On the estimation of the K parameter for the rice fading distribution

Ali Abdi, Cihan Tepedelenlioglu, Mostafa Kaveh, Georgios Giannakis

Research output: Contribution to journalArticle

193 Citations (Scopus)

Abstract

In this letter we study the statistical performance of two moment-based estimators for the K parameter of Rice fading distribution, as less complex alternatives to the maximum-likelihood estimator. Our asymptotic analysis reveals that both estimators are nearly asymptotically efficient, and that there is a compromise between the computational simplicity and the statistical efficiency of these two estimators. We also show, by Monte Carlo simulation, that the fading correlation among the envelope samples deteriorates the performance of both estimators. However, the simpler estimator, which employs the second and the fourth moments of the signal envelope, appears to be more suitable for real-world applications.

Original languageEnglish (US)
Pages (from-to)92-94
Number of pages3
JournalIEEE Communications Letters
Volume5
Issue number3
DOIs
StatePublished - Mar 2001
Externally publishedYes

Fingerprint

Asymptotic analysis
Fading
Maximum likelihood
Estimator
Envelope
Moment
Real-world Applications
Asymptotic Analysis
Maximum Likelihood Estimator
Simplicity
Monte Carlo Simulation
Rice
Monte Carlo simulation
Alternatives

Keywords

  • Asymptotic analysis
  • Fading channels
  • Maximum likelihood
  • Method of moments
  • Monte Carlo simulation
  • Parameter estimation
  • Rice distribution

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

On the estimation of the K parameter for the rice fading distribution. / Abdi, Ali; Tepedelenlioglu, Cihan; Kaveh, Mostafa; Giannakis, Georgios.

In: IEEE Communications Letters, Vol. 5, No. 3, 03.2001, p. 92-94.

Research output: Contribution to journalArticle

Abdi, Ali ; Tepedelenlioglu, Cihan ; Kaveh, Mostafa ; Giannakis, Georgios. / On the estimation of the K parameter for the rice fading distribution. In: IEEE Communications Letters. 2001 ; Vol. 5, No. 3. pp. 92-94.
@article{ac0dab8be77947b293376e87b87c229f,
title = "On the estimation of the K parameter for the rice fading distribution",
abstract = "In this letter we study the statistical performance of two moment-based estimators for the K parameter of Rice fading distribution, as less complex alternatives to the maximum-likelihood estimator. Our asymptotic analysis reveals that both estimators are nearly asymptotically efficient, and that there is a compromise between the computational simplicity and the statistical efficiency of these two estimators. We also show, by Monte Carlo simulation, that the fading correlation among the envelope samples deteriorates the performance of both estimators. However, the simpler estimator, which employs the second and the fourth moments of the signal envelope, appears to be more suitable for real-world applications.",
keywords = "Asymptotic analysis, Fading channels, Maximum likelihood, Method of moments, Monte Carlo simulation, Parameter estimation, Rice distribution",
author = "Ali Abdi and Cihan Tepedelenlioglu and Mostafa Kaveh and Georgios Giannakis",
year = "2001",
month = "3",
doi = "10.1109/4234.913150",
language = "English (US)",
volume = "5",
pages = "92--94",
journal = "IEEE Communications Letters",
issn = "1089-7798",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - On the estimation of the K parameter for the rice fading distribution

AU - Abdi, Ali

AU - Tepedelenlioglu, Cihan

AU - Kaveh, Mostafa

AU - Giannakis, Georgios

PY - 2001/3

Y1 - 2001/3

N2 - In this letter we study the statistical performance of two moment-based estimators for the K parameter of Rice fading distribution, as less complex alternatives to the maximum-likelihood estimator. Our asymptotic analysis reveals that both estimators are nearly asymptotically efficient, and that there is a compromise between the computational simplicity and the statistical efficiency of these two estimators. We also show, by Monte Carlo simulation, that the fading correlation among the envelope samples deteriorates the performance of both estimators. However, the simpler estimator, which employs the second and the fourth moments of the signal envelope, appears to be more suitable for real-world applications.

AB - In this letter we study the statistical performance of two moment-based estimators for the K parameter of Rice fading distribution, as less complex alternatives to the maximum-likelihood estimator. Our asymptotic analysis reveals that both estimators are nearly asymptotically efficient, and that there is a compromise between the computational simplicity and the statistical efficiency of these two estimators. We also show, by Monte Carlo simulation, that the fading correlation among the envelope samples deteriorates the performance of both estimators. However, the simpler estimator, which employs the second and the fourth moments of the signal envelope, appears to be more suitable for real-world applications.

KW - Asymptotic analysis

KW - Fading channels

KW - Maximum likelihood

KW - Method of moments

KW - Monte Carlo simulation

KW - Parameter estimation

KW - Rice distribution

UR - http://www.scopus.com/inward/record.url?scp=0035273711&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035273711&partnerID=8YFLogxK

U2 - 10.1109/4234.913150

DO - 10.1109/4234.913150

M3 - Article

AN - SCOPUS:0035273711

VL - 5

SP - 92

EP - 94

JO - IEEE Communications Letters

JF - IEEE Communications Letters

SN - 1089-7798

IS - 3

ER -