To assess the effects of school traits on achievement, researchers reanalyzed the data used in "Public and Private Schools" (Coleman et al.) at the school level rather than the individual level. The data for the Coleman report and the present reanalysis are drawn from the "High School and Beyond" study, a 1980 national survey of 30 sophomores in each of 1,002 high schools. The researchers find that using regression equations on aggregate school-level data instead of individual-level data reduces the error in individual-level equations (caused by error in variable measurement) and controls for the contextual effects of student-body socioeconomic status. The reanalysis indicates that the apparent superiority of private schools in academic achievement is much smaller when computed at the school level rather than at the individual level. (Author/RW)