We employed t-tests of means and proportions to compare characteristics of all individuals in three mutually exclusive groups: 1) individuals positive solely for the DSM-IV disorder in question, 2) those positive solely for the DSM-5 disorder and 3) those positive for both. For comparing overall differences in clinical profiles, the substantial diagnostic overlap (cases positive for DSM-IV and DSM-5 AUD)precluded using statistical tests designed for independent samples. Statistical procedures for testing differences in overlapping samples (Thompson, 1995) are intended to compare two different variables, e.g., income at time 1 and time 2, within an overlapping sample of the type where portions of the respondents rotate in and out in any given year. These procedures are not appropriate for testing differences in a single variable (e.g., age) across overlapping groups. Accordingly, we used a partial split sample design to create the largest possible mutually exclusive samples of individuals with DSM-IV and DSM-5 diagnoses. Using abuse/moderate AUD as an example, the sample for DSM-IV abuse comprised all respondents who were positive solely for abuse (group 1 above) and half of those positive
