Cross-Sectional Modelling

Abstract

Purpose – Information collected from police crash reports has long been the primary source of data for the analysis of factors that determine the likelihood of a crash (crash frequency) and its resulting severity (measured in terms of the extent of injuries to vehicle occupants). Proper cross-sectional analyses techniques, covered in this chapter, are important for guiding safety policy and countermeasures.

Methodology – This chapter provides an overview of some of the more commonly used cross-sectional statistical and econometric methods, and discusses the nuances and their limitations with regard to how they are applied to typical crash-report data.

Findings – The wide variety of analytic methods available to safety researchers makes the selection of appropriate methods critical. This chapter provides important guidance for safety researchers in their choice of methodological approach.

Implications – Understanding the importance of proper model specification, unobserved heterogeneity, endogeneity and other factors covered in this chapter is extremely important in analysing safety data and must be given full consideration before any results are finalised.

Citation

Mannering, F. (2018), "Cross-Sectional Modelling", Lord, D. and Washington, S. (Ed.) Safe Mobility: Challenges, Methodology and Solutions (Transport and Sustainability, Vol. 11), Emerald Publishing Limited, Leeds, pp. 257-277. https://doi.org/10.1108/S2044-994120180000011013