Ranking Spatial and Temporal Hotspots for Road Safety Interventions Using a Nonlinear Aggregation Approach

Research output: Contribution to conferencePaper

Abstract

In recent years, the concept of a composite performance index, brought from economic and business statistics, has gained popularity in the field of road safety. The construction of the Composite Safety Performance Index (CSPI) involves the following key steps: the selection of the most appropriate indicators to be aggregated and the method used to aggregate them.

Over the last decade, various aggregation methods for estimating the CSPI have been suggested in the literature. However, recent studies indicates that most of these methods suffer from many deficiencies at both the theoretical and operational level; these include the correlation and compensability between indicators, as well as their high “degree of freedom” which enables one to readily manipulate them to produce desired outcomes.

The purpose of this study is to introduce an alternative aggregation method for the estimation of the CSPI, which is free from the aforementioned deficiencies. In contrast with the current aggregation methods, which generally use linear combinations of road safety indicators to estimate a CSPI, the approach advocated in this study is based on non-linear combinations of indicators and can be summarized into the following two main steps: the pairwise comparison of road safety indicators and the development of marginal and composite road safety performance functions. The introduced method has been successfully applied to identify and rank temporal and spatial hotspots for Northern Ireland, using road traffic collision data recorded in the UK STATs19 database. The obtained results highlight the promising features of the proposed approach including its stability and consistency, which enables significantly reduced deficiencies associated with the current aggregation methods. Progressively, the introduced method could evolve into an intelligent support system for road safety assessment.
Original languageEnglish
Number of pages18
Publication statusPublished - 2014
EventTransportation Research Board (TRB) 93rd Annual Meeting - Washington DC, United States
Duration: 12 Jan 201416 Jan 2014

Conference

ConferenceTransportation Research Board (TRB) 93rd Annual Meeting
CountryUnited States
CityWashington DC
Period12/01/201416/01/2014

Fingerprint Dive into the research topics of 'Ranking Spatial and Temporal Hotspots for Road Safety Interventions Using a Nonlinear Aggregation Approach'. Together they form a unique fingerprint.

  • Cite this

    Coll, B., Moutari, S., & Marshall, A. H. (2014). Ranking Spatial and Temporal Hotspots for Road Safety Interventions Using a Nonlinear Aggregation Approach. Paper presented at Transportation Research Board (TRB) 93rd Annual Meeting, Washington DC, United States.