Robust Estimation of Origin-Destination Matrices

Abstract

The demand for travel on a network is usually rep-resented by an origin-destination (OD) trip table or matrix. OD trip tables are typically estimated with synthetic techniques that use observed data from the traffic system, such as link volume counts from intelligent transportation systems (ITS), as input. A potential problem with current estimation tech-niques is that many ITS volume counters have a rel-atively high error rate. The focus of this paper is on the development of estimators explicitly designed to be robust to outliers typically encountered in ITS. Equally important, standard errors are devel-oped so that the parameter reliability can be quantified. This paper first presents a constrained robust method for estimating OD split proportions, which are used to identify the trip table, for a network. The proposed approach is based on a recently developed statistical procedure known in the liter-ature as the L2 error (L2E). Subsequently, a closed-form solution for calculating the asymptotic variance associated with the multivariate estimator is derived. Because the solution is closed form, the computation time is significantly reduced as com-pared with computer-intensive standard error cal-culation methods (e.g., bootstrap methods), and

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 16 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.