摘要
为分析电动自行车事故和车牌使用影响因素,采用问卷调查和电话访谈方式采集了宁波市862个电动自行车用户有效样本,利用统计学方法构建了Bivariate Probit(BP)联立方程模型,计算了显著影响因素的边际效应,量化分析了电动自行车事故和车牌使用影响因素效用,并检验了两者之间潜在的关联关系.结果表明:BP模型不仅可以识别电动自行车事故和车牌使用的影响因素,而且可以有效刻画两者之间的潜在联系;两者之间关联系数为-0.475,表明电动自行车车牌的使用可以降低电动自行车事故概率;模型结果显示性别、年龄、驾驶执照、家庭是否拥有小汽车、电动自行车驾龄、法律遵守程度、驾驶行为、危险感知度等具有统计显著性,是影响电动自行车事故和车牌使用的显著因素.
In order to analyze the contributory factors associated with the e-bike involved crash and license plate use, 862 samples of Ningbo e-bike riders were collected using the questionnaire survey method and telephone interview survey method. Based on the statistical theory, a Bivariate Probit（BP） model is developed to simultaneously examine the factors that affect e-bike involved crash and e-bike license plate use among e-biker riders. Marginal effects for contributory factors are calculated to quantify their impacts on the outcomes. The results show that the BP model can not only identify the affecting factors for e-bike involved crash and license plate use, but also reflect potential relationships between them; the correlation parameter of the e-bike involved crash and license plate use is-0.475, indicating that e-bike license plate use can reduce the probability of the e-bike involved crash; several contributory factors, including gender, age group, driving license, car in household, experiences in using e-bike, law compliance, and aggressive driving behaviors are found to have significant impacts on both of e-bike involved crash and license plate use.
出处
《交通运输系统工程与信息》
EI
CSCD
北大核心
2017年第3期229-234,共6页
Journal of Transportation Systems Engineering and Information Technology
基金
浙江省公益技术应用研究计划项目(2016C33256)
浙江省自然科学基金(LY17E080013)
宁波市自然科学基金(2015A610298)~~
