This paper focuses on a novel approach of trip generation modelling. First, a summary of the trip generation models most commonly used is given. Although many of these models are based on disaggregate household data and attempt to incorporate behavioral aspects, they still lack a firm statistical basis. Furthermore, some modelling techniques such as linear and non-linear regression present difficulties in coping with many specific problems such as the discreteness of the dependent variable, the requirement of non-negative forecasts, and the bias of the expected number of trips. To provide a firm statistical basis the use of a disaggregate Poisson model is proposed in which the lambda-parameter depends on a number of household characteristics. This model avoids the problems mentioned above and can easily be interpreted. A maximum-likelihood estimation method is discussed for the two cases in which the lambda-parameter is additive and multiplicative in the explanatory variables. The Poisson model has been applied in the Netherlands as a submodel of the Apeldoorn transportation study for modelling shopping and personal business trips. The estimation results appear to be superior to the results of linear and non-linear regressions on the same data. The last section is devoted to the aggregation issue. An analytical aggregation procedure is proposed if the zonal variation of the lambda-parameter fits a gamma distribution. In the absence of knowledge of the distribution of lambda, other aggregation procedures are discussed, of which the classification method seems most appropriate. The paper ends with some suggestions for future research. (TRRL)

  • Corporate Authors:

    Inst Mathematics, Info Processing & Statistics TNO

    P.O. Box 297
    The Hague,   Netherlands 
  • Authors:
    • Ruygrok, C J
    • Essen, P G
  • Publication Date: 1980

Media Info

  • Features: References; Tables;
  • Pagination: 27 p.

Subject/Index Terms

Filing Info

  • Accession Number: 00393182
  • Record Type: Publication
  • Source Agency: Institute for Road Safety Research, SWOV
  • Report/Paper Numbers: A80VK0101 Monograph
  • Files: ITRD, TRIS
  • Created Date: Jun 30 1985 12:00AM