Development of Crash Modification Factors (DCMF) Program
The mission of the DCMF program is to save lives by identifying new safety strategies that effectively reduce crashes and promote strategies for nationwide installation by providing measures of their safety effectiveness. State departments of transportation (DOTs) and other transportation agencies need to have objective measures of safety effectiveness before investing in new strategies for statewide safety improvements.
Statistical methodologies are heavily used for all studies performed under the DCMF program, but these methodologies have been borrowed from various statistical fields and have limitations in capability and applicability when used for highway safety research. Accordingly, the DCMF program aims to advance highway safety evaluations and related research by establishing a sound foundation for the development of highway transportation-specific statistical methodologies in cooperation with the American Statistical Association (ASA), The Statistical and Applied Mathematical Sciences Institute (SAMSI), the U.S. Census Bureau, and other scientific communities and government agencies.
There are 41 State DOTs that provide technical feedback on safety improvements to the DCMF program and implement new safety improvements to facilitate evaluations. These States are members of the Evaluation of Low-Cost Safety Improvements Pooled Fund Study (ELCSI-PFS), which functions under the DCMF program and was established by the Federal Highway Administration (FHWA) in 2004 to develop reliable estimates of the safety effectiveness of low-cost safety improvement strategies. The initial study included four phases, had 24 State participants, and evaluated 20 safety countermeasures in 5 years. Currently, this is an open-ended study with 41 member States and has evaluated more than 60 strategies.
Duration: The DCMF program is a comprehensive, long-term safety research effort. It started in November 2012 and is an open-ended program.
Goal: The goal of this program is to identify crash modification factor (CMF) research needs, develop CMFs that meet the criteria for inclusion in the Highway Safety Manual (HSM), and promote installation of promising (low-, medium-, and high-cost) safety improvements as standard practice and to facilitate developing practical guides for implementation. This study will also address statistical methodology needs and challenges for the development, application, and assessment of the quality of CMFs.
Objective: The DCMF program will:
- Support the ELCSI–PFS efforts by complementing its research and enhancing quality of its evaluation products.
- Conduct the ELCSI-PFS annual meetings for:
- Advancing safety or research, and application.
- Building bridges between State DOTs, Federal Highway Administration (FHWA), and stakeholders.
- Improves safety culture for research and application.
- Conducting technology transfer, providing tools and analytical support (i.e., CMFs and safety performance functions (SPFs) development, and data analysis.)
- Identifying and communicating emerging safety needs.
- Building network with scientific communities (i.e., Transportation Research Board (TRB), ASA, U.S. Census Bureau) to advance goals.
- Work with ASA, SAMSI, the U.S. Census Bureau, and other scientific communities and government agencies to find new statistical methodologies and analytical tools for improving existing methodologies and tools for highway safety research.
Recent DCMF Completed Studies:
- The Development of Crash Modification Factors: Highway Safety Statistical Paper Synthesis, HRT-20-069, https://www.fhwa.dot.gov/publications/research/safety/20069/20069.pdf
- Contributing Factors for Focus Crash and Facility Types, HRT-20-052, https://www.fhwa.dot.gov/publications/research/safety/20052/20052.pdf
- Contributing Factors for Focus Crash and Facility types: Quick Reference Guide, HRT-20-053, https://www.fhwa.dot.gov/publications/research/safety/20053/20053.pdf
Completed Workshop Events:
- Workshop for 50 State DOTs practitioners: Highway Safety Statistical Paper Synthesis and Contributing Factors for Focus Crash and Facility Types on November 3, 2021.
- Workshop for highway researchers and statistician communities: Highway Safety Statistical Paper Synthesis and Contributing Factors for Focus Crash and Facility Types on November 15, 2021.
- Workshop for 50 State DOTs practitioners: Wrong Way Driving Low-Cost Safety Improvements on March 9-10, 2022.
Workshop presentations are posted on the ELCSI-PFS Publications webpage.
Highlights of the DCMF Statistical Efforts:
- FHWA is leading and coordinating efforts with ASA experts for series of workshops, and webinars to advance highway safety statistical science and tools in 2021 and 2022.
