Melola Discovery

← Melola Discovery

Jurnal

Pemodelan Regresi Zero Inflated Negative Binomial pada Data yang Mengalami Overdispersi

ESTIMASI: Journal of Statistics and Its Application · Vol. 6 No. 1 (2025) · pp. 10–20

DOI
10.20956/ejsa.v6i1.21037
ISSN
2721-379X, 2721-3803
Published
2025-02-17
Publisher
Hasanuddin University
Language
en

Abstract

Poisson regression is a nonlinear regression model with the response variables in the form of discrete data and Poisson distribution. Data analysis using Poisson regression must meet assumptions such as the variance value and the average value of the response variables have the same value. However, in its application, overdispersion often occurs, namely the variance value is greater than the average value. Overdispersion in Poisson regression can occur because of the number of zero observations on the response variable. Data with zero excess and overdispersion are more suitable for using ZINB regression. The ZINB regression model is a model formed from the mixed distribution of the Poisson gamma. The ZINB regression model parameters were estimated using the MLE method with the EM algorithm. This study was applied to data on the number of neonatal deaths in Makassar City in 2018. The results of testing the ZINB regression model parameters showed that the predictor variable that had a partially significant effect was the number of newborns with low birth weight.

Keywords

Collaboration network of the authors

28 authors · 62 co-authorship links

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Sultan Ageng Tirtayasa University
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Sitti SahrimanAffiliation unknown4
Nirwan IlyasAffiliation unknown2
Raupong RaupongAffiliation unknown2
Fitriatusakiah FitriatusakiahAffiliation unknown2
Rusydah KhaeratiAffiliation unknown1
Dwicahyo Ramadhan PriyatnaAffiliation unknown1
Grace Oktavia YusufAffiliation unknown1
Andi Tenri Riski AmaliaAffiliation unknown1
Georgina Maria TinungkiAffiliation unknown1
Andi Isna YunitaAffiliation unknown1
Ririn AriantiAffiliation unknown1
Muhammad IdmanAffiliation unknown1
Anisa AnisaSultan Ageng Tirtayasa University1
Najiha AlimatunAffiliation unknown1
Nasrah SirajangAffiliation unknown1
Reski AmalahAffiliation unknown1
Nur Fuadil Maqnun WahabAffiliation unknown1
Nurtit SunusiAffiliation unknown1
Anisa Haura Salsa Fatih YusufAffiliation unknown1
Nurtiti SunusiAffiliation unknown1
Ika Pratiwi HayaAffiliation unknown1
Anna IslamiyatiAffiliation unknown1
Andi Ummi Melin Aicha AichaAffiliation unknown1
Wa Ode Sitti Amni AmniAffiliation unknown1
Amalia AndrianingrumAffiliation unknown1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) https://journal.unhas.ac.id/index.php/ESTIMASI/oai, first harvested 2 Nov 2026, last seen 2 Nov 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Pemodelan Regresi Zero Inflated Negative Binomial pada Data yang Mengalami Overdispersi</dc:title>
	<dc:creator xml:lang="en">Fajri, Ainul</dc:creator>
	<dc:creator xml:lang="en">Jaya, Andi Kresna</dc:creator>
	<dc:creator xml:lang="en">Talangko, La Podje</dc:creator>
	<dc:subject xml:lang="en">Overdispersion</dc:subject>
	<dc:subject xml:lang="en">Neonatal Mortality</dc:subject>
	<dc:subject xml:lang="en">ZINB Regression</dc:subject>
	<dc:subject xml:lang="en">MLE</dc:subject>
	<dc:description xml:lang="en">Poisson regression is a nonlinear regression model with the response variables in the form of discrete data and Poisson distribution. Data analysis using Poisson regression must meet assumptions such as the variance value and the average value of the response variables have the same value. However, in its application, overdispersion often occurs, namely the variance value is greater than the average value. Overdispersion in Poisson regression can occur because of the number of zero observations on the response variable. Data with zero excess and overdispersion are more suitable for using ZINB regression. The ZINB regression model is a model formed from the mixed distribution of the Poisson gamma. The ZINB regression model parameters were estimated using the MLE method with the EM algorithm. This study was applied to data on the number of neonatal deaths in Makassar City in 2018. The results of testing the ZINB regression model parameters showed that the predictor variable that had a partially significant effect was the number of newborns with low birth weight.</dc:description>
	<dc:publisher xml:lang="en">Hasanuddin University</dc:publisher>
	<dc:date>2025-02-17</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.unhas.ac.id/index.php/ESTIMASI/article/view/21037</dc:identifier>
	<dc:identifier>10.20956/ejsa.v6i1.21037</dc:identifier>
	<dc:source xml:lang="en">ESTIMASI: Journal of Statistics and Its Application; Vol. 6, No. 1, Januari, 2025 : Estimasi; 10-20</dc:source>
	<dc:source>2721-379X</dc:source>
	<dc:source>2721-3803</dc:source>
	<dc:language>en</dc:language>
	<dc:relation>https://journal.unhas.ac.id/index.php/ESTIMASI/article/view/21037/12546</dc:relation>
</oai_dc:dc>