Application of Finite Mixture Models for Analyzing Freeway Incident Clearance Time

A number of approaches have been developed for analyzing incident clearance time data and investigating the effects of different explanatory variables on clearance time. Among these methods, hazard-based duration models (i.e., proportional hazard and accelerated failure time models) have been extensively used. The finite mixture model is an alternative approach in survival data analysis, and offers greater flexibility in describing different shapes of the hazard function. Additionally, the finite mixture model assumes that the incident clearance time dataset contains distinct subpopulations, and it allows the effects of explanatory variables to vary between different subpopulations. In this study, a g-component mixture model is applied to analyze incident clearance time. To demonstrate advantages of the proposed finite mixture model framework, incident clearance time data collected on freeway sections in Seattle, Washington State are analyzed. Estimation and prediction results from the proposed mixture model and the accelerated failure time model are presented and compared. The results suggest that the proposed mixture model can better describe the survival probability and hazard probability of incident clearance time, and can provide more accurate prediction compared to the accelerated failure time model. The mixture model can also provide inferences about the effects of explainable variables on different subpopulations present in incident clearance time data. The additional information obtained from the proposed mixture model can be potentially useful for designing targeted incident management strategies for different incident types. Overall, the findings in this study demonstrate that the mixture modeling approach is a useful and informative method for analyzing heterogeneous incident duration data and predicting incident duration on freeways.