Search results

Purpose – This chapter provides an overview of issues related to analysing crash data characterised by excess zero responses and/or long tails and how to overcome these problems. Factors affecting excess zeros and/or long tails are discussed, as well as how they can bias the results when traditional distributions or models are used. Recently introduced multi-parameter distributions and models developed specifically for such datasets are described. The chapter is intended to guide readers on how to properly analyse crash datasets with excess zeros and long or heavy tails.

Methodology – Key references from the literature are summarised and discussed, and two examples detailing how multi-parameter distributions and models compare with the negative binomial distribution and model are presented.

Findings – In the event that the characteristics of the crash dataset cannot be changed or modified, recently introduced multi-parameter distributions and models can be used efficiently to analyse datasets characterised by excess zero responses and/or long tails. They offer a simpler way to interpret the relationship between crashes and explanatory variables, while providing better statistical performance in terms of goodness-of-fit and predictive capabilities.

Research implications – Multi-parameter models are expected to become the next series of traditional distributions and models. The research on these models is still ongoing.

Practical implications – With the advancement of computing power and Bayesian simulation methods, multi-parameter models can now be easily coded and applied to analyse crash datasets characterised by excess zero responses and/or long tails.

Purpose – The purpose of this chapter is to review the methodological and empirical underpinnings of transport network screening, or management, as it relates to improving road safety. As jurisdictions around the world are charged with transport network management in order to reduce externalities associated with road crashes, identifying potential blackspots or hotspots is an important if not critical function and responsibility of transport agencies.

Methodology – Key references from within the literature are summarised and discussed, along with a discussion of the evolution of thinking around hotspot identification and management. The theoretical developments that correspond with the evolution in thinking are provided, sprinkled with examples along the way.

Findings – Hotspot identification methodologies have evolved considerably over the past 30 or so years, correcting for methodological deficiencies along the way. Despite vast and significant advancements, identifying hotspots remains a reactive approach to managing road safety – relying on crashes to accrue in order to mitigate their occurrence. The most fruitful directions for future research will be in the establishment of reliable relationships between surrogate measures of road safety – such as ‘near misses’ – and actual crashes – so that safety can be proactively managed without the need for crashes to accrue.

Research implications – Research in hotspot identification will continue; however, it is likely to shift over time to both closer to ‘real-time’ crash risk detection and considering safety improvements using surrogate measures of road safety – described in Chapter 17.

Practical implications – There are two types of errors made in hotspot detection – identifying a ‘risky’ site as ‘safe’ and identifying a ‘safe’ site as ‘risky’. In the former case no investments will be made to improve safety, while in the latter case ineffective or inefficient safety improvements could be made. To minimise these errors, transport network safety managers should be applying the current state of the practice methods for hotspot detection. Moreover, transport network safety managers should be eager to transition to proactive methods of network safety management to avoid the need for crashes to occur. While in its infancy, the use of surrogate measures of safety holds significant promise for the future.