ANALYZING RAISED MEDIAN SAFETY IMPACTS USING BAYESIAN METHODS

摘要

Because traffic safety studies are not performed in a controlled environment such as a laboratory, butrather in an uncontrolled real world setting, traditional analysis methods often lack the capability toadequately evaluate the effectiveness of roadway safety measures. In recent years, however, advancedstatistical methods have been utilized in traffic safety studies to more accurately determine theeffectiveness of such measures. These methods, particularly Bayesian statistical techniques, have thecapabilities to account for the shortcomings of traditional methods. Hierarchical Bayesian modeling is apowerful tool for expressing rich statistical models that more fully reflect a given problem than traditionalsafety evaluation methods could.This paper uses a hierarchical Bayesian model to analyze the effectiveness of raised medianinstallations on overall and severe crash frequency in the state of Utah by determining the effect each hason crash frequency and frequency of severe crashes at study locations before and after installation ofraised medians. Several sites where raised medians have been installed in the last 10 years wereevaluated using available crash data. The results of this study show that the installation of a raisedmedian is an effective technique to reduce the overall crash frequency and frequency of severe crashes onUtah roadways with results showing a reduction in overall crash frequency of 25 percent and frequency ofsevere crashes of 36 percent along corridors where raised medians were installed. The results also showthat hierarchical Bayesian modeling is a useful method for evaluating effectiveness of roadway safetymeasures.