01590305

Component

https://doi.org/10.3141/2564-10

The decision tree technique is increasingly applied in activity-based travel demand modeling. It has the strength of representing the full complexity of interactions between different variables. However, this complexity often hinders an interpretation of the relative effects of these variables on the activity travel choice. In this study, a sensitivity analysis is performed on decision trees in FEATHERS, an activity-based microsimulation modeling framework, with the purpose of quantitatively measuring the relative effect of input variables involved in the given decision trees on the choice variable. The local and global sensitivity analysis approaches are investigated: (a) a one-at-a-time approach that predicts the choice frequency distribution by varying selected input variables one after another and keeping all other variables as observed and (b) the improved Sobol method, which evaluates the effect of an input variable while all other variables are varied as well. With the application of these two approaches to two representative decision trees concerning work-related activity (i.e., commute trip) choice and transport mode choice for work-related activities in the FEATHERS framework, consistent results concerning the key input variables for these two decision trees are derived, and some extra insights are gained from each of the approaches.

01624690

16-1598

English

pp 89–98

2016

Transportation Research Record: Journal of the Transportation Research Board

9780309441452

Print

Figures (5) ; References (23) ; Tables (4)

Activity choices; Decision trees; Microsimulation; Sensitivity analysis; Travel demand; Variables

FEATHERS framework

Data and Information Technology; Highways; Planning and Forecasting

TRIS, TRB, ATRI

Jan 12 2016 4:41PM

• Assumptions Inherent in Assessing Traffic Forecast Accuracy
• Choice Set Imputation in Atomistic Spatial Choice Models
• Evaluating Transport User Benefits: Adjustment of Logsum Difference for Constrained Travel Demand Models
• Exploring the Role of Location in Dynamics of the Birth and Death of Business Establishments: Case Study Analysis of Santa Barbara County, California
• Integrated Mode Choice and Dynamic Traveler Assignment in Multimodal Transit Networks: Mathematical Formulation, Solution Procedure, and Large-Scale Application
• Integration of a Capacity-Constrained Workplace Choice Model: Recent Developments and Applications with an Agent-Based Simulation in Singapore
• Journey Levels in Strategy-Based Transit Assignment: Modeling Integrated Transit Fares and More
• Microsimulation of Demand and Supply of Autonomous Mobility On Demand
• Modeling Carsharing with the Agent-Based Simulation MATSim: State of the Art, Applications, and Future Developments
• Simulated Effects of the Location of High-Speed Rail Stations on Land Development: Case Study of the Lisbon Metropolitan Area, Portugal
• Transportation Planning Through Peer-to-Peer Modeling
• Travel Plans for New Residential Developments: Measuring Self-Selection Effects to Better Understand Travel Behavior Impacts
• Trend-Breaking Influences of Built Form on Travel in UK Cities: Evidence from New Quantifications of Within- and Between-Built-Form Variations
• Using Predicted Bicyclist and Pedestrian Route Choice to Enhance Mode Choice Models