Selection bias is problematic when evaluating the effects of postsecondary interventions on college students, and can lead to biased estimates of program effects. While instrumental variables can be used to account for endogeneity due to self-selection, current practice requires that all five assumptions of instrumental variables be met in order to credibly estimate the causal effect of a program. Using the Pike et al. (2011) study of selection bias and learning communities as an example, the paper reviews these assumptions in the postsecondary context, and offers advice to researchers seeking to use instrumental variables for research on college students. (Contains 7 footnotes, 3 figures, and 2 tables.)