吉林大学学报(工学版) ›› 2024, Vol. 54 ›› Issue (2): 461-468.doi: 10.13229/j.cnki.jdxbgxb.20220312

• 交通运输工程·土木工程 • 上一篇    

基于随机参数Logit的中小城市居民出行方式选择建模

庄焱1(),董春娇1(),米雪玉2,张小雨1,王菁1   

  1. 1.北京交通大学 综合交通运输大数据应用技术交通运输行业重点实验室,北京 100044
    2.华北理工大学 唐山市空地智慧交通重点实验室,河北 唐山 063210
  • 收稿日期:2022-03-26 出版日期:2024-02-01 发布日期:2024-03-29
  • 通讯作者: 董春娇 E-mail:yanzhuang1010@bjtu.edu.cn;cjdong@bjtu.edu.cn
  • 作者简介:庄焱(1992-),女,博士研究生. 研究方向:交通规划,交通管理和交通安全.E-mail:yanzhuang1010@bjtu.edu.cn
  • 基金资助:
    国家自然科学基金项目(72371017);中央高校基本科研业务费专项项目(2020YJS089)

Travel mode choice in small and media sized city based on random parameters Logit model

Yan ZHUANG1(),Chun-jiao DONG1(),Xue-yu MI2,Xiao-yu ZHANG1,Jing WANG1   

  1. 1.Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport,Beijing Jiaotong University,Beijing 100044,China
    2.Tangshan Key Laboratory of Air-Ground Intelligent Transportation,North China University of Science and Technology,Tangshan 063210,China
  • Received:2022-03-26 Online:2024-02-01 Published:2024-03-29
  • Contact: Chun-jiao DONG E-mail:yanzhuang1010@bjtu.edu.cn;cjdong@bjtu.edu.cn

摘要:

为了给中小城市交通规划与管理提供新思路和新方法,分析了中小城市居民出行特征,考虑居民出行方式选择的异质性,构建了基于随机参数Logit的中小城市居民出行选择模型,引入了对交通工具舒适性要求等心理潜变量因素,并采用反映潜变量与指标变量之间关系的结构方程模型标定了参数。结果表明,由结构方程标定潜变量的随机参数Logit模型预测准确率均高于95%,说明结构方程模型具有良好的参数标定效果,构建的随机参数Logit模型具有较好的拟合度。模型效用函数中,行车时间的系数为随机参数,与出行者的个人特征变量、出行特征变量和心理潜变量有关。其中,到公交站台的步行时间对出行效用的影响程度最大,每增加1单位,时间价值减少48元。此外,不同出行方式对行车时间的边际效用不同,超过45 min后,公交车的边际效用由增转减。可见,考虑个体心理潜变量等异质性的随机参数Logit模型能够刻画中小城市居民实际出行方式选择行为且对出行特征机理的解释性更强。

关键词: 城市交通, 出行方式选择, 随机参数, 中小城市, 结构方程, 边际效应

Abstract:

In order to provide new thoughts and new methods for traffic planning and management of small and medium-sized cities, the travel characteristics of residents in small and medium-sized cities was analyzed. Considering the heterogeneity of residents' travel mode choices, a travel mode choice model of based on random parameters Logit was constructed. Factors of psychological latent variables such as the requirement of comfort were introduced, and the structural equation model was used to calibrate the parameters, which reflects the relationship between latent variables and index variables. The results show that the prediction accuracy of the stochastic parameter logit model calibrated by structural equation is higher than 95%, which indicates that the structural equation model has good parameter calibration effect, and the constructed stochastic parameter logit model has good fitting degree. In the utility function of the model, the coefficient of travel time is a random parameter, which is related to the individual characteristic variables, travel characteristic variables and psychological latent variables of travelers. Among them, the walking time to the bus stop has the greatest impact on the travel utility, and the value of time decreases by 48 yuan for each additional unit. In addition, the marginal utility of different travel modes on driving time is different. The marginal utility of bus turns from increase to decrease after 45 min. Therefore, the random parameters Logit model considering the heterogeneity of individual psychological latent variables can describe the actual travel mode choice behavior of residents in small and medium-sized cities, and has a stronger explanation for the mechanism of travel characteristics.

Key words: urban transportation, travel mode selection, random parameter, small and medium cities, structural equation model, marginal effect

中图分类号: 

  • U491.1

表1

出行者个人、出行属性及心理潜变量"

变量符号含义

个人

属性

性别XGen0:女性1:男性
职业XJob1:学生2:工人3:公务员及事业单位4:公司职员5:私营及个体劳动者6:离退休7:无业8:其他
年龄XAge6~18岁(XAge1);19~29岁(XAge2);30~49岁(XAge3);50~59岁(XAge4);60岁以上(XAge5
受教育程度XEdu1:初中及其以下2:高中及中专3:大专及本科4:硕士及以上
月收入XInc<5000元(XInc1);5000~10000元(XInc2);>10000元(XInc3
私家车拥有情况XCar0、1分别表示无车、有车
非机动车拥有情况XNon0、1分别表示无车、有车

