Activity Number:
|
220
- Contributed Poster Presentations: Transportation Statistics Interest Group
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 4, 2020 : 10:00 AM to 2:00 PM
|
Sponsor:
|
Transportation Statistics Interest Group
|
Abstract #313410
|
|
Title:
|
A Random Effects Model to Capture Seasonal and Zonal Effects on Road Traffic Collisions
|
Author(s):
|
Nicola Hewett* and Lee Fawcett and Joe Matthews and Neil Thorpe and Karsten Kremer
|
Companies:
|
Newcastle University and Newcastle University and Newcastle University and Newcastle University and PTV Group
|
Keywords:
|
Road safety;
Transport;
Hierarchical Modeling;
Random Effects;
Spatiotemporal Model
|
Abstract:
|
Improving road safety is hugely important with the number of deaths on the world’s roads remaining unacceptably high; an estimated 1.35 million people die each year (WHO, 2018). This paper investigates the dependencies of road traffic collisions on season and zone location. The random effects model introduced uses a Bayesian hierarchical formulation to capture the seasonal and site effects separately to allow for prediction of the potential number of collisions per month for each zone through inference using Metropolis-within-Gibbs sampling. The study analyses road traffic accident rate data over zones in North Florida (accident rates per month per zone). The results show a clear seasonal effect and slight zonal effect across longitude/latitude on the number of collisions. We also include a comparison to a fixed effects model showing the increased precision of parameter estimates with their posterior standard deviations reducing by approximately a third.
|
Authors who are presenting talks have a * after their name.