基于累积Logistic回归道路交通拥堵强度评价模型

现有的道路交通拥堵强度评价模型缺乏有效的定量方法来划分拥堵的各个等级,选取的拥堵评价自变量之间存在相关性等问题.为了改进上述不足,该文在分析拥堵强度序次特征后,将累积Logistic回归引入到道路交通拥堵强度评价模型.采用似然比检验方法验证了累积Logistic回归的适用性,并采用Wald检验筛选自变量后,确定了以行程速度为自变量的道路交通拥堵强度评价模型.该模型的拟合优度判定系数(类R2)大于0.70,对实测数据的预测准确率达到73.39%.

Cumulative Logistic Regression-Based Measurement Models of Road Traffic Congestion Intensity

Existing models for measuring the traffic congestion intensity lack an effective quantitative method to classify the grades of congestions,and the employed congestion measurement independent variables are often inter-correlated.In order to overcome these deficiencies, this paper analyzes the ordinal characteristics of the congestion intensity,and then introduces the cumulative logistic regression into the measurement models of the congestion intensity.It adopts the likelihood ratio test to validate the adaptability of the cumulative logistic regression, and Wald test to select the independent variables.Then,it develops measurement models of the congestion intensity by using the travel speed as the independent variable.The proposed model shows a determination coefficient(analogous R2) higher than 0.70 in the goodness-of-fit test,and a prediction with an accuracy of 73.39% against the observed data.