Objective: This study used confirmatory factor analysis (CFA), latent class analysis (LCA), and factor mixture model (FMM) to ascertain the best model for ADHD symptoms, as presented in the Strengths and Weaknesses of ADHD-Symptoms and Normal Behavior Scale (SWAN). Method: Mother ratings of the ADHD symptoms of 418 clinic-referred children and adolescents were obtained. Results: The findings provided most support for an FMM with two classes (less severe inattention [IA] and hyperactivity/impulsivity [HI] symptoms and more severe IA/HI symptoms) and two factors (IA and HI) model. The more severe class had more individuals with the ADHD diagnosis, especially the combined type. Conclusion: The findings are discussed in relation to dimensional and categorical views of ADHD. (J. of Att. Dis. 2013; XX(X) 1-XX)