Bayesian Hierarchical Poisson Regression Models: An Application to a Driving Study With Kinematic Events

• Published in: Journal of the American Statistical Association Vol. 108; no. 502; pp. 494 - 503
• Main Authors: Kim, Sungduk, Chen, Zhen, Zhang, Zhiwei, Simons-Morton, Bruce G, Albert, Paul S
• Format: Journal Article
• Language: English
• Published: United States Taylor & Francis Group 01.06.2013; Taylor & Francis Group, LLC; Taylor & Francis Ltd
• Subjects: adolescents; Algorithms; Applications and Case Studies; autocorrelation; Bayesian analysis; Kinematics; Longitudinal count data; Markov analysis; Markov chain; Monte Carlo simulation; Over-dispersion; Poisson distribution; Random effect; Regression analysis; risk; Serial correlation; Statistics; Teenage driving; Teenagers; United States; variance; United States; Random effect; Serial correlation; Longitudinal Count Data; Teenage driving; Over-dispersion
• ISSN: 1537-274X; 0162-1459; 1537-274X
• DOI: 10.1080/01621459.2013.770702

Although there is evidence that teenagers are at a high risk of crashes in the early months after licensure, the driving behavior of these teenagers is not well understood. The Naturalistic Teenage Driving Study (NTDS) is the first U.S. study to document continuous driving performance of newly licensed teenagers during their first 18 months of licensure. Counts of kinematic events such as the number of rapid accelerations are available for each trip, and their incidence rates represent different aspects of driving behavior. We propose a hierarchical Poisson regression model incorporating overdispersion, heterogeneity, and serial correlation as well as a semiparametric mean structure. Analysis of the NTDS data is carried out with a hierarchical Bayesian framework using reversible jump Markov chain Monte Carlo algorithms to accommodate the flexible mean structure. We show that driving with a passenger and night driving decrease kinematic events, while having risky friends increases these events. Further the within-subject variation in these events is comparable to the between-subject variation. This methodology will be useful for other intensively collected longitudinal count data, where event rates are low and interest focuses on estimating the mean and variance structure of the process. Supplementary materials for this article are available online.