出行

属性

每周乘坐公交次数XFreq①<2次②2~5次③6~10次④11~15次⑤>5次
步行时间XTime到公交站台的步行时间(XTime1);在公交站台的等车时间(XTime2);从公交站台到目的地的步行时间(XTime3

心理

潜变量

舒适性XComf我会在意出行方式的环境(光线、气味、噪声等)c1;我会在意出行方式的速度c2;我会在意出行方式的拥挤程度c3;如果某种出行方式不舒适,我会选择更舒适的出行方式,即使要多花钱(超过2元)c4;如果某种出行方式不舒适,我会选择更舒适的出行方式,即使要多时间(超过10 min)c5
可靠性XReli我会在意站台等车时间的长短c6;我会在意公交到站的准时性c7;我会在意公交到达目的地时间估计的准确性c8
便捷性XConv我会在意步行到公交站台的时间c9;我会在意公交换乘次数的多少c10;我会在意公交行驶的线路途经的站点c11

图1

中小城市出行特征分析"

表2

不同样本划分比例和不同潜变量标定法的预测准确率 (%)"

潜变量标定方法

结构

方程

因子

分析法

主成分

分析法

训练集:验证集(60:40)95.2788.4893.45
训练集:验证集(70:30)96.4492.4991.36
训练集:验证集(80:20)95.8691.1992.65

表3

心理潜变量的指标变量表示"

潜变量指标变量符号

因素

荷载值

Cronbach's α

适配

系数

Lcomfort

舒适性

c10.630.6160.194
c20.710.219
c30.550.170
c40.660.204
c50.690.213

Lreliability

可靠性

c60.740.6480.372
c70.520.261
c80.730.367

Lconvenience

便捷性

c90.670.5950.294
c100.820.360
c110.790.346
因子分析Cronbach's α系数:0.768;KMO测度值:0.815;Bartlett检验显著性值:0
模型评价参数卡方自由度比(NC):1.987;适配度(GFI)0.906;调整适配度(AGFI):0.927;均方根残差(RMR):0.026

表4

随机参数Logit模型回归系数"

参数系数标准差zp95%置信区间

随机参数

(相关个人、出行属性及心理潜变量参数)

βT-0.265***0.0171.470.0000-0.298-0.232
σT0.042***0.0352.570.0004-0.1610.245
TXAge3-0.133***0.104-5.690.0005-0.4510.185
TXEdu-0.147***0.082-5.340.0000-0.5450.251
TXCar-0.138**0.107-1.920.0000-0.220-0.056
TXTime10.224***0.036-7.870.00000.0220.426
TXComf-0.108***0.304-1.360.0000-0.3120.096
固定参数dcar-0.098***0.162-4.120.0000-0.2590.063
dbus-0.143***0.203-5.210.0000-0.3530.067
βC-0.281***0.042-6.780.0102-0.352-0.210
βW-0.137**0.1032.350.0001-0.7330.459
总体参数McFadden's R20.278
AIC2323
BIC2146

图2

行车时间边际效应分析"

