CAR OWNERSHIP FORECASTING IN CATEGORY ANALYSIS-A PITFALL

In this effort to suggest a possible explanation for the predictive failure of current models, concepts from economic theory, particularly the theory of consumption function are utilized, and criticisms (which are equally applicable to all category analysis models for predicting car ownership) are directed at the procedures used in the original National Traffic Model. It is suggested that the problem lies in the way in which the regression equations relating pn (proportion of households owning cars) to household income are derived. The paper concludes that a model of car ownership based on permanent disposable income may prove more successful than one based on gross actual income. It is observed that current models may considerably underestimate the sensitivity of car ownership to income.

• Supplemental Notes:
  • This paper appears in "Urban Traffic Models", which is a publication containing the Proceedings of Seminar N of the Summer Annual Meeting at University of Warwick, England during July, 1975.
• Corporate Authors:

  Planning and Transport Res and Computation Co Ltd

  167 Oxford Street
  London W1R 1AH,   England 
• Authors:
  • Parish, D J
• Publication Date: 1975-7

Media Info

• Features: References;
• Pagination: p. 214-224
• Serial:
  • Publication of: IRCOBI SECRETARIAT
  • Publisher: IRCOBI (International Research Council on the Biokinetics of Impacts)

Subject/Index Terms

• TRT Terms: Automobile ownership; Forecasting; Income; Mathematical models; Regression analysis
• Uncontrolled Terms: Models
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management;

Filing Info

• Accession Number: 00148098
• Record Type: Publication
• Report/Paper Numbers: P122
• Files: TRIS
• Created Date: Feb 23 1977 12:00AM