Effects of parameter distributions and correlations on uncertainty analysis of highway capacity manual delay model for signalized intersections

The uncertainty analysis of the Highway Capacity Manual (HCM) delay model often assumes parameter variances and distributions. In tight of the difficulty in specifying distributions and estimating correlations, the present study investigated (a) the possibility of assumed distributions' major effect on the results and (b) the effects of correlations on the accuracy of delay estimates. Field data from one intersection approach in Hawaii and nine intersection approaches in Illinois were used. All input variables in the delay model except for the analysis period were considered uncertain; the analysis period remained fixed at 15 min for consistency with HCM. The simulation results showed that the confidence intervals of delay can be large even if the variability of each input parameter is small. The degree of saturation (X) has a significant effect on the uncertainty of delay estimates for X values 0.9. The standard deviation of input parameters is the main factor affecting the uncertainty of delay estimates. The probability distributions have a slight effect. Correlations among input parameters are often overlooked, but they have a significant effect on the confidence intervals of delay estimates, especially when the variability of the input parameters is large and the input parameters are highly correlated. The frequency distribution of delay estimates is not normal; the shifted lognormal distribution provides a better statistical fit.