Based on the actual data collected from black spots on mountain highways, this paper investigated the influences of roadways' attributes upon vehicle speed. The significance of different factors contribute to vehicle speed were represented by the modified coefficients of roadway attributes, and a model was established based on the modified coefficients. Moreover, we took advantage of Logarithmic regression and then applied Partial Least Squares regression for computing the modified coefficients of roadway attributes towards vehicle speed. Through analysis up model, some favorable results obtained. To fix the invalidity of classic least squares regression on this issue, we present the feasible approach to establish regression model.
