Feasibility of Modeling the Relationship Between Seat Belt Program Inputs and Outcomes

The objective of this project was to determine the feasibility of building a model that could be used as a decision-making tool for State Highway Safety Offices (SHSOs) to help predict how resource adjustments may affect seat belt use (both positively and negatively) to avoid inadvertent negative effects on seat belt use rates and unrestrained fatalities. To accomplish this objective, the study focused on 1) exploring the existence, availability, and quality of data needed to build a useful model; 2) preparing a description of the types of models that may be worth exploring given the data that are likely available; and 3) discussing the implications of the findings for future model development. The present study examined only the initial feasibility of a seat belt predictive model. Ultimately, the feasibility of any model can only be determined by developing a model and assessing the validity and reliability of that model by comparing the model output with what occurs after specific decisions are made. The present study involved determining the initial step in that process by assessing whether data and modeling techniques exist that could support a viable model. The overall conclusion of the study was that while the available evidence points to potential feasibility, it is not clear that the input variables would provide sufficient precision to create a useful predictive model due to limitations regarding what is available to the SHSOs.

• Record URL:
  • https://www.nhtsa.gov/sites/nhtsa.dot.gov/files/documents/812524_feasibility-of-modeling-the-relationship-between-seat-belt-program-inputs-and-outcomes.pdf
• Corporate Authors:

  Pacific Institute for Research and Evaluation

  11720 Beltsville Drive, Ste 900
  Calverton, MD  United States  20705-3111

  National Highway Traffic Safety Administration

  Office of Behavioral Safety Research
  1200 New Jersey Avenue SE
  Washington, DC  United States  20590
• Authors:
  • Romano, Eduardo
  • Thomas, F Dennis
  • Blomberg, Richard D
  • Ramirez, Anthony
• Publication Date: 2018-4

Language

• English

Media Info

• Media Type: Digital/other
• Edition: Final Report
• Features: Figures; References; Tables;
• Pagination: 23p

Subject/Index Terms

• TRT Terms: Data collection; Decision support systems; Feasibility analysis; Mathematical prediction; Resource allocation; Safety programs; Seat belt use; States
• Subject Areas: Highways; Planning and Forecasting; Safety and Human Factors;

Filing Info

• Accession Number: 01680319
• Record Type: Publication
• Report/Paper Numbers: DOT HS 812 524
• Contract Numbers: DTNH2211D0000226L; Task Order 5
• Files: HSL, TRIS, ATRI, USDOT
• Created Date: Sep 13 2018 9:13AM