Statistical approaches for assessing the effectiveness of safety devices use in preventing head injuries from motorcycle crashes

This study investigates the effectiveness of motorcyclist's helmet use in preventing head injuries using the binary regression model and the mosaic plots. The association between head injuries and helmet use was modeled by applying binary logistic regression. The fitted model to the Changhua city accidents dataset has revealed that wearing a helmet had a positive impact in preventing the motorcyclist from sustaining head injuries in road traffic crashes. In addition to the association between head injuries and non-wearing of helmet, we found that alcohol impairment risk factor was increasing the likelihood of head injuries during crashes. Besides, the results were supported by using the mosaic plots which provide a visualization of the joint effect of Alcohol, helmet and heading injury for motorcyclists involved in crashes.