Road safety is a complex phenomenon which is affected by several factors, with the most significant one being the driver behavior. The aim of the current research is to identify the impact of driver distraction on speeding using data obtained from smartphone sensors. To fulfil this objective, a naturalistic driving experiment was carried out in Greece and data collected from 100 drivers (18–65 aged) over a period of six months were analyzed. Four statistical lognormal regression models forecasting the percentage of exceeding the speed limits were developed: one overall model and one per road type (i.e. highway, rural, urban).Results demonstrated that driver distraction significantly affected driving behavior and, especially, speeding. Lastly, a stronger correlation had emerged between harsh accelerations and speeding, but also distance travelled, risky hours driving during night and demographic characteristics had a direct impact on speeding.