Choice of weighting for averaged nonparametric transfer function estimates

William P. Heath

doi:10.1109/TAC.2007.906216

Choice of weighting for averaged nonparametric transfer function estimates

Research output: Contribution to journal › Article › peer-review

Abstract

The statistical properties of nonparametric transfer function estimates formed via the weighted sum of Empirical Transfer Function Estimates are considered. In the case that the system input is considered deterministic, it is shown that the weighting corresponding to the classical averaged periodogram estimate is optimal. A similar asymptotic result is derived for the case where the input is considered stochastic. © 2007 IEEE.

Original language	English
Pages (from-to)	1914-1920
Number of pages	6
Journal	IEEE Transactions on Automatic Control
Volume	52
Issue number	10
DOIs	https://doi.org/10.1109/TAC.2007.906216
Publication status	Published - Oct 2007

Keywords

Frequency response
Nonparametric identification
Spectral estimation

Access to Document

10.1109/TAC.2007.906216

Cite this

@article{5080ed5142e64e0bab7a7cab371c8fa4,

title = "Choice of weighting for averaged nonparametric transfer function estimates",

abstract = "The statistical properties of nonparametric transfer function estimates formed via the weighted sum of Empirical Transfer Function Estimates are considered. In the case that the system input is considered deterministic, it is shown that the weighting corresponding to the classical averaged periodogram estimate is optimal. A similar asymptotic result is derived for the case where the input is considered stochastic. {\textcopyright} 2007 IEEE.",

keywords = "Frequency response, Nonparametric identification, Spectral estimation",

author = "Heath, {William P.}",

year = "2007",

month = oct,

doi = "10.1109/TAC.2007.906216",

language = "English",

volume = "52",

pages = "1914--1920",

journal = "IEEE Transactions on Automatic Control",

issn = "1558-2523",

publisher = "IEEE",

number = "10",

}

TY - JOUR

T1 - Choice of weighting for averaged nonparametric transfer function estimates

AU - Heath, William P.

PY - 2007/10

Y1 - 2007/10

N2 - The statistical properties of nonparametric transfer function estimates formed via the weighted sum of Empirical Transfer Function Estimates are considered. In the case that the system input is considered deterministic, it is shown that the weighting corresponding to the classical averaged periodogram estimate is optimal. A similar asymptotic result is derived for the case where the input is considered stochastic. © 2007 IEEE.

AB - The statistical properties of nonparametric transfer function estimates formed via the weighted sum of Empirical Transfer Function Estimates are considered. In the case that the system input is considered deterministic, it is shown that the weighting corresponding to the classical averaged periodogram estimate is optimal. A similar asymptotic result is derived for the case where the input is considered stochastic. © 2007 IEEE.

KW - Frequency response

KW - Nonparametric identification

KW - Spectral estimation

U2 - 10.1109/TAC.2007.906216

DO - 10.1109/TAC.2007.906216

M3 - Article

SN - 1558-2523

SN - 2334-3303

VL - 52

SP - 1914

EP - 1920

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

IS - 10

ER -

Choice of weighting for averaged nonparametric transfer function estimates

Abstract

Keywords

Access to Document

Fingerprint

Cite this