A MULTIVARIATE ANALYSIS OF FREEWAY SPEED AND HEADWAY DATA

The knowledge of speed and head way distributions is essent ial in m icroscopic traffic flow studies because speed an d headway are both fundamental microscopic characteristics of traffic flow. For microscopic simulation models, one key process is the generation of entry vehicle speeds and vehicle arrival times. It is helpful to find desirable mathematical distributions to m odel individual speed and headway values, because the individual vehicle speed and arrival tim e in microscopic simulations are usu ally generated based on som e form of mathematical models. Traditionally, distributions for speed and headway are investigated separately and independent of each other. However, this traditional approach ignores the possible dependence between speed and headway. To address this issue, the research pr esents a m ethodology to construct bivariate distributions to describe the characteri stics of speed and headway. Based on the investigation of freeway speed and headway da ta measured from the loop detector data on IH-35 in Austin, it is shown that there exists a weak dependence betw een speed and headway. The research first proposes skew-t m ixture models to capture the he terogeneity in speed distribution. Finite m ixture of skew-t distributions can significantly im prove the goodness of fit of speed data. To develop a bivariate distribut ion to capture the dependence and describe the characteristics of speed and headway, this study proposes a