Fitting the generalized logistic distribution by LQ-Moments

Ani Shabri, Abdul Aziz Jemain

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The method of LQ-moments (LQMOM) for estimating parameters and quantiles of the Generalized Logistic (GL) distribution are introduced. We explore and extend class of LQMOM with consideration combinations of p and α values in the range 0 and 0.5. The popular quantile estimator namely the weighted kernel quantile (WKQ) estimator is proposed to estimate the quantile function. A comparison of these methods is done by simulation. The performances of the proposed estimators of the GL distribution was compared with the estimators based on L-moments for various sample sizes and return periods. The overall results show the LQMOM provides better results only for small or moderate sample size.

Original languageEnglish
Pages (from-to)2663-2676
Number of pages14
JournalApplied Mathematical Sciences
Volume5
Issue number53-56
Publication statusPublished - 2011

Fingerprint

Logistics/distribution
Logistics
Quantile
Moment
Estimator
Method of moments
Sample Size
L-moments
Quantile Function
kernel
Estimate
Range of data
Simulation

Keywords

  • L-moments
  • LQ-moments
  • Quick estimator
  • The weighted kernel quantile

ASJC Scopus subject areas

  • Applied Mathematics

Cite this

Fitting the generalized logistic distribution by LQ-Moments. / Shabri, Ani; Jemain, Abdul Aziz.

In: Applied Mathematical Sciences, Vol. 5, No. 53-56, 2011, p. 2663-2676.

Research output: Contribution to journalArticle

@article{d174dfb901804881830d8fec66db1b2b,
title = "Fitting the generalized logistic distribution by LQ-Moments",
abstract = "The method of LQ-moments (LQMOM) for estimating parameters and quantiles of the Generalized Logistic (GL) distribution are introduced. We explore and extend class of LQMOM with consideration combinations of p and α values in the range 0 and 0.5. The popular quantile estimator namely the weighted kernel quantile (WKQ) estimator is proposed to estimate the quantile function. A comparison of these methods is done by simulation. The performances of the proposed estimators of the GL distribution was compared with the estimators based on L-moments for various sample sizes and return periods. The overall results show the LQMOM provides better results only for small or moderate sample size.",
keywords = "L-moments, LQ-moments, Quick estimator, The weighted kernel quantile",
author = "Ani Shabri and Jemain, {Abdul Aziz}",
year = "2011",
language = "English",
volume = "5",
pages = "2663--2676",
journal = "Applied Mathematical Sciences",
issn = "1312-885X",
publisher = "Hikari Ltd.",
number = "53-56",

}

TY - JOUR

T1 - Fitting the generalized logistic distribution by LQ-Moments

AU - Shabri, Ani

AU - Jemain, Abdul Aziz

PY - 2011

Y1 - 2011

N2 - The method of LQ-moments (LQMOM) for estimating parameters and quantiles of the Generalized Logistic (GL) distribution are introduced. We explore and extend class of LQMOM with consideration combinations of p and α values in the range 0 and 0.5. The popular quantile estimator namely the weighted kernel quantile (WKQ) estimator is proposed to estimate the quantile function. A comparison of these methods is done by simulation. The performances of the proposed estimators of the GL distribution was compared with the estimators based on L-moments for various sample sizes and return periods. The overall results show the LQMOM provides better results only for small or moderate sample size.

AB - The method of LQ-moments (LQMOM) for estimating parameters and quantiles of the Generalized Logistic (GL) distribution are introduced. We explore and extend class of LQMOM with consideration combinations of p and α values in the range 0 and 0.5. The popular quantile estimator namely the weighted kernel quantile (WKQ) estimator is proposed to estimate the quantile function. A comparison of these methods is done by simulation. The performances of the proposed estimators of the GL distribution was compared with the estimators based on L-moments for various sample sizes and return periods. The overall results show the LQMOM provides better results only for small or moderate sample size.

KW - L-moments

KW - LQ-moments

KW - Quick estimator

KW - The weighted kernel quantile

UR - http://www.scopus.com/inward/record.url?scp=80755143428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80755143428&partnerID=8YFLogxK

M3 - Article

VL - 5

SP - 2663

EP - 2676

JO - Applied Mathematical Sciences

JF - Applied Mathematical Sciences

SN - 1312-885X

IS - 53-56

ER -