Many randomized controlled trials (RCTs) in dental research test the efficacy of interventions on more than one outcome variable. Univariate methods, such as the t test or analysis of covariance, cannot evaluate the efficacy of interventions on multiple outcomes simultaneously. The aim of this study was to use structural equation modeling (SEM) to re-analyze a RCT, comparing the effects of pre-curved interdental brushes and flossing on probing pocket depth (PPD), plaque indices, and bleeding on probing (BOP) measured at baseline, intermediate, and final examinations. Results of SEM showed that the observed greater reduction in PPD and BOP in persons using interdental brushing than in those flossing is due mainly to the greater efficiency in plaque removal with the interdental brushes (indirect effect) rather than to the compression of the interdental papillae (direct effect). In contrast, smokers showed less BOP at baseline but also less improvement in BOP through direct effects.