences. Two problems are investigated: (i) the estimation of a state given measured data and model parameters, and (ii) the estimation of model parameters given the measured data only. Parameter estimation is based on the Expectation Maximization (EM) algorithm. In the case of missing measurements, the fixed interval smoothing technique is employed to complete the Expectation-step in order to `fill-in' the missing data. More mathematical details can be found in \textit{R. J. Elliott} et al. [Hidden Markov models: estimation and control, Springer-Verlag (1995; Zbl 0819.60045)].

Recommendations

• Parameter estimation of Gaussian hidden Markov models when missing observations occur
• Fixed interval estimation in state space models when some of the data are missing or aggregated
• scientific article; zbMATH DE number 1833970
• Identification of ARX-models subject to missing data

Cited in

(18)

• Frequency domain sensitivity functions for continuous time systems under sampled data control
• Parameter estimation of Gaussian hidden Markov models when missing observations occur
• Exact credal treatment of missing data
• Dual time-frequency domain system identification
• Envelope method with ignorable missing data
• Robust maximum-likelihood estimation of multivariable dynamic systems
• Nonlinear Bayesian state filtering with missing measurements and bounded noise and its application to vehicle position estimation
• Identification of ARX-models subject to missing data
• Nonparametric Mean Estimation with Missing Data
• Fixed interval estimation in state space models when some of the data are missing or aggregated
• Estimation method of moving average model with missing data
• scientific article; zbMATH DE number 5280088 (Why is no real title available?)
• scientific article; zbMATH DE number 47164 (Why is no real title available?)
• scientific article; zbMATH DE number 7027972 (Why is no real title available?)
• Estimation for incomplete manpower data
• scientific article; zbMATH DE number 1833970 (Why is no real title available?)
• scientific article; zbMATH DE number 1834445 (Why is no real title available?)
• Estimating probability values from an incomplete dataset

This page was built for publication: Estimation with Missing Data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4700086)