The Research Triangle conducted an evaluation study of the Upward Bound Program, a nationwide program funded by the U.S. Office of Education to help selected low-income high school students prepare for and enter post secondary education. This paper describes the sample design and selection procedures used in selecting a sample of Upward Bound students and a sample of comparison students for the study. A multistage probability sample design was used. In addition, data collection procedures, which included questionnaire administration, mail queries and telephone followups, are described. (Author/BW)