Exact Confidence Regions for Linear Regression Parameter under External Arbitrary Noise

被引:0
作者
Senov, Alexander [1 ]
Amelin, Konstantin [1 ]
Amelina, Natalia [1 ]
Granichin, Oleg [1 ]
机构
[1] St Petersburg State Univ, Dept Math & Mech, St Petersburg 198504, Russia
来源
2014 AMERICAN CONTROL CONFERENCE (ACC) | 2014年
关键词
MODELS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The paper propose new method for identifying non-asymptotic confidence regions for linear regression parameter under external arbitrary noise. This method called Modified Sign-Perturbed Sums (MSPS) method and it is a modification of previously proposed one, called Sign-Perturbed Sums which is applicable only in case of symmetrical centred noise. MSPS algorithm correctness and obtained confidence region convergence are proved theoretically under some additional assumptions. SPS and MSPS methods are compared basing on simulated data. Few advantages of MSPS method in case of biased and asymmetric noise are illustrated.
引用
收藏
页码:5097 / 5102
页数:6
相关论文
共 15 条
[1]  
Amelin K., 2013, IFAC Proceedings Volumes (IFAC-PapersOnline), V11, P205
[2]  
Amelin Konstantin, 2012, [Cybernetics and Physics, Cybernetics and Physics], V1, P79
[3]  
Amelin K, 2012, IEEE DECIS CONTR P, P2134, DOI 10.1109/CDC.2012.6426338
[4]  
Amelin K, 2012, P AMER CONTR CONF, P851
[5]  
[Anonymous], 2002, ROBASTNAYA USTOICHIV
[6]  
[Anonymous], 1999, SYSTEM IDENTIFICATIO
[7]   Bounded-error parameter estimation: Noise models and recursive algorithms [J].
Bai, EW ;
Nagpal, KM ;
Tempo, R .
AUTOMATICA, 1996, 32 (07) :985-999
[8]   Non-Asymptotic Confidence Sets for the Parameters of Linear Transfer Functions [J].
Campi, Marco C. ;
Weyer, Erik .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2010, 55 (12) :2708-2720
[9]  
Csaji Balazs Cs., 2012, P 16 IFAC S SYST ID, P227
[10]   Identification of approximated Hammerstein models in a worst-case setting [J].
Garulli, A ;
Giarrè, L ;
Zappa, G .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2002, 47 (12) :2046-2050