A method of analysis of personal automobile ownership is presented that differs from the well-known aggregate and disaggregate methods. The analysis consists of two steps. First, a cluster-segmentation method is applied to data from the Dutch National Travel Survey. The results show that personal automobile ownership is mainly determined by personal net income, age, and sex. Second, a model has been specified that includes these factors. When income and age are accounted for, a structural difference in automobile ownership is shown between men and women. Furthermore, for the period studied (1979-1982) the results indicate that for the age group 65 and older, automobile ownership increased significantly, whereas for those 25 years and younger, it decreased. Advantages of the method are (a) the relative stability of the homogeneous population groups independent of accidental changes in the survey population and (b) insight into the relationship of automobile ownership with the most essential determining factors. Because of these advantages, the method presented can be used to improve both analysis and forecast of automobile ownership.
Abstract