This research was initiated to determine whether a correlation between pavement marking retroreflectivity and safety could be established. Previous research on this topic provided mixed results and sometimes counterintuitive findings. Using data from Michigan, the researchers evaluated relationships between crashes and longitudinal pavement marking retroreflectivity. The retroreflectivity data consisted of pavement marking measurements representing white edge lines, white lane lines, yellow edge lines, and yellow centerlines. The data included crashes and retroreflectivity measurements from 2002 to 2008. Only nighttime crashes that occurred at nonintersection and noninterchange segments during the nonwinter months (between April and October) were considered (wet crashes were also excluded). The following specific types of crashes were initially identified as target crashes for this study: nighttime, single vehicle nighttime, fatal plus injury nighttime, and single vehicle nighttime fatal plus injury. The findings lend support to the positive safety effects of maintaining retroreflectivity of pavement markings.