The dramatic increase in vehicle travel in developing countries calls for the effectiveintroduction of features that reduce traffic accidents. An important piece of information for suchan introduction lies in the prediction of accidents and their fatalities, which is addressed in thispaper. Smeed’s model was originally developed for the prediction of traffic fatalities in both developedand developing countries. More reliable prediction models are developed for a numberof Arab countries, producing a much less absolute percentage error than those of Smeed’s model.Regression analysis was applied to time-series data in the studied countries, producing an absolutepercentage error as low as 7.67 for Saudi Arabia and 12.17 for Kuwait. An accident predictionmodel that relates accident frequency in Kuwait to various contributory factors is developedusing the Generalized Linear Modelling (GLM) technique. The final model shows that age, nationality,aggressive driver behaviour, dangerous offences, perception of effectiveness of enforcement,marital status, speed, and experience are the main contributory factors that lead toaccident involvement.