Abstract An expression is derived for the variances and covariances of the logarithms of origin- destination flows when estimated by one of a family of log-linear models. Among this family is the Furness growth factor model, the gravity model, the Willumsen model and the Van Zuylen-Bell model. Variances and covariances for the logarithms of the parameters incorporating prior information and for the values of the constraints with which the fitted values must conform are transformed linearly into approximate variances and covariances for the logarithms of the fitted values. Additional error due to misspecification of either the model or the constraints is not taken into account. Depending on the model, the prior information parameters may correspond to values of a deterrence function or to a base year trip matrix, while the constraints may represent design year trip end totals or traffic counts. As an illustration, the expression is applied to an example involving Willumsen's model.
Variances and covariances for origin-destination flows when estimated by log-linear models
Transportation Research Part B: Methodological ; 19 , 6 ; 497-507
1985-01-01
11 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Correlations, variances, covariances - from GOCE signals to GOCE products
British Library Conference Proceedings | 2007
|Origin-Destination Matrices Estimated with a Genetic Algorithm from Link Traffic Counts
Transportation Research Record | 2001
|Origin-Destination Matrices Estimated with a Genetic Algorithm from Link Traffic Counts
British Library Conference Proceedings | 2001
|Examination of Crash Variances Estimated by Poisson-Gamma and Conway-Maxwell-Poisson Models
Online Contents | 2011
|Origin-Destination Matrices Estimated with a Genetic Algorithm from Link Traffic Counts
Online Contents | 2001
|