TY  - JOUR
PY  - 2018//
TI  - Time series modeling in traffic safety research
JO  - Accident analysis and prevention
A1  - Lavrenz, Steven M.
A1  - Vlahogianni, Eleni I.
A1  - Gkritza, Konstantina
A1  - Ke, Yue
SP  - 368
EP  - 380
VL  - 117
IS  - 
N2  - 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.<br><br>Copyright © 2017 Elsevier Ltd. All rights reserved.<p />  <p>Language: en</p>
LA  - en
SN  - 0001-4575
UR  - http://dx.doi.org/10.1016/j.aap.2017.11.030
ID  - ref1
ER  -