Bivariate generalized Poisson regression model: applications on health care data

Hossein Zamani, Pouya Faroughi, Noriszura Ismail

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

This paper introduces several forms of bivariate generalized Poisson regression model (BGPR) which can be fitted to bivariate and correlated count data with covariates. The main advantage of these forms of BGPR is that they are nested and thus they allow likelihood ratio tests to be performed to choose the best model. The BGPR can be fitted not only to bivariate count data with positive, zero, or negative correlations, but also to under- or overdispersed bivariate count data with flexible form of mean–variance relationship. Applications of several forms of the BGPR are illustrated on two sets of count data: the Australian health survey data and the US National Medical Expenditure Survey data.

Original languageEnglish
Pages (from-to)1-15
Number of pages15
JournalEmpirical Economics
DOIs
Publication statusAccepted/In press - 5 Jan 2016

Fingerprint

Poisson Regression
Poisson Model
Healthcare
Regression Model
health care
Count Data
regression
Survey Data
Correlated Data
Likelihood Ratio Test
Regression model
Count data
Poisson regression
expenditures
Covariates
Health
Choose
health
Form
Zero

Keywords

  • Bivariate
  • Correlation
  • Generalized Poisson
  • Overdispersion
  • Underdispersion

ASJC Scopus subject areas

  • Economics and Econometrics
  • Social Sciences (miscellaneous)
  • Mathematics (miscellaneous)
  • Statistics and Probability

Cite this

Bivariate generalized Poisson regression model : applications on health care data. / Zamani, Hossein; Faroughi, Pouya; Ismail, Noriszura.

In: Empirical Economics, 05.01.2016, p. 1-15.

Research output: Contribution to journalArticle

@article{d030b9f7b81043c9b5f036e608c244b1,
title = "Bivariate generalized Poisson regression model: applications on health care data",
abstract = "This paper introduces several forms of bivariate generalized Poisson regression model (BGPR) which can be fitted to bivariate and correlated count data with covariates. The main advantage of these forms of BGPR is that they are nested and thus they allow likelihood ratio tests to be performed to choose the best model. The BGPR can be fitted not only to bivariate count data with positive, zero, or negative correlations, but also to under- or overdispersed bivariate count data with flexible form of mean–variance relationship. Applications of several forms of the BGPR are illustrated on two sets of count data: the Australian health survey data and the US National Medical Expenditure Survey data.",
keywords = "Bivariate, Correlation, Generalized Poisson, Overdispersion, Underdispersion",
author = "Hossein Zamani and Pouya Faroughi and Noriszura Ismail",
year = "2016",
month = "1",
day = "5",
doi = "10.1007/s00181-015-1051-7",
language = "English",
pages = "1--15",
journal = "Empirical Economics",
issn = "0377-7332",
publisher = "Physica-Verlag",

}

TY - JOUR

T1 - Bivariate generalized Poisson regression model

T2 - applications on health care data

AU - Zamani, Hossein

AU - Faroughi, Pouya

AU - Ismail, Noriszura

PY - 2016/1/5

Y1 - 2016/1/5

N2 - This paper introduces several forms of bivariate generalized Poisson regression model (BGPR) which can be fitted to bivariate and correlated count data with covariates. The main advantage of these forms of BGPR is that they are nested and thus they allow likelihood ratio tests to be performed to choose the best model. The BGPR can be fitted not only to bivariate count data with positive, zero, or negative correlations, but also to under- or overdispersed bivariate count data with flexible form of mean–variance relationship. Applications of several forms of the BGPR are illustrated on two sets of count data: the Australian health survey data and the US National Medical Expenditure Survey data.

AB - This paper introduces several forms of bivariate generalized Poisson regression model (BGPR) which can be fitted to bivariate and correlated count data with covariates. The main advantage of these forms of BGPR is that they are nested and thus they allow likelihood ratio tests to be performed to choose the best model. The BGPR can be fitted not only to bivariate count data with positive, zero, or negative correlations, but also to under- or overdispersed bivariate count data with flexible form of mean–variance relationship. Applications of several forms of the BGPR are illustrated on two sets of count data: the Australian health survey data and the US National Medical Expenditure Survey data.

KW - Bivariate

KW - Correlation

KW - Generalized Poisson

KW - Overdispersion

KW - Underdispersion

UR - http://www.scopus.com/inward/record.url?scp=84953275685&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84953275685&partnerID=8YFLogxK

U2 - 10.1007/s00181-015-1051-7

DO - 10.1007/s00181-015-1051-7

M3 - Article

AN - SCOPUS:84953275685

SP - 1

EP - 15

JO - Empirical Economics

JF - Empirical Economics

SN - 0377-7332

ER -