Background Globally, more than 165 million children were stunted. However, the distribution of stunting across the globe was not clearly known. Therefore, this study was aimed at assessing spatial distribution and determinants of stunting among under-five children in Ethiopia.Methods Ethiopian demography and health survey 2016 data set was used. A two stage stratified cluster sampling technique was used to include 8,855 under-five children. ArcGIS10.1 was used to visualize the distribution of stunting in Ethiopia. Getis-Ord statistics was used to identify whether the distribution of cases is randomly distributed, clustered, or dispersed. Getis-Ord statistics was used to identify hot spot and low spot areas. Generalized estimating equation (GEE) model was used to identify determinants. Adjusted odds ratio (AOR) and 95% confidence interval (CI) were used to measure the strength of the association.Results In the study the overall prevalence of stunting was 38.4% (37.4%-39.4%). Significantly primary clusters were found in Amhara, Southern Tigray, and Western Afar. Secondary clusters were found in Tigray, Afar, Benishangul, South-Eastern SNNPR and South-Western Oromia. Factors of a child lived in a region of Tigray [AOR = 2.3(CI = 1.53-3.46)], Afar [1.9(1.21-2.86)], Amhara (AOR=2.85, 95%CI: (1.9-4.29)), Oromia (AOR=1.71, 95% CI: (1.13-2.46)), Benishangul (AOR=2.61, 95% CI: (1.72-3.95)), SNNPR (AOR=2.04, 95% CI: (1.36-3.06)), Harari (AOR=1.63, 95% CI:(1.03-2.57)) and Dire-Dawa (AOR=2.25, 95% CI: (1.44-3.51)), HHs had television and/or radio (AOR= 1.61, 95% CI: (1.12-2.82)), poor wealth index (AOR=1.4, 95% CI: (1.2-1.6)), stunted mother (AOR=1.9, 95% CI: (1.62-2.14)), under-weight mothers (AOR=1.2, 95% CI: (1.03-1.32)), anemic mother (AOR=1.32, 95% CI (1.1-1.62)), child being male (AOR=1.2, 95% CI: (1.19-1.32)), age of child (AOR=1.25, 95% CI: (1.19-1.39)), mothers delivered at home (AOR=1.16, 95% CI: (1.04-1.33)), low birth weight of child (AOR=1.5, 95% CI (1.29-1.65)) and anemic child (AOR=1.6, 95% CI (1.43-1.79)) were significantly associated risk factors.Conclusions In Ethiopia the distribution of stunting was not randomly distributed and varies across regions. Region, wealth index, maternal, and child factors were independent predictors of stunting. Federal ministry of health with other concerned body need to prioritize hotspot areas to address contributing factors of stunting among under-five children.