1 Hu H, Xu J, Shen Q, et al. Travel mode choices in small cities of China: a case study of Changting[J]. Transportation Research part D: Transport and Environment, 2018, 59: 361-374.
2 覃栩曈. 中小城市出行即服务体系规划设计[D].桂林:桂林电子科技大学建筑与交通工程学院,2021.
Tan Xu-tong. Planning and design of mobility as a service system in small and medium-sized cities[D]. Guilin: School of Architecture and Transportation Engineering, Guilin University of Electronic Technology,2021.
3 阿东. 基于改进型MNL模型的中小城市居民出行交通方式研究[D].长沙:湖南大学土木工程学院,2019.
Dong A.Research on travel modes of residents in smal and medium-sized cities based on improved MNL mode[D].Changsha:College of Civil Engineering, Hunan University,2019.
4 McFadden D, Train K. Mixed MNL models for discrete response[J]. Journal of Applied Econometrics, 2000, 15(5): 447-470.
5 Koppelman F S, Pas E I. Travel-choice behavior: Models of perceptions, feelings, preference, and choice[J]. Transportation Research Record, 1980(765): 1-13.
6 叶玉玲,韩明初,陈俊晶.基于出行链的城际旅客出行方式选择行为[J].同济大学学报:自然科学版,2018,46(9):1234-1240.
Ye Yu-ling, Han Ming-chu, Chen Jun-jing.Intercity passenger travel mode choice behavior based on trip chain[J]. Journal of Tongji University (Natural Science),2018,46(9):1234-1240.
7 程琳,栾鑫,邓卫,等. 特大城市居民出行方式选择行为的混合Logit模型[J]. 吉林大学学报:工学版, 2018, 48(4):1029-1036.
Cheng Lin, Luan Xin, Deng Wei, et al. Mixed Logit model for understanding travel mode choice behavior of megalopolitan residents[J]. Journal of Jilin University (Engineering and Technology Edition) 2018, 48(4):1029-1036.
8 Ding C, Wang D, Liu C, et al. Exploring the influence of built environment on travel mode choice considering the mediating effects of car ownership and travel distance[J]. Transportation Research Part A: Policy and Practice, 2017, 100: 65-80.
9 刘建荣,郝小妮.基于随机系数Logit模型的市内出行方式选择行为研究[J].交通运输系统工程与信息,2019,19(5):108-113.
Liu Jian-rong, Hao Xiao-ni.Travel mode choice in city based on random parameters logit model[J]. Journal of Transportation Systems Engineering and Information Technology, 2019,19(5):108-113.
10 Escobari D. Airport, airline and departure time choice and substitution patterns: an empirical analysis[J]. Transportation Research Part A: Policy and Practice, 2017, 103: 198-210.
11 唐立,邹彤,罗霞,等.基于混合Logit模型的网约车选择行为研究[J].交通运输系统工程与信息,2018,18(1):108-114.
Tang Li, Zou Tong, Luo Xia, et al. Choice behavior of taxi-hailing based on mixed-logit model[J]. Journal of Transportation Systems Engineering and Information Technology, 2018,18(1):108-114.
12 Shamshiripour A, Golshani N, Shabanpour R, et al. Week-long mode choice behavior: dynamic random effects logit model[J]. Transportation Research Record, 2019, 2673(10): 736-744.
13 赵淑芝,赵贝.多因素影响下的城市居民出行行为时间价值[J].吉林大学学报,工学版,2011,41(1):46-50.
Zhao Shu-zhi, Zhao Bei.Value of travel time of urban resident under multifactor influence[J]. Journal of Jilin University (Engineering and Technology Edition), 2011,41(1):46-50.
14 张晨阳. 考虑潜在变量的西安居民短距离出行方式选择研究[D].西安:长安大学运输工程学院,2019.
Zhang Chen-yang. Research on short-distance travel mode choice behavior of Xi'an residents considering potential variables[D].Xian: College of Transportation Engineering, Chang'an University,2019.
15 Khan N A, Habib M A. Understanding variations in activity-based vehicle allocation decisions: a latent segmentation-based random parameter logit modeling approach[J]. Transportation Research Procedia, 2020, 48: 1505-1525.
[1] 张文会,伊静. 考虑通行能力和排队延误的公交停靠系统优化[J]. 吉林大学学报(工学版), 2024, 54(1): 146-154.
[2] 马壮林,崔姗姗,胡大伟,王晋. 限行政策下传统小汽车出行者出行方式选择[J]. 吉林大学学报(工学版), 2023, 53(7): 1981-1993.
[3] 贺宜,孙昌鑫,彭建华,吴超仲,江亮,马明. 电动载货三轮车风险行为及影响因素分析[J]. 吉林大学学报(工学版), 2023, 53(2): 413-420.
[4] 邝先验,陈自如. 基于CA的无信号灯控制路段行人过街横道处动态博弈礼让行为[J]. 吉林大学学报(工学版), 2022, 52(4): 837-846.
[5] 贾洪飞,邵子函,杨丽丽. 终点不确定条件下网约车合乘匹配模型及算法[J]. 吉林大学学报(工学版), 2022, 52(3): 564-571.
[6] 董春娇,董黛悦,诸葛承祥,甄理. 电动自行车出行特性及骑行决策行为建模[J]. 吉林大学学报(工学版), 2022, 52(11): 2618-2625.
[7] 杨世军,裴玉龙,潘恒彦,程国柱,张文会. 城市公交车辆驻站时间特征分析及预测[J]. 吉林大学学报(工学版), 2021, 51(6): 2031-2039.
[8] 刘志伟,刘建荣,邓卫. 基于潜在类别的无人驾驶汽车选择行为[J]. 吉林大学学报(工学版), 2021, 51(4): 1261-1268.
[9] 孙宝凤,姜源,郑黎黎,崔万坤,任欣欣. 变覆盖半径下城市轨道交通维护保障网络设计模型[J]. 吉林大学学报(工学版), 2020, 50(2): 526-534.
[10] 陈磊,王江锋,谷远利,闫学东. 基于思维进化优化的多源交通数据融合算法[J]. 吉林大学学报(工学版), 2019, 49(3): 705-713.
[11] 栾鑫, 邓卫, 程琳, 陈新元. 特大城市居民出行方式选择行为的混合Logit模型[J]. 吉林大学学报(工学版), 2018, 48(4): 1029-1036.
[12] 侯现耀, 陈学武. 基于态度的公交出行信息使用市场细分[J]. 吉林大学学报(工学版), 2018, 48(1): 98-104.
[13] 于德新,杨兆升,高鹏. 动态限制搜索区域的带约束K则最优路径算法[J]. 吉林大学学报(工学版), 2009, 39(增刊2): 172-0176.
[14] 杨兆升,于悦,杨薇. 基于固定型检测器和浮动车的路段行程时间获取技术[J]. 吉林大学学报(工学版), 2009, 39(增刊2): 168-0171.
[15] 李霞,邵春福,贾洪飞 . 土地利用与居民出行生成模型及其参数标定[J]. 吉林大学学报(工学版), 2007, 37(06): 1300-1303.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!