How Much Do Attitudinal Variables Improve Travel Demand Models? Evaluation Using an Overlap Sample From an Attitude-Rich Survey and the 2017 National Household Travel Survey

Details

• Creators:
  Kim, Ilsu ; Mokhtarian, Patricia L.
• Corporate Creators:
  Georgia Institute of Technology. School of Civil and Environmental Engineering
• Corporate Contributors:
  National Center for Understanding Future Travel Behavior and Demand (TBD) ; United States. Department of Transportation. University Transportation Centers (UTC) Program ; United States. Department of Transportation. Office of the Assistant Secretary for Research and Technology
• Subject/TRT Terms:
  Attitude Imputation Datasets Electric Vehicles Evaluation Households Machine Learning Marker Variables Mathematical Prediction Overlap Sample Regression Analysis Surveys Travel Behavior Travel Demand Vehicle Miles Of Travel

  More +
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States ; Georgia
• Edition:
  Final Report: 2024-2025
• Corporate Publisher:
  United States. Department of Transportation. University Transportation Centers (UTC) Program
• Abstract:
  This study aims to evaluate the effectiveness of adding a handful of attitudinal marker statements to transportation surveys (instead of designing, deploying, and factor-analyzing a full set of attitudinal variables). We exploit the rare opportunity offered by the 2017 Georgia Department of Transportation (GDOT) Emerging Technologies (ET) survey and the 2017 Georgia add-on to the National Household Travel Survey (NHTS) having 1,245 respondents in common. The non-overlap GDOT ET survey dataset (N = 2,043) is selected as the donor sample, based on which elastic net regression (ENR) models are trained for imputation of attitudinal factor scores using marker variables (MVs). The overlap NHTS dataset (i.e., the recipient sample) (N = 1,245) is treated as if it has only MVs, with attitude scores needing to be imputed using the ENR models trained on the donor sample. The ENR models display high prediction performance in both the donor and recipient datasets, while MVs present excellent performance as well. Three travel behavior variables in the recipient dataset are modeled with no attitudes, predicted attitude scores, and MVs: household vehicle count, (personal yearly) vehicle miles driven, and hybrid/electric vehicle adoption. For each dependent variable, several attitudes show statistical significance, although their contributions to model fit vary. The results indicate that including attitudes leads to (a) better prediction of less-common alternatives (zero vehicles and hybrid/electric vehicle adoption), primarily by improving the prediction of the groups most likely to select such alternatives, and (b) discovery of additional non-attitude variables that would have been considered insignificant otherwise.
• Format:
  PDF
• Funding:
  69A3552344815 ; 69A3552348320
• Collection(s):
  University Transportation Centers
• Main Document Checksum:
  urn:sha-512:1301c5e62359e6a573f132abe330029eb873e021cf13f742277d75db633b1ac3c70009b7d552ad581507a82ab3cacfdb840ff5f2a72f0a95f951a91f56f3950d
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/91949/dot_91949_DS1.pdf
• File Type:
  [PDF - 1.39 MB ]