Suchergebnisse

A statistical model for the evaluation of the effectiveness of the Demerit Points System (DPS) in reducing traffic offenses is presented. The model for the waiting times between detected traffic offenses is based on an exponential distribution. Since traffic offenses are relatively rare events, the length of the study period was such that censoring was unavoidable. Under these circumstances Maximum Likelihood (ML) estimates of the waiting time between offenses are determined and the corresponding hypotheses are tested. The empirical results showed that the DPS was responsible for most of the deterrent effect reflected in the increased mean time until the third offense subsequent to the first and second offense detected less than three years apart.