An empirical assessment of fixed and random parameter logit models using crash- and non-crash-specific injury data

▶ We compare fixed & random parameter models using crash- & non-crash-specific injury data. ▶ The random-parameter logit is statistically superior to the fixed-parameter model. ▶ The individual crash-data models provide better fit compared to the proportions models. ▶ Using proportions data may be practically very close to using individual-crash data. ▶ Both approaches identify nearly the same segments with the top 5% fatality proportions.