Citation

Ayon BD, Ofori-Amoah B, Oh JS, Baker K. Accid. Anal. Prev. 2020; 144: e105510.

Copyright

(Copyright © 2020, Elsevier Publishing)

DOI

10.1016/j.aap.2020.105510

PMID

32563729

Abstract

Highlights

• The study develops a crash count model establishing the relationship between lake-effect snow (LES) and traffic crashes.

• The methodological approach uses Integer-valued Generalized Autoregressive Conditional Heteroscedastic (INGARCH) model.

• Negative Binomial INGARCH model outperformed Poisson INGARCH model by managing the overdispersion and autocorrelation issues.

• The model also captured the temporal correlation and allowed nonnegative covariate effects.

• Overall, the proposed method enables safety personnel to better understand the impact of LES on increased crashes.

Language: en

Keywords

Crash frequency; Unobserved heterogeneity; Lake effect snow; NB-INGARCH; Overdispersion