A clustering regression approach: A comprehensive injury severity analysis of pedestrian–vehicle crashes in New York, US and Montreal, Canada

Abstract

Understanding the underlying relationship between pedestrian injury severity outcomes and factors leading to more severe injuries is very important in addressing the problem of pedestrian safety. This research combines data mining and statistical regression methods to identify the main factors associated with the levels of pedestrian injury severity outcomes. This work relies on the analysis of two unique pedestrian injury severity datasets from New York City, US (2002–2006) and the City of Montreal, Canada (2003–2006). General injury severity models were estimated for each dataset and for sub-populations obtained through clustering analysis. This paper shows how the segmentation of the accident datasets helps to better understand the complex relationship between the injury severity outcomes and the contribution of geometric, built environment and socio-demographic factors. While using the same methodology for the two datasets, different techniques were tested. Within the New York dataset, a latent class with ordered probit method provides the best results. However, for Montreal, K-means with a multinomial logit model proves most appropriate. Among other results, it was found that pedestrian age, location type, driver age, vehicle type, driver alcohol involvement, lighting conditions, and several built environment characteristics influence the likelihood of fatal crashes. Finally, the research provides recommendations for policy makers, traffic engineers, and law enforcement in order to reduce the severity of pedestrian–vehicle collisions.