Simple OLS estimates of the effect of school-imposed penalties for drug use on a student's consumption of marijuana are biased if both are determined by unobservable school or individual attributes. The potential reverse causality is also a challenge to retrieving estimates of the causal relationship, as the severity of school sanctions may simply reflect the need for more-severe sanctions. I offer an instrumental-variables approach to retrieving an estimate of the causal response of marijuana use to sanctions and thereby demonstrate the efficacy of school-imposed penalties as a deterrent to adolescent drug use. This is the first evidence of such efficacy and, given what is known about the consequences of drug use, suggests that school sanctions may have important long-run benefits.