Assessing the Quality of Origin-Destination Matrices Derived from Activity/Travel Surveys: Results from a Monte Carlo Experiment

Abstract

To support policy makers combating travel-related externalities, quality data is required for the design and management of transportation systems and policies. To this end, large amounts of money have been spent on collecting household and person-based data. The main objective of this paper is to assess the quality of origin-destination matrices derived from household activity/travel surveys. To this purpose, a Monte Carlo experiment is set up to estimate the precision of OD-matrices given different sampling rates. The Belgian 2001 census data, containing work/school-related travel information for all 10,296,350 residents, are used for the experiment. For different sampling rates, 2000 random stratified samples are drawn. For each sample, three origin-destination-matrices are composed: one at municipality level, one at district level, and one at provincial level. The correspondence between the samples and the population is assessed by using the Mean Absolute Percentage Error (MAPE) and a censored version of the MAPE (MCAPE). The results show that no accurate OD-matrices can be directly derived from these surveys. Only when half of the population is queried, an acceptable OD-matrix is obtained at provincial level. Therefore, it is recommended to use additional information to better grasp the behavioral realism underlying destination choices and to collect information about particular origin-destination pairs by means of vehicle intercept surveys. In addition, the results suggest using the MCAPE next to traditional criteria to examine dissimilarities between different OD-matrices. An important avenue for further research is the investigation of the effect of sampling proportions on travel demand model outcomes.