This study examined the latent class structure of Diagnostic and Statistical Manual of Mental Disorders (text rev.; DSM-IV; American Psychiatric Association, 2000) symptoms used to diagnose cannabis, hallucinogen, cocaine, and opiate disorders among 501 adolescents recruited from addictions treatment. Latent class results were compared with the DSM-IV categories of abuse and dependence, and latent transition analysis (LTA) was used to examine changes in symptom severity over a 1-year follow-up. Although 2- and 3-class solutions provided the best fit to the data (2-class: hallucinogens, cocaine, opioids; 3-class: cannabis), 3-class solutions provided more substantive results and were emphasized in analyses. There was good agreement between latent classes and DSM-IV diagnosis. LTA suggested greater likelihood of transitioning to a less severe class at 1 year for all 4 drugs; in- and outpatients differed in pattern of change.