Online Program Home
My Program

Abstract Details

Activity Number: 647
Type: Topic Contributed
Date/Time: Thursday, August 4, 2016 : 8:30 AM to 10:20 PM
Sponsor: Government Statistics Section
Abstract #319362 View Presentation
Title: Identifying Risk Factors for Interstate Crashes Using Spatial Statistics
Author(s): Kaitlin Gibson* and Matthew J. Heaton
Companies: Brigham Young University and Brigham Young University
Keywords: point process ; HIghway Safety Information System ; Bayesian
Abstract:

The goal of systemic roadway safety analyses is to identify roadway characteristics (called "risk factors") associated with an increased occurrence of car crashes. However, the statistical methods generally used in these analyses often fail to take into account the spatial correlation between road segments and are thus not appropriate for the data. In addition, traditional spatial methods are unsuitable for the data used in roadway analyses, since these methods estimate the correlation between two points based on straight-line distance rather than a measure such as driving distance, which is more appropriate for roadway data. Data for this project were obtained from the Highway Safety Information System (HSIS) database, which contains information such as traffic volume, roadway characteristics, and number and type of crashes for each segment of state-owned road in several states. In this project, we implement a point pattern Poisson process to model the locations of crashes along an interstate network -specifically five interstate highways in Washington-and make inference for the effect of risk factors on crash location.


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

Back to the full JSM 2016 program

 
 
Copyright © American Statistical Association