Elsevier

Accident Analysis & Prevention

Volume 43, Issue 5, September 2011, Pages 1666-1676
Accident Analysis & Prevention

The statistical analysis of highway crash-injury severities: A review and assessment of methodological alternatives

https://doi.org/10.1016/j.aap.2011.03.025Get rights and content

Abstract

Reducing the severity of injuries resulting from motor-vehicle crashes has long been a primary emphasis of highway agencies and motor-vehicle manufacturers. While progress can be simply measured by the reduction in injury levels over time, insights into the effectiveness of injury-reduction technologies, policies, and regulations require a more detailed empirical assessment of the complex interactions that vehicle, roadway, and human factors have on resulting crash-injury severities. Over the years, researchers have used a wide range of methodological tools to assess the impact of such factors on disaggregate-level injury-severity data, and recent methodological advances have enabled the development of sophisticated models capable of more precisely determining the influence of these factors. This paper summarizes the evolution of research and current thinking as it relates to the statistical analysis of motor-vehicle injury severities, and provides a discussion of future methodological directions.

Highlights

► This paper provides a state-of-the-practice review of statistical methods for analyzing crash-injury severity data. ► Methodological issues germane to the analysis of injury severity data are discussed. ► Appropriate techniques for addressing these methodological issues are described. ► These techniques range from simple, binary outcome models to more sophisticated models allowing for heterogeneous effects and correlated error terms. ► Areas of opportunity for future research are highlighted based upon advances in computing and richer data sources.

Introduction

Due to the incredible economic and emotional burden traffic crashes impose on society, vehicle manufacturers and transportation agencies are under constant pressure to implement improvements in vehicle and roadway design to reduce the frequency of traffic crashes and the degree of injury sustained by those involved in crashes. It is important to note that reducing crash frequency and reducing crash-injury severity may necessitate different strategic approaches. For example, limiting rates of curvature or superelevation are policies aimed at reducing the potential for crashes while crashworthy median barriers and roadway signs are designed to reduce the level of injury sustained in the event such objects are struck during a crash. In addition to roadway features, advances in vehicle design also have the potential to reduce crash frequency (electronic stability control and anti-lock brakes) or severity (safety belts or airbags) while driver-training programs and targeted enforcement may have potential in reducing both frequency and severity.

The development of effective countermeasures requires a thorough understanding of the factors that affect the likelihood of a crash occurring or, given that a crash has occurred, the characteristics that may mitigate or exacerbate the degree of injury sustained by crash-involved road users. To gain such an understanding, safety researchers have applied a wide variety of methodological techniques over the years. While these various methodological applications have undoubtedly provided new insights, the fundamental characteristics of crash data often result in methodological limitations that are not fully understood or accounted for.

Lord and Mannering (2010) recently provided an assessment of the characteristics of crash-frequency data and the methodological alternatives and limitations for examining such data. The intent of this paper is to provide a similar assessment of data characteristics and methodological alternatives and limitations for examining crash-severity data, highlighting the strengths and weaknesses of each approach and identifying areas of opportunity for future research.1

Section snippets

Characteristics of crash-injury severity data and methodological issues

Injury-severity data are generally represented by discrete categories such as fatal injury or killed, incapacitating injury, non-incapacitating, possible injury, and property damage only.2

Methodological approaches

A variety of methodological techniques have been applied to analyze crash-severity data. The statistical methods employed by researchers have primarily relied on the nature of the dependent variable and various methodological issues associated with the data, as discussed previously. The dependent variables of existing crash severity models are typically either a binary response outcome (e.g., injury or non-injury) or a multiple response outcome (e.g., fatality, disabling injury, evident injury,

Directions for future research

The preceding discussion shows that a wide variety of methodological approaches have been used to study crash-injury severities and that there has been a steady methodological evolution that has sought to overcome known deficiencies in analysis and provide new insights. For example, issues relating to the trade-offs between ordered and unordered models have begun to be addressed and recent applications of random parameter and multi-state models have opened up new ways to account for unobserved

References (130)

  • L.-Y. Chang et al.

    Analysis of traffic injury severity: an application of non-parametric classification tree techniques

    Accident Analysis and Prevention

    (2006)
  • M. de Lapparent

    Willingness to use safety belt and levels of injury in car accidents

    Accident Analysis and Prevention

    (2008)
  • D. Delen et al.

    Identifying significant predictors of injury severity in traffic accidents using a series of artificial neural networks

    Accident Analysis and Prevention

    (2006)
  • S. Dissanayake et al.

    Factors influential in making an injury severity difference to older drivers involved in fixed object—passenger car crashes

    Accident Analysis and Prevention

    (2002)
  • K. El-Basyouny et al.

    Collision prediction models using multivariate Poisson-lognormal regression

    Accident Analysis and Prevention

    (2009)
  • N. Eluru et al.

    A joint econometric analysis of seat belt use and crash-related injury severity

    Accident Analysis and Prevention

    (2007)
  • N. Eluru et al.

    A mixed generalized ordered response model for examining pedestrian and bicyclist injury severity level in traffic crashes

    Accident Analysis and Prevention

    (2008)
  • C. Farmer et al.

