Mixed Logit Model Approach to Investigate Effects of Age on Driver Injury Severity in Single-Vehicle Accidents

This research develops a mixed logit model of driver-injury severity in single-vehicle accidents to investigate in particular the effect of driver age. Using data for single-vehicle crashes in 2003–2004 from the Statewide Integrated Traffic Records System of the California Highway Patrol, several factors were found to significantly increase the probability of fatal injury for drivers in single-vehicle crashes: older driver 65+, male driver, drunk driving, unsafe speed, older driver driving an older vehicle, and darkness without streetlights. It was also shown that older drivers (aged 65 and over) lead to a uniform distributed random parameter for fatal injury and gender accounts for heterogeneity for new to 5 year old vehicles, with males linked to an increase in the probability of fatal injury in a newer vehicle but with females linked to a decrease.