Potential crash involvement of young novice drivers with previous crash and citation records

A goal for any licensing agency is the ability to identify crash-prone drivers. Thus, the objective of this study is the development of a crash prediction model that can be used to estimate the likelihood of a young novice driver's involvement in a crash occurrence. Multiple logistic regression techniques were employed with available Kentucky data. This study considers as crash predictors the driver's total number of previous crashes, citations accumulated, and demographic factors. The driver's total number of previous crashes was further disaggregated into the driver's total number of previous at-fault and not-at-fault crashes. Sensitivity analysis was used to select an optimal cut-point for the model. The overall efficiency of the model is 77.82%, and it can be used to classify correctly more than one-third of potential crash-prone drivers if a cut-point of 0.247 is selected. The total number of previous at-fault and not-at-fault crash involvements and the accumulation of speeding citations are strongly associated with a driver's being at risk. In addition, a driver's risk is increased by being young and being male. Although the statistical nature of driver crash involvements makes them difficult to predict accurately, the model presented here enables agencies to identify correctly 49.4% of crash-involved drivers from the top 500 high-risk drivers. Moreover, the model can be used for driver control programs aimed at road crash prevention that may range from issuance of warning letters to license suspension.