Finite sample properties of linear model identification

被引:27
|
作者
Weyer, E [1 ]
Williamson, RC
Mareels, IMY
机构
[1] Univ Melbourne, Dept Elect & Elect Engn, Parkville, Vic 3052, Australia
[2] Australian Natl Univ, Dept Engn, Canberra, ACT 0200, Australia
基金
澳大利亚研究理事会;
关键词
ARX models; finite sample properties; FIR models; least squares system identification; risk minimization theory;
D O I
10.1109/9.774109
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 finite sample properties of prediction error methods using a quadratic criterion function for system identification. The problem we pose is: How many data points are required to guarantee with high probability that the expected value of the quadratic identification criterion is close to its empirical mean value? The sample sizes are obtained using risk minimization theory which provides uniform probabilistic bounds on the difference between the expected value of the squared prediction error and its empirical mean evaluated on a finite number of data points. The bounds are very general. No assumption is made about the true system belonging to the model class, and the noise sequence is not assumed to be uniformly bounded. Further analysis shows that in order to maintain a given bound on the deviation, the number of data points needed grows no faster than quadratically with the number of parameters for FIR and ARX models.
引用
收藏
页码:1370 / 1383
页数:14
相关论文
共 50 条
  • [31] THE EFFECT OF FINITE TEMPERATURE ON THE NUCLEON PROPERTIES IN THE EXTENDED LINEAR SIGMA MODEL
    Abu-Shady, M.
    INTERNATIONAL JOURNAL OF MODERN PHYSICS E, 2012, 21 (06):
  • [32] METAL-SURFACE PROPERTIES IN FINITE LINEAR POTENTIAL (FLP) MODEL
    MA, CQ
    FLAMHOLZ, JS
    SAHNI, V
    BULLETIN OF THE AMERICAN PHYSICAL SOCIETY, 1977, 22 (03): : 365 - 365
  • [33] Finite sample performance of linear least squares estimation
    Krikheli, Michael
    Leshem, Amir
    JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS, 2021, 358 (15): : 7955 - 7991
  • [35] Finite Sample Analysis for Structured Discrete System Identification
    Xie, Xiaotian
    Katselis, Dimitrios
    Beck, Carolyn L.
    Srikant, R.
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2023, 68 (10) : 6345 - 6352
  • [36] Finite sample properties of the QMLE for the Log-ACD model: Application to Australian stocks
    Allen, David
    Chan, Felix
    McAleer, Michael
    Peiris, Shelton
    JOURNAL OF ECONOMETRICS, 2008, 147 (01) : 163 - 185
  • [37] Finite time identification in unstable linear systems
    Faradonbeh, Mohamad Kazem Shirani
    Tewari, Ambuj
    Michailidis, George
    AUTOMATICA, 2018, 96 : 342 - 353
  • [38] Nucleon properties in the quantized linear sigma model at finite temperature and chemical potential
    Abu-Shady, M.
    Mansour, H. M.
    JOURNAL OF PHYSICS G-NUCLEAR AND PARTICLE PHYSICS, 2016, 43 (02)
  • [39] Exact finite-sample bias and MSE reduction in a simple linear regression model with measurement error
    Hisayuki Tsukuma
    Japanese Journal of Statistics and Data Science, 2019, 2 : 1 - 29
  • [40] A Finite-sample bias correction method for general linear model in the presence of differential measurement errors
    Al-Sharadqah, Ali
    Bagdasaryan, Karine
    Nusierat, Ola
    ASTA-ADVANCES IN STATISTICAL ANALYSIS, 2025, 109 (01) : 149 - 195