    Two-vehicle side impact crashes: the relationship of vehicle and crash characteristics to injury severity

    Accident Analysis and Prevention

    (1997)
  • P. Garder

    Segment characteristics and severity of head-on crashes on two-lane rural highways in Maine

    Accident Analysis and Prevention

    (2006)
  • R. Gray et al.

    Injury severity analysis of accidents involving young male drivers in Great Britain

    Journal of Safety Research

    (2008)
  • E. Hauer

    The frequency–severity indeterminacy

    Accident Analysis and Prevention

    (2006)
  • J. Hausman et al.

    Misclassification of the dependent variable in a discrete-response setting

    Journal of Econometrics

    (1998)
  • J. Holdridge et al.

    The crash severity impacts of fixed roadside objects

    Journal of Safety Research

    (2005)
  • W. Hu et al.

    Median barrier crash severity: some new insights

    Accident Analysis and Prevention

    (2010)
  • S. Islam et al.

    Driver aging and its effect on male and female single-vehicle accident injuries: some additional evidence

    Journal of Safety Research

    (2006)
  • S. Jung et al.

    Rainfall effect on single-vehicle crash severities using polychotomous response models

    Accident Analysis and Prevention

    (2010)
  • A. Khorashadi et al.

    Differences in rural and urban driver-injury severities in accidents involving large-trucks: an exploratory analysis

    Accident Analysis and Prevention

    (2005)
  • J.-K. Kim et al.

    Bicyclist injury severities in bicycle–motor vehicle accidents

    Accident Analysis and Prevention

    (2007)
  • J.-K. Kim et al.

    Age and pedestrian injury severity in motor-vehicle crashes: a heteroskedastic logit analysis

    Accident Analysis and Prevention

    (2008)
  • J.-K. Kim et al.

    A note on modeling pedestrian injury severity in motor vehicle crashes with the mixed logit model

    Accident Analysis and Prevention

    (2010)
  • K. Kockelman et al.

    Driver injury severity: an application of ordered probit models

    Accident Analysis and Prevention

    (2002)
  • D.W. Kononen et al.

    Identification and validation of a logistic regression model for predicting serious injuries associated with motor vehicle crashes

    Accident Analysis and Prevention

    (2011)
  • Y. Kweon et al.

    Overall injury risk to different drivers: combining exposure, frequency, and severity models

    Accident Analysis and Prevention

    (2003)
  • C. Lee et al.

    Comprehensive analysis of vehicle-pedestrian crashes at intersections in Florida

    Accident Analysis and Prevention

    (2005)
  • C. Lee et al.

    Presence of passengers: does it increase or reduce driver's crash potential?

    Accident Analysis and Prevention

    (2008)
  • J. Lee et al.

    Impact of roadside features on the frequency and severity of run-off-roadway accidents: an empirical analysis

    Accident Analysis and Prevention

    (2002)
  • J.D. Lemp et al.

    Analysis of large truck crash severity using heteroskedastic ordered probit models

    Accident Analysis and Prevention

    (2011)
  • D. Lord et al.

    The statistical analysis of crash-frequency data: a review and assessment of methodological alternatives

    Transportation Research Part A

    (2010)
  • J. Ma et al.

    A multivariate Poisson-lognormal regression model for prediction of crash counts by severity, using Bayesian methods

    Accident Analysis and Prevention

    (2008)
  • N. Malyshkina et al.

    Markov switching multinomial logit model: an application to accident-injury severities

    Accident Analysis and Prevention

    (2009)
  • N. Malyshkina et al.

    Empirical assessment of the impact of highway design exceptions on the frequency and severity of vehicle accidents

    Accident Analysis and Prevention

    (2010)
  • J. Milton et al.

    Highway accident severities and the mixed logit model: an exploratory empirical analysis

    Accident Analysis and Prevention

    (2008)
  • D.N. Moore et al.

    Mixed logit analysis of bicyclist injury severity resulting from motor vehicle crashes at intersection and non-intersection locations

    Accident Analysis and Prevention

    (2011)
  • A. Morgan et al.

    The effects of road-surface conditions, age, and gender on driver-injury severities

    Accident Analysis and Prevention

    (2011)
  • A.V. Moudon et al.

    The risk of pedestrian injury and fatality in collisions with motor vehicles, a social ecological study of state routes and city streets in King County, Washington

    Accident Analysis and Prevention

    (2011)
  • C. O’Donnell et al.

    Predicting the severity of motor vehicle accident injuries using models of ordered multiple choice

    Accident Analysis and Prevention

    (1996)
  • C. Pai

    Exploring motorcyclist injury severity in approach-turn collisions at T-junctions: focusing on the effects of driver's failure to yield and junction control measures

    Accident Analysis and Prevention

    (2008)
  • C. Pai

    Motorcyclist injury severity in angle crashes at T-junctions: identifying significant factors and analyzing what made motorists fail to yield to motorcycles

    Safety Science

    (2009)
  • C. Pai et al.

    An analysis of motorcyclist injury severity under various traffic control measures at three-legged junctions in the UK

    Safety Science

    (2007)
  • R. Paleti et al.

    Examining the influence of aggressive driving behavior on driver injury severity in traffic crashes

    Accident Analysis and Prevention

    (2010)
  • Cited by (762)

    • Network-wide road crash risk screening: A new framework

      2024, Accident Analysis and Prevention
    View all citing articles on Scopus
    View full text