An ordered probit model is used to predict motor vehicle usage in Australia on the basis of the unit record files underlying the Australian Bureau of Statistics' Survey of Motor Vehicle Use. Both household and freight transport are analysed. The paper examines the statistical significance of a number of driver, vehicle and travel purpose variables on the level of motor vehicle usage. Factors analysed include driver age and gender, vehicle and fuel type, age of the vehicle, purpose of trip, place of registration, type of freight and number of drivers. The results indicate that the cut-off points between very low, low, medium, high and very high vehicle usages are significant and that the factors associated with differences in usage include driver age, engine size and age of vehicle for household vehicles and the type of freight, type of vehicle, gender and number of drivers for freight usage.