Analysis, detection and correction of misspecified discrete time state space models

DOI10.1016/J.CAM.2017.10.020zbMATH Open1377.93162arXiv1704.00587OpenAlexW2605486557MaRDI QIDQ679587FDOQ679587

Salima El Kolei, Frédéric Patras

Publication date: 11 January 2018

Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)

Abstract: Misspecifications (i.e. errors on the parameters) of state space models lead to incorrect inference of the hidden states. This paper studies weakly nonlin-ear state space models with additive Gaussian noises and proposes a method for detecting and correcting misspecifications. The latter induce a biased estimator of the hidden state but also happen to induce correlation on innovations and other residues. This property is used to find a well-defined objective function for which an optimisation routine is applied to recover the true parameters of the model. It is argued that this method can consistently estimate the bias on the parameter. We demonstrate the algorithm on various models of increasing complexity.

Full work available at URL: https://arxiv.org/abs/1704.00587

Recommendations

• GMM and misspecification correction for misspecified models with diverging number of parameters
• Stochastic model specification search for Gaussian and partial non-Gaussian state space models
• STABLE ALGORITHMS FOR THE STATE SPACE MODEL
• Sequential Change-Point Detection in State-Space Models
• The estimation of a state space model by estimating functions with an application

zbMATH Keywords

Kalman filterrobust estimationstate space modelsextended Kalman filtermisspecified modelsdiscrete time state space models

Mathematics Subject Classification ID

Filtering in stochastic control theory (93E11) Discrete-time control/observation systems (93C55) Estimation and detection in stochastic control theory (93E10)

Cites Work

• A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options
• Particle Markov Chain Monte Carlo Methods
• Time series analysis by state space methods.
• Title not available (Why is that?)
• Title not available (Why is that?)
• Kalman Filtering
• Title not available (Why is that?)
• On particle Gibbs sampling
• On particle Gibbs samplers
• The Accurate Continuous-Discrete Extended Kalman Filter for Radar Tracking

Cited In (4)

• LEAVE-K -OUT DIAGNOSTICS IN STATE-SPACE MODELS
• Detecting misspecifications in autoregressive conditional duration models and non-negative time-series processes
• Kalman filtering based gradient estimation algorithms for observer canonical state-space systems with moving average noises
• Parametric estimation of hidden Markov models by least squares type estimation and deconvolution

This page was built for publication: Analysis, detection and correction of misspecified discrete time state space models

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q679587)