Are estimates of crash modification factors mis-specified?

Robert Noland, Yemi Adediji

Research output: Contribution to journalArticle

Abstract

Transportation planners and traffic engineers are using crash modification factors to evaluate how changes in road geometry and design features can reduce crashes. Crash modification factors are typically estimated based on segmenting links on a highway and associating with geometric features. This allows statistical methods to be applied to the data. Concurrently there is a stream of research that relies on spatial units of analysis to examine crashes; these typically use broad features of the road network combined with socio-economic and demographic factors that are associated with crashes. In this paper, we examine whether omission of these spatial factors in a link-based model results in mis-specified models, in particular, omitted variable bias. Our results suggest that there is no change in coefficient signs, but that there is a reduction in the magnitude of estimates, suggesting that omitted variable bias exists. The sign of spatial variables differ substantially when combined with a link-based model. We also find substantial variability in coefficient estimates, and discuss the implications of these results for the use of crash modification factors in cost-benefit analysis of road safety projects.

Original languageEnglish (US)
Pages (from-to)29-37
Number of pages9
JournalAccident Analysis and Prevention
Volume118
DOIs
StatePublished - Sep 1 2018

Fingerprint

Spatial Analysis
Cost-Benefit Analysis
Economics
Demography
Safety
Research
road
Cost benefit analysis
cost-benefit analysis
trend
road network
demographic factors
statistical method
economic factors
engineer
Statistical methods
mathematics
traffic
Engineers
Geometry

All Science Journal Classification (ASJC) codes

  • Human Factors and Ergonomics
  • Safety, Risk, Reliability and Quality
  • Public Health, Environmental and Occupational Health

Keywords

  • Crash modification factors
  • Geometric design
  • Spatial analysis

Cite this

@article{d88183ae0270441785395e575086ae36,
title = "Are estimates of crash modification factors mis-specified?",
abstract = "Transportation planners and traffic engineers are using crash modification factors to evaluate how changes in road geometry and design features can reduce crashes. Crash modification factors are typically estimated based on segmenting links on a highway and associating with geometric features. This allows statistical methods to be applied to the data. Concurrently there is a stream of research that relies on spatial units of analysis to examine crashes; these typically use broad features of the road network combined with socio-economic and demographic factors that are associated with crashes. In this paper, we examine whether omission of these spatial factors in a link-based model results in mis-specified models, in particular, omitted variable bias. Our results suggest that there is no change in coefficient signs, but that there is a reduction in the magnitude of estimates, suggesting that omitted variable bias exists. The sign of spatial variables differ substantially when combined with a link-based model. We also find substantial variability in coefficient estimates, and discuss the implications of these results for the use of crash modification factors in cost-benefit analysis of road safety projects.",
keywords = "Crash modification factors, Geometric design, Spatial analysis",
author = "Robert Noland and Yemi Adediji",
year = "2018",
month = "9",
day = "1",
doi = "10.1016/j.aap.2018.05.017",
language = "English (US)",
volume = "118",
pages = "29--37",
journal = "Accident Analysis and Prevention",
issn = "0001-4575",
publisher = "Elsevier Limited",

}

Are estimates of crash modification factors mis-specified? / Noland, Robert; Adediji, Yemi.

In: Accident Analysis and Prevention, Vol. 118, 01.09.2018, p. 29-37.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Are estimates of crash modification factors mis-specified?

AU - Noland, Robert

AU - Adediji, Yemi

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Transportation planners and traffic engineers are using crash modification factors to evaluate how changes in road geometry and design features can reduce crashes. Crash modification factors are typically estimated based on segmenting links on a highway and associating with geometric features. This allows statistical methods to be applied to the data. Concurrently there is a stream of research that relies on spatial units of analysis to examine crashes; these typically use broad features of the road network combined with socio-economic and demographic factors that are associated with crashes. In this paper, we examine whether omission of these spatial factors in a link-based model results in mis-specified models, in particular, omitted variable bias. Our results suggest that there is no change in coefficient signs, but that there is a reduction in the magnitude of estimates, suggesting that omitted variable bias exists. The sign of spatial variables differ substantially when combined with a link-based model. We also find substantial variability in coefficient estimates, and discuss the implications of these results for the use of crash modification factors in cost-benefit analysis of road safety projects.

AB - Transportation planners and traffic engineers are using crash modification factors to evaluate how changes in road geometry and design features can reduce crashes. Crash modification factors are typically estimated based on segmenting links on a highway and associating with geometric features. This allows statistical methods to be applied to the data. Concurrently there is a stream of research that relies on spatial units of analysis to examine crashes; these typically use broad features of the road network combined with socio-economic and demographic factors that are associated with crashes. In this paper, we examine whether omission of these spatial factors in a link-based model results in mis-specified models, in particular, omitted variable bias. Our results suggest that there is no change in coefficient signs, but that there is a reduction in the magnitude of estimates, suggesting that omitted variable bias exists. The sign of spatial variables differ substantially when combined with a link-based model. We also find substantial variability in coefficient estimates, and discuss the implications of these results for the use of crash modification factors in cost-benefit analysis of road safety projects.

KW - Crash modification factors

KW - Geometric design

KW - Spatial analysis

UR - http://www.scopus.com/inward/record.url?scp=85047768990&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047768990&partnerID=8YFLogxK

U2 - 10.1016/j.aap.2018.05.017

DO - 10.1016/j.aap.2018.05.017

M3 - Article

C2 - 29860129

AN - SCOPUS:85047768990

VL - 118

SP - 29

EP - 37

JO - Accident Analysis and Prevention

JF - Accident Analysis and Prevention

SN - 0001-4575

ER -