Using data from three different samples and more than 1000 participants, the current study examines differences in dangerous driving in terms of age, gender, professional driving, as well as the relationship of dangerous driving with behavioral indicators (mileage) and criteria (traffic offenses). The study uses an adapted (Romanian) version of the Dula Dangerous Driving Index (DDDI, Dula and Ballard, 2003) and also reports data on the psychometric characteristics of this measure. Findings suggest that the Romanian version of the DDDI has sound psychometric properties. Dangerous driving is higher in males and occasional drivers, is not correlated with mileage and is significantly related with speeding as a traffic offense, both self-reported and objectively measured. The utility of predictive models including dangerous driving is not very large: logistic regression models have a significant fit to the data, but their misclassification rate (especially in terms of sensitivity) is unacceptable high. (C) 2012 Elsevier Ltd. All rights reserved.