PEMODELAN PENYAKIT DIFTERI DI SUMATERA BARAT MENGGUNAKAN REGRESI ZERO INFLATED DAN REGRESI HURDLE

Abstract

Data that states the number of events in a certain period of time is called count data. Poisson regression is one of the regression models included in the application of GLM that can be used to model the count data. In Poisson regression, there are assumptions that must be met, namely the mean and variance of the response variables must be the same (equidispersion). Several models that are able to overcome overdispersion due to excess zero are the Zero Inflated model and the Hurdle model. This study examines the characteristics of parameter estimation in the modeling of quantified data that is overdispersed due to excess zero using the Zero Inflated Poisson (ZIP), Zero Inflated Negative Binomial (ZINB), Hurdle Poisson (HP) model and the Hurdle Negative Binomial (HNB) model in cases of diphtheria. in West Sumatra in 2018. Based on individual parameter testing and AIC values, the HP model provides better performance than the ZIP, ZINB, and HNB models. So the Hurdle Poisson model is better used in this case than other models