Whether we use our own vehicle or use public transportation or walking when we choose an individual modes of transportation is influenced by a variety of factors. In this study, we analyze the effects of the initial condition of transportation on the selection of individuals after the passage of time. Panel data are used to develop and estimate models that can take into account dynamic changes to reflect these state dependencies. In this study, the factors affecting the choice of the individual’s modes of transportation are considered human factors such as gender, age, and income level and reflect the random effect on the assumption that there are unobserved heterogeneity such as individual tendency or habits. In order to solve the problem of the initial condition in which the initial condition without previous information is misinterpreted as the unobserved heterogeneity, we use the dynamic random effect probit model using the Heckman estimator. The results of this study suggest that there is a significant state dependence, which means that the initial condition of transport will not change over time. It is suggested that the early formation of transportation is important for the transportation policy, and the development of the policy that is compatible with the initial formation is necessary.
State Dependence; Dynamic Probit; Panel Data; Heterogenous; Heckman Estimator