- FHWA used the USA Census Bureau data for Contributing Factors for Focus Crash and Facility Types, and validated contribution of socio-economy factors to highway focus crash types (published 2020).
- Conducted the 2016 Data Challenge of the American Statistical Association (ASA) in cooperation with the ASA, Government Statistics Section (GSS) to identify potential applicable statistical methodologies that transportation agencies could add to their transportation toolboxes and to gauge statisticians’ interest in using transportation crash data. The data set for the 2016 GSS Data Challenge was the National Highway Transportation Safety Administration’s (NHTSA) General Estimates System (GES). This data challenge resulted in five award-winning papers, now published in 2016 Special Issue (SI) of Computational Statistics (COST): Volume 36, Issue 3, September 2021 (Computational Statistics | Volume 36, issue 3 (springer.com)). The following award-winning papers (with links) were published in the COST, Vol 36, issue 3:
- Predictive Modeling of Maximum Injury Severity and Potential Economic Cost in a Car Accident Based on the General Estimates System Data
- A Hierarchical Bayes Approach to Adjust for Selection Bias in Before–After Analyses of Vision Zero Policies
- Analysis of Drowsy Driving: Exploring Subpopulation Risk with Weighted Contingency Table Tools
- A Cluster-Based Taxonomy of Bus Crashes in the United States
- An Analysis of Crash-Safety Ratings and the True Assessment of Injuries by Vehicle
- FHWA worked with the ASA, Transportation Statistical Interest Group (TSIG) and The Statistical and Applied Mathematical Sciences Institute (SAMSI) to organize and conduct a two-day "Transportation Virtual Workshop" on Dec. 7/8, 2020. The primary focus of the workshop was upon safety and autonomous vehicles, but other topics adjacent to those fields was covered.
- FHWA started in November 2018 an effort with the U.S. Census Bureau to conduct a multivariant Time Series analysis for vulnerable road users.
- FHWA worked with SAMSI to conduct a one-week workshop on Transportation Statistics at Duke University in Durham, NC, August 14–18, 2017. The goal of the workshop was to generate research and publications and identify statistical tools that would be helpful to transportation engineers. The workshop was sponsored by SAMSI, and had 29 participants. Sixteen of the participants had a background in civil engineering or transportation, 18 were statisticians or mathematicians who had worked on various aspect of transportation, and 5 had significant expertise in both areas. The outcome of this workshop was 6 statistical papers.
- FHWA worked with the Government Statistics Section (GSS) to sponsor a “Data Challenge 2016” for the ASA, Joint Statistical Meeting (JSM) 2016. The contest was open to any statistician who was interested in participating, including college students and professionals from the private or public sector. This contest challenged participants to analyze the National Highway Traffic Safety Administration’s (NHTSA) General Estimate System (GES) highway crash dataset using statistical and visualization tools and methods. Fifteen entries were discussed in two sessions, and a poster session at the JSM 2016, was held in August 2016 in Chicago, IL. Four contestants were selected for best papers and won cash prices. The papers are in the editorial process and are intended for publication in the Computational Statistics (CompStat) in 2020. CompStat is an international journal that promotes the publication of applications and methodological research in the field of computational statistics. The journal serves as a forum for computer scientists, mathematicians, and statisticians who work in a multitude of areas in statistics, including biometrics, econometrics, data analysis, graphics, simulation, algorithms, knowledge-based systems, and Bayesian computing.
- FHWA worked in 2016 with GSS and the U.S. Census Bureau to identify Time Series methodology as a useful tool for identifying recurring patterns in crashes for short- to long-term highway safety improvement applications.
- Conducted in 2014 CMF stakeholder meetings for feedback and sharing expertise and resources for State DOTs, the American Association of State Highway and Transportation Officials, National Highway Traffic Safety Administration (NHTSA), Transportation Research Board (TRB), National Cooperative Highway Research Program (NCHRP), and other stakeholders.
Research Product: The final products of the DCMF program are published by FHWA and will serve as a resource for the HSM and other technical publications.
For more information, contact:
Roya Amjadi, Research Highway Safety Specialist
Federal Highway Administration.
Office of Safety and Operations Research and Development
6300 Georgetown Pike, McLean, VA 22101
Phone: 202–493–3383, Fax: 202–493–3374