There is a rich theoretical literature in economics which models habit‐forming behaviors, of which addiction is the exemplar, but there is a paucity of experimental economic studies eliciting and comparing the preferences that economic theory suggests may differ between addicts and nonaddicts. We evaluate an incentive‐compatible risk and time preference experiment conducted on a sample of student smokers and nonsmokers at the University of Cape Town in 2012. We adopt a full information maximum likelihood statistical framework, which is consistent with the data generating processes proposed by structural theories and accounts for subject errors in decision making, to explore the relationship between risk preferences, time preferences, and addiction. Across different theories and econometric specifications, we find no differences in the risk preferences of smokers and nonsmokers but do find that smokers discount significantly more heavily than nonsmokers. We also identify a nonlinear effect of smoking intensity on discounting behavior and find that smoking intensity increases the likelihood of discounting hyperbolically, which means heavier smokers may be more prone to time inconsistency and more recalcitrant to treatment. These results highlight the importance of the theory‐experimental design‐econometric trinity and have important implications for theories of addiction.