JSM 2015 Preliminary Program

Online Program Home
My Program

Abstract Details

Activity Number: 172
Type: Topic Contributed
Date/Time: Monday, August 10, 2015 : 10:30 AM to 12:20 PM
Sponsor: Transportation Statistics Interest Group
Abstract #314946 View Presentation
Title: Change-Points Detection in Driving Risk Allowing for Varying Change-Points Among Subjects by Parametric Latent Class Modeling
Author(s): Qing Li* and Feng Guo
Companies: Virginia Tech and Virginia Tech
Keywords: recurrent-event ; change-point detection ; Latent class modeling
Abstract:

This research developed recurrent-event change-point models to detect the time when driving risk changes significantly for novice teenager drivers. Teenage drivers who have been newly licensed are exposed to significantly higher accident risk than beyond the initial licensure period. Previous studies showed that driving risk changed around six months after licensure. One common issue is that most existing research aggregated data into pre-defined time intervals for analysis, e.g., three-month cluster, which reduced the time resolution. Furthermore, limited research has been conducted to evaluate the change in driving risk in terms of driving time. We proposed models to allow change-points to vary among drivers with latent clustering using a parametric Bayesian approach, considering that clusters over change-point might exist among the teenagers. A Dirichlet Distribution prior was used. Monte Carlo Markov Chain algorithm was developed to sample from the posterior distribution. Model selection will be conducted to choose the best number of clusters.


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

Back to the full JSM 2015 program





For program information, contact the JSM Registration Department or phone (888) 231-3473.

For Professional Development information, contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

2015 JSM Online Program Home