Parameter estimation of the Pareto distribution using a pivotal quantity

Joseph H.T. Kim, Sanghyun Ahn, Soohan Ahn

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

In estimating the parameters of the two-parameter Pareto distribution it is well known that the performance of the maximum likelihood estimator deteriorates when sample sizes are small or the underlying model is contaminated. In this paper we propose a new parameter estimator that utilizes a pivotal quantity based on the regression framework, allowing separate estimation of the two parameters in a straightforward manner. The consistency of the estimator is also established. Simulation studies show that the proposed estimator is a competitive, well-rounded robust estimator for both Pareto and contaminated Pareto datasets when the sample sizes are small.

Original languageEnglish
Pages (from-to)438-450
Number of pages13
JournalJournal of the Korean Statistical Society
Volume46
Issue number3
DOIs
Publication statusPublished - 2017 Sep 1

Fingerprint

Pivotal Quantity
Pareto Distribution
Parameter Estimation
Pareto
Estimator
Two Parameters
Sample Size
Robust Estimators
Maximum Likelihood Estimator
Regression
Simulation Study
Model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability

Cite this

@article{2a961f69907e498480693309abd2c684,
title = "Parameter estimation of the Pareto distribution using a pivotal quantity",
abstract = "In estimating the parameters of the two-parameter Pareto distribution it is well known that the performance of the maximum likelihood estimator deteriorates when sample sizes are small or the underlying model is contaminated. In this paper we propose a new parameter estimator that utilizes a pivotal quantity based on the regression framework, allowing separate estimation of the two parameters in a straightforward manner. The consistency of the estimator is also established. Simulation studies show that the proposed estimator is a competitive, well-rounded robust estimator for both Pareto and contaminated Pareto datasets when the sample sizes are small.",
author = "Kim, {Joseph H.T.} and Sanghyun Ahn and Soohan Ahn",
year = "2017",
month = "9",
day = "1",
doi = "10.1016/j.jkss.2017.01.004",
language = "English",
volume = "46",
pages = "438--450",
journal = "Journal of the Korean Statistical Society",
issn = "1226-3192",
publisher = "Korean Statistical Society",
number = "3",

}

Parameter estimation of the Pareto distribution using a pivotal quantity. / Kim, Joseph H.T.; Ahn, Sanghyun; Ahn, Soohan.

In: Journal of the Korean Statistical Society, Vol. 46, No. 3, 01.09.2017, p. 438-450.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Parameter estimation of the Pareto distribution using a pivotal quantity

AU - Kim, Joseph H.T.

AU - Ahn, Sanghyun

AU - Ahn, Soohan

PY - 2017/9/1

Y1 - 2017/9/1

N2 - In estimating the parameters of the two-parameter Pareto distribution it is well known that the performance of the maximum likelihood estimator deteriorates when sample sizes are small or the underlying model is contaminated. In this paper we propose a new parameter estimator that utilizes a pivotal quantity based on the regression framework, allowing separate estimation of the two parameters in a straightforward manner. The consistency of the estimator is also established. Simulation studies show that the proposed estimator is a competitive, well-rounded robust estimator for both Pareto and contaminated Pareto datasets when the sample sizes are small.

AB - In estimating the parameters of the two-parameter Pareto distribution it is well known that the performance of the maximum likelihood estimator deteriorates when sample sizes are small or the underlying model is contaminated. In this paper we propose a new parameter estimator that utilizes a pivotal quantity based on the regression framework, allowing separate estimation of the two parameters in a straightforward manner. The consistency of the estimator is also established. Simulation studies show that the proposed estimator is a competitive, well-rounded robust estimator for both Pareto and contaminated Pareto datasets when the sample sizes are small.

UR - http://www.scopus.com/inward/record.url?scp=85011547328&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011547328&partnerID=8YFLogxK

U2 - 10.1016/j.jkss.2017.01.004

DO - 10.1016/j.jkss.2017.01.004

M3 - Article

AN - SCOPUS:85011547328

VL - 46

SP - 438

EP - 450

JO - Journal of the Korean Statistical Society

JF - Journal of the Korean Statistical Society

SN - 1226-3192

IS - 3

ER -