Instrumental variables is a popular approach for causal inference in education when randomization of treatment is not feasible. Using a first-year college program as a running example, this article reviews the five assumptions that must be met to successfully use instrumental variables to estimate a causal effect with observational data: SUTVA, as-if random assignment, exclusion restriction, nonzero average causal effect of instrument on treatment, and monotonicity, and concludes with recommendations for researchers.