An Empirical Study of Influence Relationship on Traffic Culture Index(TCI) utilizing PLS-SEM(Structural Equation Modeling)

The traffic culture index is used as a major index in evaluating the traffic safety services of local governments and also serve as important data for the planning and implementation of traffic safety services. However, as the traffic culture index gradually became a standard for comparison among local governments, in part, certain cases arose which questioned the grounds for selecting variables for the index and the validity of the index in terms of its influential relationship between evaluation items. This study analyzed the index's influential relationship by utilizing a PLS structural equation model based on the evaluation results of the 2011 traffic culture index. A variable-linking model was created which recognized the relativity taking into account of the indirect effects between latent variables and this model was proven to be a model suitable in explaining the traffic culture index with a 97.8% explanation power. It was found that traffic safety(0.530), driving behavior(0.527), pedestrian behavior(0.187) and vulnerable road users(0.147), in such order, had an effect on the traffic culture index. It was also found that human casualties due to traffic accidents under "traffic safety" and traffic light compliance rate under "driving behavior" had an important effect. The study showed that motor vehicle share in illegal parking in school zones did not have a valid explanation power regarding "vulnerable road users".

PLS구조방정식 모형을 활용한 교통문화지수의 영향관계 실증연구