Open AccessPENERAPAN REGRESI GENERALIZED POISSON UNTUK MENGATASI FENOMENA OVERDISPERSI PADA KASUS REGRESI POISSON
Author(s) -
I Putu Yudanta Eka Putra,
I Putu Eka Nila Kencana,
I Gusti Ayu Made Srinadi
Publication year - 2013
Publication title -
e-jurnal matematika
Language(s) - English
Resource type - Journals
ISSN - 2303-1751
DOI - 10.24843/mtk.2013.v02.i02.p038
Subject(s) - overdispersion , poisson regression , mathematics , statistics , poisson distribution , zero inflated model , quasi likelihood , regression analysis , generalized linear model , count data , variance (accounting) , value (mathematics) , econometrics , population , accounting , business , demography , sociology
The Poisson regression is generally used to analyze the response variable that is a discrete data. Poisson regression has assumption which must be met, that is condition equidispersion. But in fact this assumption is often violated, that is the value of the variance is greater or less than the mean value. The condition when value of the variance is greater than the mean value is called overdispersion. One method that can be used for overdispersion data is Generalized Poisson regression. In this research, it was found that the Generalized Poisson regression method was better than Poisson regression method.