E-Jurnal Matematika
Vol 2 No 4 (2013)

PENERAPAN REGRESI ZERO-INFLATED NEGATIVE BINOMIAL (ZINB) UNTUK PENDUGAAN KEMATIAN ANAK BALITA

NI MADE SEKARMINI (Faculty of Mathematics and Natural Sciences, Udayana University)
I KOMANG GDE SUKARSA (Faculty of Mathematics and Natural Sciences, Udayana University)
I GUSTI AYU MADE SRINADI (Faculty of Mathematics and Natural Sciences, Udayana University)



Article Info

Publish Date
29 Nov 2013

Abstract

One method of regression analysis used to analyze the count data is Poisson regression. Poisson regression requires that the mean value equal to the value of variance (equidispersion). However, sometimes the data is going overdispersion  the state variance values ??greater than the mean value. One of the causes overdispersion is the excessive number of zero values ??on the response variable (excess zeros). One method of analysis that can be used on data that had overdispersion due to excess zeros is regression Zero-Inflated Negative Binomial (ZINB). The data that can be analyzed using the ZINB regression is the early childhood mortality in the province of Bali because much of the data is zero. The analysis showed that the data had overdispersion on Poisson regression, so the ZINB regression analysis was used. From the results of the ZINB regression can overcome overdispersion so it was better than the Poisson Regression Model.

Copyrights © 2013






Journal Info

Abbrev

mtk

Publisher

Subject

Mathematics

Description

E-Jurnal Matematika merupakan salah satu jurnal elektronik yang ada di Universitas Udayana, sebagai media komunikasi antar peminat di bidang ilmu matematika dan terapannya, seperti statistika, matematika finansial, pengajaran matematika dan terapan matematika dibidang ilmu lainnya. Jurnal ini lahir ...