Previous research has shown that greater longitudinal pavement marking retroreflectivity levels increase drivers’ visibility and detection distance. However, increased visibility may cause drivers to feel too comfortable during nighttime conditions, and drivers may then pay less attention, operate their vehicles at unsafe speeds, or both. Before-and-after studies have been conducted on a pavement marking improvement such as repainting stripes or changing to a more durable marking material. Studies have also used models to estimate the retroreflectivity on the basis of the date of installation and vehicle exposure or have assumed a linear reduction in retroreflectivity over time. Only two studies have related field-measured pavement marking retroreflectivity to safety performance (crash data). One study analyzed the relationship between 3 years of pavement marking retroreflectivity data collected by the Iowa Department of Transportation on all state primary roads and corresponding crash and traffic data. The other study developed a spatial–temporal database by using measured retroreflectivity data to account for the deterioration of pavement markings over time, along with a statewide crash database to attempt to quantify a relationship between crashes and the quality (measured by retroreflectivity) of pavement marking. Three sets of data were analyzed: the complete database, records for two-lane roads, and records with retroreflectivity values less than or equal to 200 mcd/m²/lx only. The distributions and models of the entire database and the two-lane records did not show that poor pavement marking retroreflectivity correlated to a higher crash probability. However, when only records with retroreflectivity values of 200 mcd/m²/lx or less were examined, a statistically significant, albeit weak, relationship was determined.