Evaluation of Data Needs, Crash Surrogates, and Analysis Methods to Address Lane Departure Research Questions Using Naturalistic Driving Study Data

Abstract

A large component of the safety research undertaken in the second Strategic Highway Research Program (SHRP 2) is aimed at reducing injuries and fatalities that result from highway crashes. Through a naturalistic driving study (NDS) involving more than 3,000 volunteer drivers, SHRP 2 expects to learn more about how individual driver behavior interacts with vehicle and roadway characteristics. In anticipation of the large volume of data to be collected during the SHRP 2 NDS, several projects were conducted to demonstrate that it is possible to use existing NDS data and data from other sources to further the understanding of the risk factors associated with road crashes. More specifically, the four projects conducted under the title Development of Analysis Methods Using Recent Data examined the statistical relationship between surrogate measures of collisions (conflicts, critical incidents, near collisions, or roadside encroachment) and actual collisions. This report presents the results of one of these projects, undertaken by the Institute for Transportation, Iowa State University. It documents the second phase of a two-phase project under SHRP 2 Safety Project S01E. The primary objective of this project was to investigate the feasibility of using NDS data to increase our understanding of lane departure crashes. Research questions specific to lane departure were identified, and data requirements to answer these research questions were determined. Methodologies for selecting and applying crash surrogates specific to lane departure were evaluated. Finally, four analytical approaches were investigated: data mining using classification and regression tree analysis; simple odds ratio and logistic regression; logistic regression for correlated data that accounts for repeated sampling among observations; and time series analysis. The report discusses the advantages and limitations for each of these approaches. It will provide useful information for analysts of the SHRP 2 NDS data.