Application of Latent Class Growth Model to Longitudinal Analysis of Traffic Crashes
Academic Article
Overview
Research
Identity
Additional Document Info
Other
View All
Overview
abstract
One of the most important and meaningful tasks in traffic safety is to describe how traffic crash risk changes over time. Over the past 20 years, much work has been done about this task. The recent introduction of latent class models to analyze crash data has created a need to examine how these models could be used for longitudinal data analysis. Latent class models dictate that part of the heterogeneity be attributed by grouping distinct subpopulations into a common data set. Investigation of the commonalities of the subgroups can be useful for targeting specific safety interventions. This paper describes the application of the latent class growth model (LCGM), which is tailored to longitudinal data. Analysis was accomplished with the use of data collected between 1997 and 2007 on rural, two-lane highways in Texas. Trends for all crash severities and injury crashes were examined. It was determined that the crash data could be drawn from three population subgroups for which crash risks were low, medium, and high. The results of this study showed that average shoulder width and speed limit had stronger effects at sites classified as high crash risks, whereas traffic flow had a stronger influence at sites classified as low risks. As expected, higher speed limits increased crash risk, whereas a wider shoulder width reduced risk. In conclusion, the LCGM showed good potential for use in the analysis of longitudinal data, but further research is needed.
