Non-asymptotic confidence ellipsoids for the least-squares estimate

DOI10.1016/S0005-1098(02)00064-XMaRDI QIDQ1614424zbMATH OpenFDO

Authors Erik Weyer, M. C. Campi

Publication date 5 September 2002

Published in Automatica (Search for Journal in Brave)

zbMATH Keywords

least squaressystem identificationfinite sample propertiesconfidence ellipsoidsnon-asymptotic confidence ellipsoids

Mathematics Subject Classification ID

Identification in stochastic control theory (93E12) Least squares and related methods for stochastic control systems (93E24)

Recommendations

• Asymptotic properties of SPS confidence regions
• Guaranteed non-asymptotic confidence regions in system identification
• Non-asymptotic confidence regions for the parameters of EIV systems
• A stopping rule for least-squares identification
• Conservative confidence ellipsoids for linear model parameters

Cites work

• Finite sample properties of linear model identification
• Finite sample properties of system identification methods
• Finite sample properties of system identification of ARX models under mixing conditions
• Nonparametric statistics for stochastic processes. Estimation and prediction.
• On covariance function tests used in system identification

Cited in

(12)

• Non-asymptotic quality assessment of generalised FIR models with periodic inputs
• From experiment design to closed-loop control
• scientific article; zbMATH DE number 2063711 (Why is no real title available?)
• Confidence ellipsoids for regression coefficients by observations from a mixture
• A combined MAP and Bayesian scheme for finite data and/or moving horizon estimation
• Stochastic approach to the comparison of ellipsoidal and interval estimates
• Nonasymptotic confidence sets of prescribed dimensions for parameters of nonlinear regressions
• Assessing the quality of identified models through the asymptotic theory -- when is the result reliable?
• Identification of linear systems with multiplicative noise from multiple trajectory data
• Non-asymptotic confidence regions for model parameters in the presence of unmodelled dynamics
• Guaranteed non-asymptotic confidence regions in system identification
• Confidence ellipsoids based on a general family of shrinkage estimators for a linear model with non-spherical disturbances

This page was built for publication: Non-asymptotic confidence ellipsoids for the least-squares estimate

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1614424)