家庭收入差异对出行方式选择的影响分析  

Effects of Household Income Differences on Travel Mode Choice

作　　者：范琪 王炜[1,2,3] 杨洋[1,2,3] 华雪东 FAN Qi;WANG Wei;YANG Yang;HUA Xuedong(Jiangsu Key Laboratory of Urban ITS,Southeast University,Nanjing 210096,China;Jiangsu Province Collaborative Innovation Center of Modern Urban Traffic Technologies,Southeast University,Nanjing 210096,China;School of Transportation,Southeast University,Nanjing 210096,China)

机构地区：[1]东南大学城市智能交通江苏省重点实验室,南京210096 [2]东南大学现代城市交通技术江苏高校协同创新中心,南京210096 [3]东南大学交通学院,南京210096

出　　处：《交通信息与安全》2019年第6期111-120,共10页Journal of Transport Information and Safety

基　　金：国家自然科学基金项目(51338003、71801042)资助

摘　　要：出行者时间价值是影响出行决策的最重要因素之一,研究时间价值有利于准确构建方式划分离散选择模型。在分析居民出行调查数据的基础上,应用聚类树分析对家庭收入分组的合理性进行了探讨,分别对每种出行方式的出行者家庭收入统计分析,说明家庭收入对家庭成员出行方式选择的影响。在说明家庭收入与出行时间价值之间关系的前提下,提出家庭共享时间价值的概念,数据拟合的结果发现家庭共享时间价值服从对数正态分布。分别基于MNL模型和ML模型构建出行方式选择模型以家庭共享时间价值为主要变量的对比模型,研究了设置家庭收入变量与不设置家庭收入变量、设置家庭收入分段变量与设置家庭收入常量、设置服从对数正态分布的费用项随机系数与不设置费用项随机系数3类情况下模型的精度和准确程度。当设置家庭收入变量且费用项系数服从对数正态分布时,拟合效果最优,居民对交通出行的主观支付意愿期望值约为家庭共享小时收入的2倍。Time value is one of the most important factors that affect travel mode choice of travelers.Studies of time value are beneficial to improve accuracy to establish a model of mode split discrete selection.Based on the data from a travel survey of residents,rationality of household income grouping is discussed by cluster tree analysis.The household income of each travel mode is analyzed.Influences of household income on travel choices of family members are studied.On the premise of explaining the relationship between household income and travel time value,a concept of family shared-time value is proposed.The data fitting results shows that the value of family shared-time follows lognormal distribution.Three comparison groups are set based on a MNL model and a ML model,in which the family shared-time value is a main variable.The comparison focuses on setting household income variables or not,setting segmentation variables of household income or household income constant,setting random coefficients of cost items which obey lognormal distribution or no random coefficient.The fitting result is the best when the household income variables are set and the coefficients of cost items obey lognormal distribution.The expected value of subjective willingness to pay for travel is about twice of the family shared-time value.

关 键 词：交通规划 家庭收入差异 出行方式选择 离散选择模型 出行时间价值 

分 类 号：U121[交通运输工程]