In the developing country, Road Traffic Accidents are among the leading cause of deathrnand injury; Ethiopia in particular experiences the highest rate of such accidents. RoadrnTraffic Accidents cannot be absolutely eradicated, however, it is possible to prevent themrnto some extent as long as the contributing factors are identified and tackled appropriately. rnThe driver behavior plays a crucial role in the occurrence of a crash; but, it is usuallyrncomplex and unpredictable, and also focusing too much on the driver as the cause of arncrash often masked the ability to see other causes that could reduce crash rates and crashrnseverity. So it is important to figure out the role of the non-behavioral factors in trafficrnaccidents, based on which cost-effective countermeasures can be recommended to reducernthe chance of accidents. Previously, significant studies were undertaken to predict thernmagnitude of road traffic accidents and black spot areas in Addis Ababa City consideringrnthe driver as the main causing factor. However significant studies were not undertaken tornpredict the magnitude of accident severity considering the non-behavioral factors as thernmain causing factor. As a result, this study developed accident severity prediction modelsrnusing Multinomial logistic regression that link accident severity to non-behavioralrncontributing factors. For this study, a total of 5251 traffic accident data from June 30/2011rnto June 30/2016GC were collected from Yeka sub-city. Multinomial logistic regressionrnwas used to estimate the model parameters. The data set obtained for this study werernapplied to examine the goodness-of-fit regression models. The dependent variable used inrnthis study was crash severity. As part of the study, the models have been tested to see howrnwell they predict the accidents observed during a one year accident period. From the modelrndeveloped, road type, road surface condition, crash type, maneuvering condition andrnlighting conditions were found as significant explanatory variables that influence thernprediction of crashes in the yeka sub-city. This indicates that non-behavioral factors havernan effect on the occurrence of accident.