Time series modeling in traffic safety research. (August 2018)

• Record Type: Journal Article
• Authors: Lavrenz, Steven M.; Vlahogianni, Eleni I.; Gkritza, Konstantina; Ke, Yue
• Is Part Of: Accident analysis and prevention. Volume 117(2018)
• Page Start: 368
• Page End: 380
• Publication Date: 2018-08
• Subjects: Traffic safety -- Time series analysis -- Statistical methods -- Econometric methods -- Computational intelligence models -- Crash data modeling; Accidents -- Prevention -- Periodicals; Accident Prevention -- Periodicals; Accidents -- Prévention -- Périodiques; 363.106
• DOI: 10.1016/j.aap.2017.11.030
• Languages: English
• ISSNs: 0001-4575

Abstract

Highlights: Time series models are underutilized in traffic safety literature. Reasons for limited use include limited understanding and lack of proper data. A critical review of time series models found in the traffic safety literature is provided. Successful applications have been on driver behavior and roadway environment. High-resolution and connected data hold promise for time series modeling in traffic safety. Abstract: The use of statistical models for analyzing traffic safety (crash) data has been well-established. However, time series techniques have traditionally been underrepresented in the corresponding literature, due to challenges in data collection, along with a limited knowledge of proper methodology. In recent years, new types of high-resolution traffic safety data, especially in measuring driver behavior, have made time series modeling techniques an increasingly salient topic of study. Yet there remains a dearth of information to guide analysts in their use. This paper provides an overview of the state of the art in using time series models in traffic safety research, and discusses some of the fundamental techniques and considerations in classic time series modeling. It also presents ongoing and future opportunities for expanding the use of time series models, and explores newer modeling techniques, including computational intelligence models, which hold promise in effectively handling ever-larger data sets. The information contained herein is meant to guide safety researchers in understanding this broad area of transportation data analysis, and provide a framework for understanding safety trends that can influence policy-making.