Estimation of an origin-destination matrix with random link choice proportions: A statistical approach

H. P. Lo, N. Zhang, Hing Keung William Lam

Research output: Journal article publicationJournal articleAcademic researchpeer-review

85 Citations (Scopus)


The use of statistical modeling in the estimation of Origin-Destination (OD) matrix from traffic counts is reviewed. In particular, statistical models that consider explicitly the presence of measurement and sampling errors in the observed link flows are discussed. This paper proposes treating the link choice proportions as random variables. Accordingly, new statistical models are formulated and the corresponding Maximum Likelihood Estimator and Bayesian Estimator of the OD matrix are developed. The accuracies of these estimators are compared with those obtained by previous methods.
Original languageEnglish
Pages (from-to)309-324
Number of pages16
JournalTransportation Research Part B: Methodological
Issue number4 PART B
Publication statusPublished - 1 Jan 1996

ASJC Scopus subject areas

  • Transportation

Cite this