Psychological factors (latent variables) play a significant role in formation of travel mode choice behavior preference. An integrated choice and latent variable (ICLV) model, which integrates structural equation model (SEM) and mixed-logit (MXL) is proposed in this paper to predict the mode choice behavior under the impacts of congestion pricing. The model is estimated using stated preference travel mode choice data of over 1000 automobile travelers (including more habitual automobile travelers and less habitual automobile travelers) collected in Beijing inner districts. Results from the empirical application shows that the goodness of fit for the integrated choice and latent variable model is higher than that of the traditional mixed-logit model, which proves that latent variables have an obvious impact on mode choice behavior under the impacts of congestion pricing. This study provides insights for designing congestion pricing and illustrates the importance of developing complementary modules that target psychological factors to effectively promote mode shifts from automobile to sustainable travel modes in China.

CICTP