A higher order correlation unscented Kalman filter

DOI10.1016/J.AMC.2013.03.019zbMATH Open1287.93093arXiv1207.4300OpenAlexW2963462742MaRDI QIDQ2453299FDOQ2453299

Authors: Oliver Grothe 

Publication date: 6 June 2014

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

Abstract: Many nonlinear extensions of the Kalman filter, e.g., the extended and the unscented Kalman filter, reduce the state densities to Gaussian densities. This approximation gives sufficient results in many cases. However, this filters only estimate states that are correlated with the observation. Therefore, sequential estimation of diffusion parameters, e.g., volatility, which are not correlated with the observations is not possible. While other filters overcome this problem with simulations, we extend the measurement update of the Gaussian two-moment filters by a higher order correlation measurement update. We explicitly state formulas for a higher order unscented Kalman filter within a continuous-discrete state space. We demonstrate the filter in the context of parameter estimation of an Ornstein-Uhlenbeck process.

Full work available at URL: https://arxiv.org/abs/1207.4300

Recommendations

• A high order unscented Kalman filtering method
• THE UNSCENTED KALMAN FILTER, A POWERFUL TOOL FOR DATA ANALYSIS
• High-order filters for estimation in non-Gaussian noise
• Nonlinear estimation applying an unscented transformation in systems with correlated uncertain observations
• Higher order sigma point filter: a new heuristic for nonlinear time series filtering

zbMATH Keywords

nonlinear systemsvolatility estimationunscented Kalman filtercontinuous-discrete state spaceestimation of uncorrelated statessequential parameter estimation

Mathematics Subject Classification ID

Filtering in stochastic control theory (93E11) Estimation and detection in stochastic control theory (93E10)

Cites Work

• A theory of the term structure of interest rates
• Stochastic processes and filtering theory
• Title not available (Why is that?)
• Filtering via Simulation: Auxiliary Particle Filters
• On linear and quadratic estimating functions
• An extension of quasi-likelihood estimation
• Quasi-likelihood models and optimal inference
• Electricity prices and power derivatives: evidence from the Nordic Power Exchange
• Title not available (Why is that?)
• Different approaches for state filtering in nonlinear systems with uncertain observations
• Filtering via estimating functions
• Filtering and Smoothing Via Estimating Functions
• Nonlinear continuous-discrete filtering using kernel density estimatesand functional integrals
• On combining quasi-likelihood estimating functions
• Construction of fully symmetric numerical integration formulas

Cited In (6)

• Maximum correntropy unscented Kalman and information filters for non-Gaussian measurement noise
• Volatility research based on the modified unscented Kalman filter
• Higher order sigma point filter: a new heuristic for nonlinear time series filtering
• A robust meta-heuristic adaptive Bi-CGSTAB algorithm to online estimation of a three DoF state-space model in the presence of disturbance and uncertainty
• A high order unscented Kalman filtering method
• Recursive and iterative least squares parameter estimation algorithms for observability canonical state space systems

This page was built for publication: A higher order correlation unscented Kalman filter

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2453299)