elementary, math, science, English/language arts, social studies, vocational/technical, or other), as well as whether the school felt the teacher would likely be teaching at the same school the following year.
Sampling was also done on an ongoing basis throughout the roster collection period. The Census Bureau first stratified teachers into five teacher types: (1) new teachers expected to be teaching at the same school the next school year, (2) experienced teachers expected to be teaching at the same school the next school year, (3) new teachers expected to leave the next school year, (4) mid-career teachers expected to leave the next school year, and (5) highly experienced teachers expected to leave the next school year. Before teachers were allocated to these strata, schools were first allocated an overall number of teachers to be selected within each school stratum. Sampling rates for teachers varied between the strata listed above. Private school teachers in above category 2 and all teachers in above categories 3-5 were oversampled at different rates. So that a school would not be overburdened by sampling too large a proportion of its teachers, the maximum number of teachers per school was set at 20. About 14 percent of the eligible public schools, 15 percent of the eligible private schools, and 13 percent of eligible BIE schools did not provide teacher lists. For these schools, no teachers were selected. Within each teacher stratum in each school, teachers were selected systematically with equal probability. About 56,360 teachers were sampled, 47,440 from public schools, 750 from BIE schools, and 8,180 from private schools (detail may not sum to totals because of rounding).
Principals. The principal of each sampled school was selected. About 12,910 school principals were sampled (9,800 public, 180 BIE, and 2,940 private) (detail may not sum to totals because of rounding).
Library media centers. A library media center in each sampled public and BIE school was also selected. Private schools were not included in the library media center survey because of NCES budget constraints. About 9,800 public school and 180 BIE school library media centers were sampled.
Data Collection Procedures
Before the administration of the 2007-08 SASS, several changes were made in the survey sample design, questionnaire content, procedures, and methodology. For details on these changes, see the Documentation for the 2007-08 Schools and Staffing Survey (Tourkin et al. forthcoming).
In 2007-08, SASS employed a mail-based survey approach, with subsequent telephone and field follow-up. In preparation for data collection, advance letters were mailed to the sampled schools in September 2007 to verify their addresses. School packages were