Abstract Alternative goodness of fit statistics for comparing observed and model generated trip matrices are examined. The behaviour and appropriateness of the alternative statistics are tested by comparing trip matrices for eight Canadian cities with simulated trip matrices calculated by the introduction of progressively larger random errors in the trip cells. The tests suggested that the phi-statistic is the most appropriate to test goodness of fit of alternative trip distribution models. Evidence is also presented which illustrates that state-of-the-art work trip distribution models incorporating a negative exponential travel deterrence function have goodness of fit equivalent to a random error of from 75–100%.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Goodness of fit statistics for trip distribution models


    Contributors:

    Published in:

    Publication date :

    1980-05-24


    Size :

    9 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Modifying Trip Distribution Models to Account for Trip Chaining

    Ewing, R. / Li, S.-C. / Shaw, S.-L. | British Library Conference Proceedings | 1995


    A note on goodness-of-fit statistics for probit and logit models

    Tardiff, Timothy J. | Online Contents | 1976


    Fuzzy Trip Distribution Models for Discretionary Trips

    Shafahi, Yousef / Nourbakhsh, Seyed Mohammad / Seyedabrishami, Seyedehsan | IEEE | 2008


    Empirical studies of work trip distribution models

    Sikdar, P.K. / Hutchinson, B.G. | Elsevier | 1980


    Transferability Analysis of Work-Trip-Distribution Models

    Elmi, Abdishakor M. / Badoe, Daniel A. / Miller, Eric J. | Transportation Research Record | 1999