Changes in distracted driver injury severities are analyzed.
Random parameters and latent class models are estimated.
Statistically significant temporal shifts in parameter estimates are found.
Out-of-sample simulations are conducted to predict injury probabilities.
Simulations show distracted driving injuries have become less severe over time.
Alnawmasi, N., Mannering, F., 2022. A temporal assessment of distracted driving injury severities using alternate unobserved-heterogeneity modeling approaches. Analytic Methods in Accident Research 34, 100216