Diphtheria is an upper respiratory tract disease caused by the bacteria Corynebacterium Diphtheriae. Diphtheria is a dangerous infectious disease, because there were 23 deaths from 529 cases in 2019. The data used in this final project research is secondary data taken from the Health Office in 2019. The number of deaths of diphtheria patients is calculated data and the assumption is distributed as a Poisson distribution. . The number of zero data of 73.5 percent indicates an overdispersion of the response variables. One of the conditions of Poisson Regression is that it requires equality between the mean and variance, this model is not appropriate to be applied to the dispersion below and above. The Zero Inflated Conway Maxwel Poisson (ZICMP) regression model can be an alternative because it is flexible for under- and over-dispersion data and can solve the problem of excess zero values in the response variable. In this study, ZICMP was applied to mortality cases in diphtheria patients in Indonesia. This study aims to examine the probability function and develop an algorithm to estimate ZICMP parameters and apply the ZICMP model to mortality cases in diphtheria patients. The Maximum Likelihood Estimation (MLE) method is used to estimate the parameters in ZICMP and the probability function is maximized using the Expectation-Maximization (EM) algorithm.

Overdispersion

Zero Inflation

Zero Inflated Conway Maxwel Poisson

Diphtheria.