Abstract: The risk ratio of occupants′ death in traffic accidents is affected by many factors.In order to understand the nonlinear effects, the data of fatal crashes that obtained from the Fatality Analysis Reporting System (FARS) are adopted.After matching and filtering the data, according to death of occupants, a dataset of inherent matching pairs is obtained.The relative risk of death is set as an indicator in this paper.A model based on nonparametric logistic regression is developed to estimate the influential mechanisms of gender, age, belt usage, and seating position on fatalities.The results are expected to provide an important basis for the development of policy and the implementation of measures for traffic safety.Besides, the model is able to reveal significant influence of nonlinear effects when age is regarded as a continuous variable.The results show that the four factors of gender, age, belt usage, and seating position can significantly affect the risk of occupants′ death in traffic accidents, and the structures of inherently matched pairs are able to exclude the interference of external factors in this model.Compared with male occupants, the risk of death of female is 15.9% higher (the logarithmic value);the usage of seat belt can reduce the risk of death by 74.8% (the logarithmic value);the risk of death increases with age;and the middle and left of rear seats are the safest seating positions in a car.