How Effective Are Attitudinal Variables at Improving Travel Behavior Models? Evaluation Using an Overlapping Sample From an Attitude-Rich Survey and the 2017 National Household Travel Survey

Facing various factors affecting travel behavior, including altered work/commute patterns and advancements in transportation technologies, travel demand models are, and will be, in need of enhanced prediction performances. One well-established way to better understand and predict travel behavior is to include attitudes in travel behavior models, which enables explaining behavior more completely and meaningfully and simulating scenarios involving changes in attitudes. To encourage measuring and utilizing attitudes in practice-oriented travel demand models, a clear demonstration of the effectiveness of such an approach is necessary. To this end, this study aims to evaluate the efficacy of including a handful of attitudinal marker variables in government-sponsored surveys, by examining the improvements that those variables bring to modeling travel behavior measured in the surveys. The datasets to be used are the responses to the 2017 Georgia Department of Transportation (GDOT) Emerging Technologies survey (an attitude-rich survey dataset) and the Georgia add-on sample’s responses to the 2017 National Household Travel Survey (NHTS). Using attitudes predicted from machine learning functions trained on the non-overlapping sample of respondents to the former survey (N » 1,800) using only a skeletal set of attitudinal variables (called marker variables), the overlap sample of respondents completing both surveys (N » 1,500) will be deployed to model several travel behavior variables found in the latter survey, to investigate how effective the predicted attitudes are as explanatory variables, compared to the “observed” attitudinal factor scores created from the former survey, and to the marker variables themselves. This study will yield insight into the potential of employing attitudinal marker variables in practice-oriented travel behavior modeling based on government-administered surveys.

• Record URL:
  • https://tbd.ctr.utexas.edu/research-product/how-effective-are-attitudinal-variables-at-improving-travel-behavior-models-evaluation-using-an-overlapping-sample-from-an-attitude-rich-survey-and-the-2017-national-household-travel-survey/

Language

• English

Project

• Status: Active
• Funding: $200,000.00
• Contract Numbers:

  69A3552344815

  69A3552348320

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Center for Understanding Future of Travel Behavior and Demand

  University of Texas
  Austin, TX  United States 
• Project Managers:

  Bhat, Chandra

• Performing Organizations:

  Georgia Institute of Technology, Atlanta

  790 Atlantic Drive
  Atlanta, GA  United States  30332-0355
• Principal Investigators:

  Mokhtarian, Patricia

• Start Date: 20240601
• Expected Completion Date: 20250531
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers Program

Subject/Index Terms

• TRT Terms: Attitudes; Machine learning; Surveys; Travel behavior; Travel demand; Variables
• Subject Areas: Planning and Forecasting; Society; Transportation (General);

Filing Info

• Accession Number: 01955082
• Record Type: Research project
• Source Agency: Center for Understanding Future of Travel Behavior and Demand
• Contract Numbers: 69A3552344815, 69A3552348320
• Files: UTC, RIP
• Created Date: May 15 2025 2:39PM