Guaranteed non-asymptotic confidence regions in system identification

被引：80

作者：

Campi, MC

Weyer, E ^{[1
]}

机构：

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

[2] Univ Brescia, Dept Elect Engn & Automat, I-25123 Brescia, Italy

来源：

AUTOMATICA | 2005年 / 41卷 / 10期

关键词：

confidence sets; uncertainty evaluation; general linear models; finite sample results; system identification;

D O I：

10.1016/j.automatica.2005.05.005

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper we consider the problem of constructing confidence regions for the parameters of identified models of dynamical systems. Taking a major departure from the previous literature on the subject, we introduce a new approach called 'Leave-out Sign-dominant Correlation Regions' (LSCR) which delivers confidence regions with guaranteed probability. All results hold rigorously true for any finite number of data points and no asymptotic theory is involved. Moreover, prior knowledge on the noise affecting the data is reduced to a minimum. The approach is illustrated on several simulation examples, showing that it delivers practically useful confidence sets with guaranteed probabilities. (c) 2005 Elsevier Ltd. All rights reserved.

引用

页码：1751 / 1764

页数：14

共 25 条

[1] Bounded-error parameter estimation: Noise models and recursive algorithms [J].