Please use this identifier to cite or link to this item:
http://repositorio.unicamp.br/jspui/handle/REPOSIP/353252
Type: | Artigo |
Title: | Asymptotically efficient moment-based estimator of the Kappa Parameter for the Kappa - Mu distribution |
Author: | Oliveira Ribeiro, Antonio Marcelo Conforti, Evandro |
Abstract: | The kappa - mu distribution is a general fading model applied to predict multipath faded envelope in wireless channels, under a line-of-sight propagation condition. However, its algebraic moment-based estimator of the parameter kappa available in the literature depends on higher-order statistical moments, which impose a high penalty over the estimator efficiency. In this letter, we have proposed a new moment-based estimator of the parameter kappa, which depends on a simple average of the normalized envelope and takes advantage of lower estimation errors. We have proved that the proposed estimator is asymptotically efficient, from a practical point of view, since its normalized asymptotic variance closely attained the Cramer-Rao lower bound for the useful range of kappa. In addition, big sample size Monte Carlo simulations have revealed that the algebraic estimator is positively biased with a highly broad sample confidence region, in contrast to the almost unbiased proposed estimator with a much narrower sample confidence region. Furthermore, the proposed estimator yielded a much lower sample variance for the wide range of sample number when compared to the algebraic one |
Subject: | Teoria da estimativa Métodos MCMC (Estatística) |
Country: | Estados Unidos |
Editor: | Institute of Electrical and Electronics Engineers |
Rights: | Fechado |
Identifier DOI: | 10.1109/LAWP.2014.2372001 |
Address: | https://ieeexplore.ieee.org/document/6963311 |
Date Issue: | 2015 |
Appears in Collections: | FEEC - Artigos e Outros Documentos |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.