Online Program Home
  My Program

Abstract Details

Activity Number: 629 - Advanced Topics in Statistics Education
Type: Contributed
Date/Time: Thursday, August 3, 2017 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Education
Abstract #324499 View Presentation
Title: Time Series Methodologies May Save Lives on Highways
Author(s): Roya Amjadi*
Companies: Federal Highway Administration
Keywords: Highway Crash ; Time Series ; Highway Safety ; Highway Crash Data

Highway crashes have recurring patterns with time, and may benefit from use of Time Series methodologies, and in specific, Seasonal Adjustment's predictive models to enhance highway safety and operation efforts for reducing crash fatalities/injuries. These crashes have patterns that repeat over fixed period of time. In some States the night-time, pedestrian, motorcycle, bicycle, rollover, fixed object, and winter crashes show weekly, monthly, or seasonal patterns. Contributing factors such as light condition, age group, weather, Season, economy, and others impact these variations. Modelling these patterns for highway safety performance, and removing the high-frequency seasonality will be a key to understanding the underlying dynamics for highway crashes. Current highway crash modelling practices ignore contributions of variables such as vehicle type, population, age, and income while data resources are available for correctly accounting for these variables. Scientific identification of major highway safety concerns will assist practitioners to identify effective safety countermeasures, and improve highway safety.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2017 program

Copyright © American Statistical Association