<![CDATA[ABSTRACTTuberculosis is a direct infectious disease caused by bacteria (Mycobacterium tuberculosis). The number of TB cases in NTB in 2020 decreased by 16.58% from 2019. This needs to be analyzed to find out what factors influence tuberculosis so that the number of tuberculosis cases can be minimized. Data on the number of TB cases is count data, so the analysis used to model is Poisson regresi regression. In Poisson regression analysis, the phenomenon of overdispersion often occurs. If there is overdispersion, Poisson regression is not suitable for modeling the data because it will produce biased parameter estimates. One of the methods used to overcome overdispersion in Poisson regression is Negative Binomial regression. The results of the analysis show that there are four variables that are significant to the number of TB cases, namely population density (), number of health centers (), number of nursing staff (), and the percentage of households that have access to proper sanitation () with the model . The results of selecting the best model show that the Negative Binomial Regression model is better than the Poisson regression model based on the criteria for the goodness of the Deviance and AIC models.]]>
Copyrights © 2022
