TY - JOUR
T1 - Injury severity analysis of commercially-licensed drivers in single-vehicle crashes
T2 - Accounting for unobserved heterogeneity and age group differences
AU - Osman, Mohamed
AU - Mishra, Sabyasachee
AU - Paleti, Rajesh
N1 - Publisher Copyright:
© 2018 Elsevier Ltd
PY - 2018/9
Y1 - 2018/9
N2 - This study analyzes the injury severity of commercially-licensed drivers involved in single-vehicle crashes. Considering the discrete ordinal nature of injury severity data, the ordered response modeling framework was adopted. The moderating effect of driver's age on all other factors was examined by segmenting the parameters by driver's age group. Additional effects of the different drivers’ age groups are taken into consideration through interaction terms. Unobserved heterogeneity of the different covariates was investigated using the Mixed Generalized Ordered Response Probit (MGORP) model. The empirical analysis was conducted using four years of the Highway Safety Information System (HSIS) data that included 6247 commercially-licensed drivers involved in single-vehicle crashes in the state of Minnesota. The MGORP model elasticity effects indicate that key factors that increase the likelihood of severe crashes for commercially-licensed drivers across all age groups include: lack of seatbelt usage, collision with a fixed object, speeding, vehicle age of 11 years or more, wind, night time, weekday, and female drivers. Also, the effects of several covariates were found to vary across different age groups.
AB - This study analyzes the injury severity of commercially-licensed drivers involved in single-vehicle crashes. Considering the discrete ordinal nature of injury severity data, the ordered response modeling framework was adopted. The moderating effect of driver's age on all other factors was examined by segmenting the parameters by driver's age group. Additional effects of the different drivers’ age groups are taken into consideration through interaction terms. Unobserved heterogeneity of the different covariates was investigated using the Mixed Generalized Ordered Response Probit (MGORP) model. The empirical analysis was conducted using four years of the Highway Safety Information System (HSIS) data that included 6247 commercially-licensed drivers involved in single-vehicle crashes in the state of Minnesota. The MGORP model elasticity effects indicate that key factors that increase the likelihood of severe crashes for commercially-licensed drivers across all age groups include: lack of seatbelt usage, collision with a fixed object, speeding, vehicle age of 11 years or more, wind, night time, weekday, and female drivers. Also, the effects of several covariates were found to vary across different age groups.
UR - http://www.scopus.com/inward/record.url?scp=85047222096&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85047222096&partnerID=8YFLogxK
U2 - 10.1016/j.aap.2018.05.004
DO - 10.1016/j.aap.2018.05.004
M3 - Article
C2 - 29784448
AN - SCOPUS:85047222096
SN - 0001-4575
VL - 118
SP - 289
EP - 300
JO - Accident Analysis and Prevention
JF - Accident Analysis and Prevention
ER -