On resampling and uncertainty estimation in linear system identification

DOI10.1016/j.automatica.2010.02.015zbMath1191.93136MaRDI QIDQ980906

Bitmead, Robert R., Simone Garatti

Publication date: 8 July 2010

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2010.02.015

zbMATH Keywords

bootstrap; system identification; Monte Carlo; resampling; model validation; subsampling

Mathematics Subject Classification ID

93C41: Control/observation systems with incomplete information

93E10: Estimation and detection in stochastic control theory

93E12: Identification in stochastic control theory

Related Items

A counterexample to the uniqueness of the asymptotic estimate in ARMAX model identification via the correlation approach, NN-adaptive output feedback tracking control for a class of discrete-time non-affine systems with a dynamic compensator

Uses Software

• bootstrap

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Assessing the quality of identified models through the asymptotic theory -- when is the result reliable?
• On covariance function tests used in system identification
• Mixing properties of ARMA processes
• Edgeworth correction by bootstrap in autoregressions
• Nonparametric statistics for stochastic processes. Estimation and prediction.
• Resampling methods for dependent data
• Large sample confidence regions based on subsamples under minimal assumptions
• The jackknife and bootstrap
• Estimation of model quality
• The asymptotic model quality assessment for instrumental variable identification revisited
• Guaranteed non-asymptotic confidence regions in system identification
• Computer-Intensive Methods in Statistical Regression
• Using the bootstrap to estimate the variance in the case of undermodeling
• Convergence of Distributions Generated by Stationary Stochastic Processes
• Bootstrap-based estimates of uncertainty in subspace identification methods