基于嵌套Logit模型的居民出行行为研究

Research on Residents’ Travel Behavior Based on Nested Logit Model

摘要: 随着突发公共卫生事件进入常态化阶段，居民的出行行为模式发生了显著变化。为了深入探究个体属性、出行特征及家庭因素对居民出行选择行为的影响，本文基于效用最大化理论构建双层嵌套Logit模型(Nested Logit Model)，将出行方式作为上层决策变量，出行目的作为下层决策变量，对两者之间的联合选择行为进行建模。通过问卷调查获取全国范围内513份有效样本数据，并利用R软件开展相关性分析、主成分分析、多重共线性检验及模型参数标定。结果表明：性别和职业对出行方式具有显著影响，家庭中6岁以下儿童和60岁以上老年人口对出行目的具有显著影响，而是否拥有驾照及小汽车则同时对出行方式与目的产生显著影响。鉴于样本以城市青年为主，研究成果主要适用于与样本特征相似的群体，可为城市交通政策制定和差异化出行管理提供数据支持与理论依据。

Abstract: Under the background of the normalization of the epidemic, the travel methods and purposes of residents have undergone significant changes. In order to deeply explore the influence of individual attributes, travel characteristics and family factors on residents’ travel choice behavior, this paper constructs a two-layer nested Logit model based on the utility maximization theory, taking travel mode as the upper-level decision variable and travel purpose as the lower-level decision variable. Model the joint choice behavior between the two. Through questionnaire surveys, 513 valid sample data from across the country were obtained, and correlation analysis, principal component analysis, multicollinearity test and model parameter calibration were carried out using R software. The results show that gender and occupation have a significant impact on the mode of travel. Children under 6 years old and the elderly population over 60 years old in the family have a significant impact on the purpose of travel. Meanwhile, whether one has a driver’s license and a car has a significant impact on both the mode of travel and the purpose. Given that the sample is mainly composed of urban youth, the research results are mainly applicable to groups with similar characteristics to the sample, and can provide data support and theoretical basis for the formulation of urban traffic policies and differentiated travel management.