Application of Smeed and Andreassen accident models for Turkey: Various scenario analyses

Abstract

In this study, accident prediction models for Turkey were developed by using the historical data, between 1986 and 2005, including population (P), the number of vehicles (N), accidents (C), injuries (I), and fatalities (D). In the models development, the structural form of Smeed and Andreassen Models were employed. However, Smeed Model was developed in different point of view so that this model was called as Smeed Similarity Model. The number of accident, injury and fatalities in Turkey which is on the way of a full member of European Union, were tried to estimate under different three scenarios until the year of 2010. Both models were compared in terms of percent difference (PD), mean absolute percent errors (MAPE), and root mean square errors (RMSE). Despite that Andreassen model for the years between 1986 and 2005 had errors lower than Smeed Similarity model, for future estimates latter gave more plausible results with scenarios.