Non-Asymptotic Confidence Regions for Errors-In-Variables Systems

被引：8

作者：

Khorasani, Masoud Moravej ^{[1
]}

Weyer, Erik ^{[1
]}

机构：

[1] Univ Melbourne, Dept Elect & Elect Engn, Melbourne, Vic 3010, Australia

来源：

IFAC PAPERSONLINE | 2018年 / 51卷 / 15期

关键词：

system identification; confidence regions; errors-in-variable; finite sample results; joint-output method; IDENTIFICATION; PARAMETERS; QUALITY; MODELS;

D O I：

10.1016/j.ifacol.2018.09.060

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

This paper deals with constructing non-asymptotic confidence regions for Errors In-Variables (EIV) systems when there is noise on both the input and the output signal. The Leave-out Sign-dominant Correlation Regions (LSCR) approach originally devised for systems with no noise on the input is extended to EIV systems. The correlation functions used in LSCR for EIV systems are computed using elements of an innovation vector which is obtained from a state space model of the system where also the input is regarded as an output. As with standard LSCR, the confidence regions are guaranteed to contain the true parameter with a user chosen probability for any finite number of data points. Moreover, the confidence region shrinks around the true parameter when the number of data points increases. The method and its properties are illustrated in a simulation example. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

引用

页码：1020 / 1025

页数：6

共 50 条

[31] Recursive Quantile Estimation: Non-Asymptotic Confidence Bounds
Chen, Likai
Keilbar, Georg
Wu, Wei Biao
JOURNAL OF MACHINE LEARNING RESEARCH, 2023, 24
[32] ADAPTIVE NON-ASYMPTOTIC CONFIDENCE BALLS IN DENSITY ESTIMATION
Lerasle, Matthieu
ESAIM-PROBABILITY AND STATISTICS, 2012, 16 : 61 - 85
[33] Universal, Non-asymptotic Confidence Sets for Circular Means
Hotz, Thomas
Kelma, Florian
Wieditz, Johannes
GEOMETRIC SCIENCE OF INFORMATION, GSI 2015, 2015, 9389 : 635 - 642
[34] ON ASYMPTOTIC NORMALITY OF PARAMETERS IN MULTIPLE LINEAR ERRORS-IN-VARIABLES MODEL
ZHANG Sanguo(Hua Loo-Keng Institute for Applied Mathematics and Information Science
Department of Mathematics
Journal of Systems Science & Complexity, 2003, (04) : 438 - 445
[35] Perspectives on errors-in-variables estimation for dynamic systems
Söderström, T
Soverini, U
Mahata, K
SIGNAL PROCESSING, 2002, 82 (08) : 1139 - 1154
[36] On non-asymptotic observation of nonlinear systems
Reger, Johann
Ramirez, Hebertt Sira
Fliess, Michel
2005 44th IEEE Conference on Decision and Control & European Control Conference, Vols 1-8, 2005, : 4219 - 4224
[37] Recursive identification of errors-in-variables Wiener systems
Mu, Bi-Qiang
Chen, Han-Fu
AUTOMATICA, 2013, 49 (09) : 2744 - 2753
[38] Recursive identification for multivariate errors-in-variables systems
Chen, Han-Fu
AUTOMATICA, 2007, 43 (07) : 1234 - 1242
[39] Perspectives on errors-in-variables estimation for dynamic systems
Södertröm, T
Soverini, U
Mahata, K
TOTAL LEAST SQUARES AND ERRORS-IN-VARIABLES MODELING: ANALYSIS, ALGORITHMS AND APPLICATIONS, 2002, : 271 - 280
[40] A new confidence interval in errors-in-variables model with known error variance
Yan, Liang
Wang, Rui
Xu, Xingzhong
JOURNAL OF APPLIED STATISTICS, 2017, 44 (12) : 2204 - 2221

← 1 2 3 4 5 →