OBJECTIVES The aim of this study was to assess the association between changes in living arrangement and the initiation of daily smoking and monthly risky single-occasion drinking (RSOD) in a cohort of young Swiss men. STUDY DESIGN Longitudinal cohort study. METHODS The sample consisted of 4662 young men drawn from the Cohort Study on Substance Use Risk Factors who lived with their family at baseline. Follow-up assessments occurred 15 months later. Multiple regression models were adjusted for individual and family factors (family model), as well as for individual and peer-related factors (peer model). RESULTS Relative to those still living with their parents at follow-up (n = 3845), those who had moved out (n = 817) were considerably more likely to have taken up smoking or RSOD after adjusting for several individual, family, and peer-related variables: OR (daily smoking) = 1.67 (95% CI 1.15-2.41) (P = 0.007) and OR (monthly RSOD) = 1.42 (95% CI 1.08-1.88) (P = 0.012). The strongest family-related predictors of smoking initiation were family structure and the lack of parental regulation and the strongest peer-related factors alcohol/drug problems in peers. Meanwhile, the strongest peer-related predictors of RSOD initiation were peer pressure (misconduct), perceived social support from friends, and perceived social support from a significant other, whereas family factors were not associated with RSOD initiation. Further subanalyses were conducted to examine the impact of different living arrangement changes on substance use initiation and revealed that living with peers at follow-up was associated with the greatest risk. CONCLUSIONS We identified a strong association between moving out of one's parents' home and daily smoking and monthly RSOD initiation in young Swiss men. Moving out to live with peers was an especially strong predictor of substance use initiation. Campaigns that aim to prevent heavy smoking and drinking should be intensified at the end of obligatory school.