Reduction of the under-five mortality rate of 25 or fewer deaths per 1000 live births by 2030 is one of the priorities of the Sustainable Development Goals. Over 80% of all under-five deaths occur in Africa and South-East Asia regions. About half of under-five deaths occur in only six countries including Ethiopia. One in every 15 Ethiopian children dies before the fifth birthday. Therefore, the aim of this study was to identify factors that affect under-five mortality based on 2016 EDHS dataset using count regression models. The survey collected information from a total of 15,683 women aged 15-49 years out of which 14,370 women were considered in this study. The data were found to have excess zeros (53.7%) and the variance was higher than its mean. Thus several count models such as Poisson, NB, ZIP, ZINB, HP, and HNB models were fitted to select the model which best fits the data. Among this model, HNB fits the data best. The LRT test suggested that, the number of under-five death varies among regions and multilevel count model fit better than the single level count model. For selected multilevel HNB model, the truncated negative binomial part showed that fathers who have secondary and above education are about 29% less likely to die children compared with no formal education. Similarly, the risk of under-five death is 28% lower among the mothers having primary than those with no formal education. A child of multiple births is 1.45 more likely to die as compared with single birth. Babies delivered at private sector are 0.65 lower risk of under-five mortality compared to the babies delivered at home. A child with birth order 2-3 and 4 and above is 46.6% and 58.6% which are more likely to die as compared with birth order first. The study also showed that there is a significant regional variation of under-five mortality (𝜎̂ = 0.450 𝑝 − 𝑣𝑎𝑙𝑢𝑒 = 0.0250 and 𝜎̂ 𝑤0 2 𝑢0 2 = 0.668 𝑝 − 𝑣𝑎𝑙𝑢𝑒 = 0.0043) . Moreover, mother education level, the age of mother, family size, place of delivery, vaccination of child and types of birth effects on under-five mortalities vary among regions of Ethiopia. The variables of vaccination, family size, age of mother, antenatal visit, birth interval, birth order, and religion, contraceptive used, father education level, mother education level, father occupation, place of delivery, child twin and age first birth were identified as significant factors. The Ministry of Health should work properly to raise the awareness of parents for vaccination, family planning services and efforts should be made to improve parental educational level. Keywords: Under Five Mortality, Ethiopia, Hurdle Negative Binomial, Multilevel.