The school sample size was assigned to achieve a targeted number of assessed students in the various sessions in the study. The sampling process was probability proportionate to size, with measure of size equal to the estimated number of age-eligible students in the school divided by the primary sampling unit (PSU) probability of selection. The estimated number of age-eligible students was computed using a derived linear function of estimated grade enrollments, with the coefficients for this function derived from Current Population Survey data.
There was a set of private schools for which no grade enrollment estimates were available. These schools received a special equal measure of size.