This paper provides detailed evidence regarding the nature of selection into a school voucher system. We use micro-data on scholarship applications matched with state student-level records on test scores, schools attended, and demographic background characteristics to describe the attributes of students who choose to participate in Florida's Corporate Tax Credit Scholarship Program, a means-tested scholarship program that is the largest of its type in the United States. We find evidence that those who choose to participate in the program tend to be lower-performing students from poorly performing schools, and that students of different backgrounds tend to choose different types of private schools. Students participating in the program tend to select schools that have more white students and fewer minority students, regardless of student race. (Contains 7 figures and 9 tables.)