Suggested Citation:
Yang, Yudi, Yueyue Fan, Johannes O. Roysetb (2019) Estimating Probability Distributions of Travel Demand on a Congested Network. Transportation Research Part B 122, 265 - 286

We aim to infer the probability density function (pdf) of Origin–Destination (O–D) demand variables using multiple sets of traffic counts over a network. Through integrating statistics and optimization techniques with transportation domain knowledge, we propose an estimation framework based on Generalized Method of Moment (GMM) with both options of exact and approximated estimators. Compared with existing methods for day-to-day O–D matrix estimation, our approach has three unique advantages. First, it is a rigorous statistical method with a capability of incorporating complex traffic network models suitable for a congested network. Second, our estimation framework is flexible to handle a wide variety of probabilistic models. Finally, instead of just providing point estimates, it reveals large sample statistical properties of the proposed estimator, which serve as a theoretical foundation for assessing estimation quality, constructing confidence region and testing model adequacy. Three numerical examples of different scales are accompanied to demonstrate various aspects of the proposed estimation framework.

Key words: Origin–destination travel demand estimation, probability distribution, generalized method of moments, congested networks