Developing Safety Performance Function for Freeways by considering Interactions between Speed Limit and Geometric Variables

• DOI: 10.3141/2435-09
• Publication Date: 2014-11-18T02:29:40Z
• Authors: M. Saidul Islam; John N. Ivan; Nicholas E. Lownes; Reda A. Ammar; Sanguthevar Rajas...
• Keywords: Akaike information criterion; Speed limit; Geometric design; Goodness of fit

Safety performance functions (SPFs) are crash prediction models that quantitatively relate the expected number of counts with traffic volume and roadway roadside geometries. SPFs help safety officials identify unsafe locations take appropriate counteractive measures. A study assembled geometry data freeways (only Interstate highway were used for this study) in Connecticut development SPFs. Models estimated separately single-vehicle multivehicle crashes. Total fatal injury crashes considered model estimation both For each category, three estimations performed negative binomial distribution all geometric variables, speed limit only, interaction between variables. The best selected category through a comparison goodness-of-fit measures (Akaike information criterion). Interaction found to be categories. This finding suggests importance incorporating effect particular variables such as lanes, shoulder width, median type, models.