考虑潜变量的大学生返程出行方式选择行为研究

Research on the Return Trip Choice Behavior of College Students Considering Latent Variables and Heterogeneity

为分析潜变量因素对大学生返程出行选择行为的影响,综合考虑出行者对出行方式的评价建立混合Logit模型。首先,通过交通调查获取南京市大学生返程出行数据;其次,对各指标变量进行信效度检验并对心理因素进行验证性因子分析;然后,分别建立二项Logit模型、不考虑个人因素的混合Logit模型、混合Logit模型进行对比分析;最后,对模型计算的参数和边际效应进行了分析。结果表明:混合Logit模型相较于传统模型具备更好地拟合优度。对出行方式舒适度要求系数可以设置为随机参数,大巴以时间和价格优势转移了部分高铁出行人群,大学生对于高铁的舒适性和可靠性较为认同。

In order to analyze the influence of latent variable factors on college students'return trip choice behavior,a mixed Logit model was established by considering travelers'evaluation of travel modes.Firstly,we obtained the return trip data of college students in Nanjing through a traffic survey;secondly,we tested the reliability of each indicator variable and conducted a validation factor analysis on psychological factors;then,we established a binomial Logit model,a mixed Logit model without considering personal factors,and a mixed Logit model for comparative analysis;finally,we analyzed the parameters and marginal effects calculated by the model.The results show that the mixed Logit model has better fitting superiority compared with the traditional model.The coefficient of comfort requirement for travel mode can be set as a random parameter,and the bus has shifted some of the high speed rail travelers with time and price advantages,and the college students are more agreeable to the comfort and reliability of high speed rail.