Alcoholic patients randomly assigned to day hospital or inpatient rehabilitation were compared with patients who self-selected these treatment settings to examine differences in substance use and psychosocial outcomes under experimental and nonexperimental designs. Patients who self-selected treatment did not have better outcomes than those who were randomly assigned, and there were no significant differences between day hospital patients and inpatients on any of the 11 outcome measures. Significant interactions between treatment setting and assignment were found with only 2 outcome measures. Therefore, the comparisons between day hospital and inpatient treatment yielded similar outcomes under both "scientific" conditions and the conditions that more closely approximate the experiences of most patients. Implications for the use of nonrandomized participants in alcoholism treatment research and limitations of the study were also discussed.