The National Education Longitudinal Study of 1988 (NELS:88) serves as an example of how three specific problems of representativeness in a longitudinal study may be approached and overcome. NELS:88 was designed to provide longitudinal data about the educational transitions experienced by students as they leave eighth grade and move through high school and postsecondary education. The cohort, initially 26,432 students, is being followed at 2-year intervals. The three key issues that are discussed are: (1) eligibility and exclusion rules and the measures taken to deal with undercoverage resulting from exclusion; (2) the need for sample freshening to ensure representative sophomore and senior cohorts in 1990 and 1992; and (3) attempts to minimize sample attrition and nonresponse error. Longitudinal designs are a powerful vehicle for measuring individual-level change. At the same time, they have distinct limitations, which can be overcome by careful execution and research design. One figure and three tables illustrate the discussion. (Contains 21 references.) (SLD)