Construction of bivariate and multivariate weighted distributions via conditioning

Barry C. Arnold, Indranil Ghosh, Ayman Alzaatreh

Research output: Contribution to journalArticle

Abstract

Weighted distributions (univariate and bivariate) have received widespread attention over the last two decades because of their flexibility for analyzing skewed data. In this article, we propose an alternative method to construct a new family of bivariate and multivariate weighted distributions. For illustrative purposes, some examples of the proposed method are presented. Several structural properties of the bivariate weighted distributions including marginal distributions together with distributions of the minimum and maximum, evaluation of the reliability parameter, and verification of total positivity of order two are also presented. In addition, we provide some multivariate extensions of the proposed models. A real-life data set is used to show the applicability of these bivariate weighted distributions.

Original languageEnglish
Pages (from-to)8897-8912
Number of pages16
JournalCommunications in Statistics - Theory and Methods
Volume46
Issue number18
DOIs
Publication statusPublished - Sep 17 2017

Fingerprint

Weighted Distributions
Multivariate Distribution
Conditioning
Bivariate Distribution
Total Positivity
Marginal Distribution
Structural Properties
Univariate
Flexibility
Alternatives
Evaluation

Keywords

  • Bivariate weighted Pareto II distribution
  • increasing and decreasing failure rate
  • Laplace transform
  • multivariate weighted Pareto II distribution
  • total positivity of order two
  • weighted distributions

ASJC Scopus subject areas

  • Statistics and Probability

Cite this

Construction of bivariate and multivariate weighted distributions via conditioning. / Arnold, Barry C.; Ghosh, Indranil; Alzaatreh, Ayman.

In: Communications in Statistics - Theory and Methods, Vol. 46, No. 18, 17.09.2017, p. 8897-8912.

Research output: Contribution to journalArticle

@article{41e2c8ccab75489f978db4b418d4fe90,
title = "Construction of bivariate and multivariate weighted distributions via conditioning",
abstract = "Weighted distributions (univariate and bivariate) have received widespread attention over the last two decades because of their flexibility for analyzing skewed data. In this article, we propose an alternative method to construct a new family of bivariate and multivariate weighted distributions. For illustrative purposes, some examples of the proposed method are presented. Several structural properties of the bivariate weighted distributions including marginal distributions together with distributions of the minimum and maximum, evaluation of the reliability parameter, and verification of total positivity of order two are also presented. In addition, we provide some multivariate extensions of the proposed models. A real-life data set is used to show the applicability of these bivariate weighted distributions.",
keywords = "Bivariate weighted Pareto II distribution, increasing and decreasing failure rate, Laplace transform, multivariate weighted Pareto II distribution, total positivity of order two, weighted distributions",
author = "Arnold, {Barry C.} and Indranil Ghosh and Ayman Alzaatreh",
year = "2017",
month = "9",
day = "17",
doi = "10.1080/03610926.2016.1197256",
language = "English",
volume = "46",
pages = "8897--8912",
journal = "Communications in Statistics - Theory and Methods",
issn = "0361-0926",
publisher = "Taylor and Francis",
number = "18",

}

TY - JOUR

T1 - Construction of bivariate and multivariate weighted distributions via conditioning

AU - Arnold, Barry C.

AU - Ghosh, Indranil

AU - Alzaatreh, Ayman

PY - 2017/9/17

Y1 - 2017/9/17

N2 - Weighted distributions (univariate and bivariate) have received widespread attention over the last two decades because of their flexibility for analyzing skewed data. In this article, we propose an alternative method to construct a new family of bivariate and multivariate weighted distributions. For illustrative purposes, some examples of the proposed method are presented. Several structural properties of the bivariate weighted distributions including marginal distributions together with distributions of the minimum and maximum, evaluation of the reliability parameter, and verification of total positivity of order two are also presented. In addition, we provide some multivariate extensions of the proposed models. A real-life data set is used to show the applicability of these bivariate weighted distributions.

AB - Weighted distributions (univariate and bivariate) have received widespread attention over the last two decades because of their flexibility for analyzing skewed data. In this article, we propose an alternative method to construct a new family of bivariate and multivariate weighted distributions. For illustrative purposes, some examples of the proposed method are presented. Several structural properties of the bivariate weighted distributions including marginal distributions together with distributions of the minimum and maximum, evaluation of the reliability parameter, and verification of total positivity of order two are also presented. In addition, we provide some multivariate extensions of the proposed models. A real-life data set is used to show the applicability of these bivariate weighted distributions.

KW - Bivariate weighted Pareto II distribution

KW - increasing and decreasing failure rate

KW - Laplace transform

KW - multivariate weighted Pareto II distribution

KW - total positivity of order two

KW - weighted distributions

UR - http://www.scopus.com/inward/record.url?scp=85019566820&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85019566820&partnerID=8YFLogxK

U2 - 10.1080/03610926.2016.1197256

DO - 10.1080/03610926.2016.1197256

M3 - Article

VL - 46

SP - 8897

EP - 8912

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

SN - 0361-0926

IS - 18

ER -