Modelling Rail Accident and Incident Causes by Using Zero-Inflated Poisson Approach

The development of Railway industry has been growing rapidly until today, which make it as one of the popular choice of transportation mode to travel from one place to another and it becoming more complex. Thus, the complexity of rail network required high level of safety features to prevent any unwanted incident. Therefore, this study proposed a proper procedure on modelling accident which is conducted by using Poisson model. The most contributory factor that influenced the accident can be identified by using root cause analysis. “Ishikawa diagram” is a popular tool to identify problem occurring from the root where it begins. The data were taken from several sources which is secondary data where the data period was starting from 1999 to 2014. Analysis from Ishikawa shows there are ten main factors involved to influences an accident. Those factors are “train driver mistake”, “other’s human mistake”, “weather influence”, “track problem”, “train problem”, “signaling error”, “maintenance error”, “communication error”, “procedure error”, and “others”. Then, the model was tested to know which model among regression model is suitable and give a better prediction result by carrying out Dispersion test and Vuong test. The results show that Zero-inflated model considered as a sophisticated model to predict accidents and incident cases by Vuong test with p-value of 0.19695481, 0.1301056 and 0.0689108. The most factors contribute to the cases are “collisions”, “derailment” and “SPAD”.