We develop and estimate a model of study time choices of students on a social network. The model is designed to exploit unique data collected in the Berea Panel Study. Study time data allow us to quantify an intuitive mechanism for academic social interactions: own study time may depend on friend study time. Social network data allow study time choices and resulting academic achievement to be embedded in an estimable equilibrium framework. New data on study propensities allow us to directly address potential sorting into friendships based on typically unobserved determinants of study time. We develop a specification test that exploits the equilibrium nature of social interactions and use it to show that our study propensity measures substantially address endogeneity concerns. We find friend study time strongly affects own study time, and, therefore, student achievement. We examine how network structure interacts with student characteristics to affect academic achievement. Sorting on friend characteristics appears important in explaining variation across students in study time and achievement, and determines the aggregate achievement level.