Assessing Uncertainty in Urban Simulations Using Bayesian Melding

The authors develop a method for assessing uncertainty about quantities of interest using urban simulation models. The method is called Bayesian melding, and extends a previous method developed for macrolevel deterministic simulation models to agent-based stochastic models. It encodes all the available information about model inputs and outputs in terms of prior probability distributions and likelihoods, and uses Bayes's theorem to obtain the resulting posterior distribution of any quantity of interest that is a function of model inputs and/or outputs. It is Monte Carlo based, and quite easy to implement. The authors apply the method to the projection of future household numbers by traffic activity zone in Eugene-Springfield, OR, using the UrbanSim model developed at the University of Washington. The authors then compare the model with a simpler method that uses repeated runs of the model with fixed estimated inputs. The authors find that the simple repeated runs method gives distributions of quantities of interest that are too narrow, while Bayesian melding gives well calibrated uncertainty statements.

• Record URL:
  • http://www.sciencedirect.com/science/article/B6V99-4MR7D2M-1/2/358f275aca3d70867d3038c7a544d8b1
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/01912615
• Supplemental Notes:
  • Abstract reprinted with permission from Elsevier
• Authors:
  • Sevcikova, Hana
  • Raftery, Adrian E
  • Waddell, Paul A
• Publication Date: 2007-7

Language

• English

Media Info

• Media Type: Print
• Features: Appendices; Figures; References; Tables;
• Pagination: pp 652-669
• Serial:
  • Transportation Research Part B: Methodological
  • Volume: 41
  • Issue Number: 6
  • Publisher: Elsevier
  • ISSN: 0191-2615
  • Serial URL: http://www.sciencedirect.com/science/journal/01912615

Subject/Index Terms

• TRT Terms: Bayes' theorem; Computer models; Evaluation and assessment; Households; Input output models; Mathematical models; Monte Carlo method; Simulation; Statistical distributions; Stochastic processes; Uncertainty; Urban areas
• Identifier Terms: UrbanSim (Computer model)
• Uncontrolled Terms: Bayesian approach
• Geographic Terms: Eugene (Oregon); Springfield (Oregon)
• Subject Areas: Data and Information Technology; Economics; Highways; Planning and Forecasting; Society; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01051759
• Record Type: Publication
• Files: TRIS
• Created Date: Jun 19 2007 8:28AM