Novel Estimation Method and Interpretation of the Peak Hour Factor at Intersections

This study presents a statistically grounded method for estimating the peak hour factor (PHF) at intersections, using classical optimization techniques. Unlike the traditional approach, which computes a single ratio from aggregated turning movement volumes, the proposed method explicitly accounts for the count variability across individual turning movements and over multiple days. It produces not only a point estimate but also a confidence interval, offering a more defensible basis for analysis. The method implementation is quite straightforward: the optimization method revealed that PHF is actually the slope of the zero-intercept regression line between the peak interval flow rate and peak hourly volumes, in addition to generating its upper and lower 95^th percentile estimates. This finding enables a simple spreadsheet application of the estimation method. Regardless of the data aggregation intervals studied in this paper (5, 10, and 15 min), the traditionally estimated PHF fell outside of the proposed method’s 95% confidence interval in many cases, indicating a statistically significant difference between the outcomes of the two methods. This could result in under- or over-estimation of the design demand volumes in some cases.